You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/06/10 03:39:38 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@53d163c96850c8476d479803c59344c6977ef9e8)
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 14174486e deploying docs (apache/tvm@53d163c96850c8476d479803c59344c6977ef9e8)
14174486e is described below
commit 14174486e074fc2d48481ac7f50e9ddcadbab3c0
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 10 03:39:33 2022 +0000
deploying docs (apache/tvm@53d163c96850c8476d479803c59344c6977ef9e8)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 1287 ++++++++++++++------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 188 ++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 226 ++--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 12 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 16 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 40 +-
docs/commit_hash | 2 +-
docs/genindex.html | 2 +
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 131 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 26 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 112 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../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 | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1287 ++++++++++++++------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 188 ++-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 226 ++--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 12 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/objects.inv | Bin 22599 -> 22611 bytes
docs/reference/api/doxygen/namespacemembers.html | 3 +
.../api/doxygen/namespacemembers_func_i.html | 3 +
.../api/doxygen/namespacemembers_func_p.html | 6 +-
docs/reference/api/doxygen/namespacemembers_i.html | 3 +
docs/reference/api/doxygen/namespacemembers_p.html | 6 +-
.../api/doxygen/namespacemembers_vars.html | 3 +
.../api/doxygen/namespacetvm_1_1tir_1_1attr.html | 19 +
.../doxygen/namespacetvm_1_1tir_1_1transform.html | 23 +
docs/reference/api/doxygen/search/all_11.js | 2 +-
docs/reference/api/doxygen/search/all_2.js | 1 +
docs/reference/api/doxygen/search/all_a.js | 1 +
docs/reference/api/doxygen/search/functions_10.js | 2 +-
docs/reference/api/doxygen/search/functions_9.js | 1 +
docs/reference/api/doxygen/search/variables_1.js | 1 +
docs/reference/api/doxygen/stmt_8h.html | 3 +
docs/reference/api/doxygen/stmt_8h_source.html | 41 +-
docs/reference/api/doxygen/tir_2transform_8h.html | 3 +
.../api/doxygen/tir_2transform_8h_source.html | 3 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 89 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
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 | 40 +-
138 files changed, 3217 insertions(+), 2148 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 e3585195d..65ddd51a9 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip288d684a-0d98-4373-ba6b-d2548f045e80 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip461d1bed-8d19-44ac-88ae-0c414f65a715 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 65957051f..e0205e7bc 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:08, 89.1kB/s]
0%| | 40.0k/41.5M [00:00<06:18, 115kB/s]
0%| | 80.0k/41.5M [00:00<04:25, 164kB/s]
0%| | 160k/41.5M [00:00<02:38, 274kB/s]
1%| | 336k/41.5M [00:00<01:21, 527kB/s]
2%|1 | 680k/41.5M [00:01<00:43, 996kB/s]
3%|2 | 1.22M/41.5M [00:01<00:24, 1.70MB/s]
4%|4 | 1.77M/41.5M [00:01<00:19, 2.16MB/s]
6%|5 | 2.33M/41.5M [00:01<00:16, 2.47MB/s]
7%|6 | 2.88M/41.5M [00:01<00:15, 2.68MB/s]
8%|8 | 3.44M/41.5M [00:02<00:14, 2.82MB/s]
10%|9 | 3.99M/41.5M [00:02<00:13, 2.92MB/s]
11%|# | 4.55M/41.5M [00:02<00:12, 3.07MB/s]
12%|#2 | 5.09M/41.5M [00:02<00:10, 3.58MB/s]
13%|#3 | 5.47M/41.5M [00:02<00:10, 3.63MB/s]
14%|#4 | 5.84M/41.5M [00:02<00:12, 3.08MB/s]
15%|#4 | 6.21M/41.5M [00:02<00
:11, 3.18MB/s]
16%|#6 | 6.77M/41.5M [00:03<00:11, 3.10MB/s]
18%|#7 | 7.33M/41.5M [00:03<00:10, 3.52MB/s]
19%|#8 | 7.69M/41.5M [00:03<00:10, 3.39MB/s]
19%|#9 | 8.02M/41.5M [00:03<00:12, 2.87MB/s]
20%|## | 8.46M/41.5M [00:03<00:12, 2.82MB/s]
22%|##1 | 9.02M/41.5M [00:03<00:11, 2.95MB/s]
23%|##3 | 9.59M/41.5M [00:04<00:11, 3.03MB/s]
24%|##4 | 10.2M/41.5M [00:04<00:10, 3.09MB/s]
26%|##5 | 10.7M/41.5M [00:04<00:10, 3.14MB/s]
27%|##7 | 11.3M/41.5M [00:04<00:08, 3.53MB/s]
29%|##8 | 11.9M/41.5M [00:04<00:08, 3.72MB/s]
29%|##9 | 12.2M/41.5M [00:04<00:08, 3.56MB/s]
30%|### | 12.6M/41.5M [00:04<00:10, 3.02MB/s]
31%|###1 | 13.0M/41.5M [00:05<00:08, 3.36MB/s]
33%|###2 | 13.6M/41.5M [00:05<00:07, 3.97MB/s]
34%|###3 | 14.0M/41.5M [00:05<00:08, 3.49MB/s]
35%|###4 | 14.4M/41.5M [00:05<00:09, 3.00MB/s]
36%|###5
| 14.8M/41.5M [00:05<00:08, 3.23MB/s]
37%|###7 | 15.4M/41.5M [00:05<00:07, 3.73MB/s]
38%|###8 | 15.8M/41.5M [00:05<00:07, 3.50MB/s]
39%|###8 | 16.2M/41.5M [00:06<00:08, 2.96MB/s]
40%|#### | 16.7M/41.5M [00:06<00:08, 3.05MB/s]
42%|####1 | 17.3M/41.5M [00:06<00:07, 3.58MB/s]
43%|####3 | 17.9M/41.5M [00:06<00:05, 4.16MB/s]
44%|####4 | 18.4M/41.5M [00:06<00:06, 3.78MB/s]
45%|####5 | 18.7M/41.5M [00:06<00:07, 3.21MB/s]
46%|####6 | 19.2M/41.5M [00:07<00:07, 3.22MB/s]
48%|####7 | 19.9M/41.5M [00:07<00:06, 3.40MB/s]
50%|####9 | 20.6M/41.5M [00:07<00:06, 3.56MB/s]
51%|#####1 | 21.3M/41.5M [00:07<00:05, 3.67MB/s]
53%|#####3 | 22.0M/41.5M [00:07<00:05, 3.77MB/s]
55%|#####4 | 22.7M/41.5M [00:07<00:05, 3.86MB/s]
57%|#####6 | 23.4M/41.5M [00:08<00:04, 3.96MB/s]
58%|#####8 | 24.2M/41.5M [00:08<00:04, 4.03MB/s]
60%|###### | 25.0M/41.5M [00:08<0
0:04, 4.13MB/s]
62%|######2 | 25.7M/41.5M [00:08<00:03, 4.68MB/s]
64%|######3 | 26.5M/41.5M [00:08<00:03, 5.21MB/s]
65%|######5 | 27.0M/41.5M [00:08<00:03, 4.73MB/s]
66%|######6 | 27.5M/41.5M [00:09<00:03, 4.06MB/s]
68%|######7 | 28.2M/41.5M [00:09<00:03, 4.02MB/s]
70%|######9 | 29.0M/41.5M [00:09<00:03, 4.28MB/s]
72%|#######2 | 29.9M/41.5M [00:09<00:02, 4.50MB/s]
74%|#######4 | 30.8M/41.5M [00:09<00:02, 5.21MB/s]
76%|#######6 | 31.7M/41.5M [00:09<00:01, 5.71MB/s]
78%|#######7 | 32.3M/41.5M [00:09<00:01, 5.48MB/s]
79%|#######9 | 32.8M/41.5M [00:10<00:01, 4.65MB/s]
81%|########1 | 33.6M/41.5M [00:10<00:01, 4.70MB/s]
83%|########3 | 34.6M/41.5M [00:10<00:01, 5.01MB/s]
86%|########5 | 35.6M/41.5M [00:10<00:01, 5.26MB/s]
88%|########8 | 36.7M/41.5M [00:10<00:00, 5.48MB/s]
91%|#########1| 37.8M/41.5M [00:11<00:00, 5.68MB/s]
94%|#########3| 38.9M/41.5M [00:11<00:00, 6.52MB/s]
96%|###
######6| 40.0M/41.5M [00:11<00:00, 7.47MB/s]
98%|#########8| 40.7M/41.5M [00:11<00:00, 6.79MB/s]
100%|#########9| 41.4M/41.5M [00:11<00:00, 5.88MB/s]
100%|##########| 41.5M/41.5M [00:11<00:00, 3.73MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:15, 87.8kB/s]
0%| | 48.0k/41.5M [00:00<05:12, 139kB/s]
0%| | 80.0k/41.5M [00:00<04:39, 155kB/s]
0%| | 136k/41.5M [00:00<03:22, 215kB/s]
1%| | 288k/41.5M [00:00<01:39, 436kB/s]
1%|1 | 568k/41.5M [00:01<00:53, 807kB/s]
2%|1 | 848k/41.5M [00:01<00:40, 1.04MB/s]
3%|2 | 1.12M/41.5M [00:01<00:34, 1.24MB/s]
3%|3 | 1.44M/41.5M [00:01<00:30, 1.40MB/s]
4%|4 | 1.76M/41.5M [00:01<00:27, 1.52MB/s]
5%|5 | 2.10M/41.5M [00:02<00:25, 1.64MB/s]
6%|5 | 2.46M/41.5M [00:02<00:23, 1.75MB/s]
7%|6 | 2.84M/41.5M [00:02<00:21, 1.86MB/s]
8%|7 | 3.23M/41.5M [00:02<00:20, 1.95MB/s]
9%|8 | 3.63M/41.5M [00:02<00:19, 2.05MB/s]
10%|9 | 4.06M/41.5M [00:03<00:18, 2.16MB/s]
11%|# | 4.52M/41.5M [00:03<00:
16, 2.28MB/s]
12%|#2 | 5.00M/41.5M [00:03<00:15, 2.40MB/s]
13%|#3 | 5.50M/41.5M [00:03<00:15, 2.52MB/s]
15%|#4 | 6.02M/41.5M [00:03<00:14, 2.64MB/s]
16%|#5 | 6.58M/41.5M [00:03<00:13, 2.78MB/s]
17%|#7 | 7.16M/41.5M [00:04<00:12, 2.91MB/s]
19%|#8 | 7.77M/41.5M [00:04<00:11, 3.06MB/s]
20%|## | 8.40M/41.5M [00:04<00:10, 3.20MB/s]
22%|##1 | 9.07M/41.5M [00:04<00:10, 3.37MB/s]
24%|##3 | 9.77M/41.5M [00:04<00:09, 3.52MB/s]
25%|##5 | 10.5M/41.5M [00:05<00:08, 3.71MB/s]
27%|##7 | 11.3M/41.5M [00:05<00:08, 3.89MB/s]
29%|##9 | 12.1M/41.5M [00:05<00:07, 4.09MB/s]
31%|###1 | 12.9M/41.5M [00:05<00:06, 4.29MB/s]
33%|###3 | 13.8M/41.5M [00:05<00:06, 4.51MB/s]
36%|###5 | 14.8M/41.5M [00:06<00:05, 4.73MB/s]
38%|###8 | 15.8M/41.5M [00:06<00:05, 4.97MB/s]
41%|#### | 16.8M/41.5M [00:06<00:04, 5.22MB/s]
43%|####3
| 17.9M/41.5M [00:06<00:04, 5.99MB/s]
46%|####5 | 19.0M/41.5M [00:06<00:03, 7.13MB/s]
48%|####7 | 19.8M/41.5M [00:06<00:03, 6.60MB/s]
49%|####9 | 20.4M/41.5M [00:06<00:03, 5.66MB/s]
52%|#####1 | 21.5M/41.5M [00:07<00:03, 6.37MB/s]
55%|#####4 | 22.8M/41.5M [00:07<00:02, 7.76MB/s]
57%|#####6 | 23.6M/41.5M [00:07<00:02, 7.29MB/s]
59%|#####8 | 24.3M/41.5M [00:07<00:02, 6.20MB/s]
62%|######1 | 25.7M/41.5M [00:07<00:02, 7.69MB/s]
65%|######5 | 27.1M/41.5M [00:07<00:01, 9.18MB/s]
68%|######7 | 28.0M/41.5M [00:07<00:01, 8.19MB/s]
70%|######9 | 28.9M/41.5M [00:08<00:01, 7.00MB/s]
73%|#######2 | 30.1M/41.5M [00:08<00:01, 8.02MB/s]
76%|#######5 | 31.5M/41.5M [00:08<00:01, 9.49MB/s]
78%|#######8 | 32.5M/41.5M [00:08<00:01, 8.39MB/s]
80%|######## | 33.4M/41.5M [00:08<00:01, 7.17MB/s]
83%|########3 | 34.5M/41.5M [00:08<00:00, 8.06MB/s]
87%|########6 | 35.9M/41.5M [00:08<00
:00, 9.49MB/s]
89%|########9 | 36.9M/41.5M [00:09<00:00, 8.42MB/s]
91%|#########1| 37.8M/41.5M [00:09<00:00, 7.19MB/s]
94%|#########3| 39.0M/41.5M [00:09<00:00, 8.05MB/s]
97%|#########7| 40.4M/41.5M [00:09<00:00, 9.54MB/s]
100%|#########9| 41.4M/41.5M [00:09<00:00, 8.43MB/s]
100%|##########| 41.5M/41.5M [00:09<00:00, 4.54MB/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 e93c217ce..1cd3e3660 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -210,7 +210,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.129 seconds)
+ **Total running time of the script:** ( 1 minutes 8.661 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 3d8cdb6a1..3b0ce7df0 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
4%|4 | 2.01M/44.7M [00:00<00:02, 20.6MB/s]
9%|8 | 3.97M/44.7M [00:00<00:02, 16.0MB/s]
13%|#3 | 6.00M/44.7M [00:00<00:02, 18.1MB/s]
17%|#7 | 7.79M/44.7M [00:00<00:02, 18.1MB/s]
22%|##1 | 9.62M/44.7M [00:00<00:01, 18.4MB/s]
27%|##6 | 11.9M/44.7M [00:00<00:01, 20.2MB/s]
31%|###1 | 13.9M/44.7M [00:00<00:01, 20.1MB/s]
36%|###5 | 15.9M/44.7M [00:00<00:01, 20.4MB/s]
41%|#### | 18.2M/44.7M [00:00<00:01, 21.5MB/s]
45%|####5 | 20.3M/44.7M [00:01<00:01, 20.9MB/s]
50%|##### | 22.4M/44.7M [00:01<00:01, 20.7MB/s]
55%|#####4 | 24.6M/44.7M [00:01<00:00, 21.3MB/s]
60%|#####9 | 26.7M/44.7M [00:01<00:00, 21.5MB/s]
64%|######4 | 28.7M/44.7M [00:01<00:00, 20.9MB/s]
69%|######8 | 30.8M/44.7M [00:01<00:00, 20.6MB/s]
73%|#######3 | 32.8M/44.7M [00:01<00:00, 20.5MB/s]
78%|#######7 | 34.7M/44.7M [00
:01<00:00, 20.3MB/s]
82%|########2 | 36.8M/44.7M [00:01<00:00, 20.5MB/s]
87%|########6 | 38.7M/44.7M [00:02<00:00, 20.0MB/s]
91%|######### | 40.6M/44.7M [00:02<00:00, 19.3MB/s]
96%|#########6| 43.0M/44.7M [00:02<00:00, 20.7MB/s]
100%|##########| 44.7M/44.7M [00:02<00:00, 20.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
29%|##8 | 12.9M/44.7M [00:00<00:00, 129MB/s]
57%|#####6 | 25.3M/44.7M [00:00<00:00, 130MB/s]
94%|#########3| 41.9M/44.7M [00:00<00:00, 149MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 147MB/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 fcf57b5dd..18604824c 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -381,7 +381,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.304 seconds)
+ **Total running time of the script:** ( 1 minutes 1.695 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 533adbe3e..18761c193 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,15 +5,15 @@
Computation times
=================
-**05:30.077** total execution time for **how_to_compile_models** files:
+**05:28.166** total execution time for **how_to_compile_models** files:
-- **01:07.129**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:00.304**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.175**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:36.918**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.072**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:23.305**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:22.323**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:20.915**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.440**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.496**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:08.661**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:01.695**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:57.537**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:35.301**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:23.932**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:22.900**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:21.964**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:18.952**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:14.316**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.908**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 931bb43aa..fd7b1973e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7251 15.7260 15.8028 15.6457 0.0499
+ 16.9240 16.1431 22.0168 16.0062 1.8231
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 9eca01ee8..bc86e2f3a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.62M/170M [00:00<00:03, 47.5MB/s]
5%|5 | 9.16M/170M [00:00<00:04, 34.5MB/s]
7%|7 | 12.6M/170M [00:00<00:04, 34.3MB/s]
9%|9 | 16.0M/170M [00:00<00:04, 33.5MB/s]
12%|#2 | 20.7M/170M [00:00<00:04, 38.4MB/s]
15%|#5 | 26.2M/170M [00:00<00:03, 44.7MB/s]
18%|#8 | 30.6M/170M [00:00<00:03, 42.4MB/s]
20%|## | 34.8M/170M [00:00<00:03, 37.5MB/s]
23%|##2 | 38.5M/170M [00:01<00:03, 34.7MB/s]
25%|##4 | 41.9M/170M [00:01<00:03, 33.9MB/s]
27%|##6 | 45.2M/170M [00:01<00:03, 33.1MB/s]
29%|##8 | 48.4M/170M [00:01<00:04, 29.3MB/s]
30%|### | 51.3M/170M [00:01<00:04, 28.0MB/s]
32%|###1 | 54.1M/170M [00:01<00:04, 28.2MB/s]
34%|###3 | 57.1M/170M [00:01<00:04, 29.0MB/s]
35%|###5 | 59.9M/170M [00:01<00:04, 28.6MB/s]
38%|###7 | 64.0M/170M [00:01<00:03, 32.7MB/
s]
40%|###9 | 67.2M/170M [00:02<00:04, 26.8MB/s]
41%|####1 | 69.9M/170M [00:02<00:03, 26.6MB/s]
43%|####3 | 73.1M/170M [00:02<00:03, 28.3MB/s]
45%|####5 | 76.6M/170M [00:02<00:03, 30.5MB/s]
47%|####6 | 79.6M/170M [00:02<00:03, 30.7MB/s]
49%|####9 | 83.9M/170M [00:02<00:02, 34.5MB/s]
52%|#####1 | 87.8M/170M [00:02<00:02, 36.3MB/s]
54%|#####3 | 91.3M/170M [00:02<00:02, 34.8MB/s]
56%|#####5 | 94.7M/170M [00:03<00:02, 34.8MB/s]
58%|#####7 | 98.0M/170M [00:03<00:02, 33.1MB/s]
60%|#####9 | 102M/170M [00:03<00:02, 34.5MB/s]
62%|######1 | 105M/170M [00:03<00:02, 30.7MB/s]
64%|######3 | 108M/170M [00:03<00:02, 29.9MB/s]
66%|######6 | 113M/170M [00:03<00:01, 33.2MB/s]
68%|######8 | 116M/170M [00:03<00:01, 33.3MB/s]
71%|####### | 121M/170M [00:03<00:01, 36.7MB/s]
73%|#######3 | 124M/170M [00:03<00:01, 34.4MB/s]
76%|#######6 | 129M/170M [00:04<00:01, 39.
9MB/s]
79%|#######9 | 135M/170M [00:04<00:00, 44.6MB/s]
82%|########1 | 139M/170M [00:04<00:00, 34.7MB/s]
85%|########4 | 144M/170M [00:04<00:00, 37.8MB/s]
87%|########6 | 148M/170M [00:04<00:00, 34.9MB/s]
89%|########8 | 151M/170M [00:04<00:00, 32.2MB/s]
91%|######### | 154M/170M [00:04<00:00, 31.6MB/s]
93%|#########2| 158M/170M [00:04<00:00, 30.9MB/s]
95%|#########4| 161M/170M [00:05<00:00, 29.0MB/s]
96%|#########6| 163M/170M [00:05<00:00, 28.5MB/s]
98%|#########7| 166M/170M [00:05<00:00, 23.5MB/s]
100%|#########9| 169M/170M [00:05<00:00, 25.6MB/s]
100%|##########| 170M/170M [00:05<00:00, 32.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 2.07M/170M [00:00<00:08, 21.1MB/s]
3%|2 | 4.81M/170M [00:00<00:06, 25.4MB/s]
5%|4 | 8.12M/170M [00:00<00:05, 29.4MB/s]
6%|6 | 10.9M/170M [00:00<00:06, 24.3MB/s]
8%|7 | 13.4M/170M [00:00<00:06, 24.0MB/s]
9%|9 | 15.7M/170M [00:00<00:07, 21.6MB/s]
10%|# | 17.8M/170M [00:00<00:07, 21.4MB/s]
12%|#1 | 19.9M/170M [00:00<00:07, 21.5MB/s]
13%|#2 | 22.0M/170M [00:01<00:07, 20.8MB/s]
15%|#4 | 25.3M/170M [00:01<00:06, 24.4MB/s]
18%|#7 | 29.8M/170M [00:01<00:04, 30.8MB/s]
19%|#9 | 32.8M/170M [00:01<00:05, 26.7MB/s]
21%|## | 35.4M/170M [00:01<00:05, 24.0MB/s]
23%|##2 | 38.7M/170M [00:01<00:05, 26.4MB/s]
24%|##4 | 41.3M/170M [00:01<00:05, 26.3MB/s]
26%|##5 | 43.9M/170M [00:01<00:04, 26.4MB/s]
27%|##7 | 46.5M/170M [00:02<00:06, 21.5MB/
s]
29%|##8 | 48.8M/170M [00:02<00:05, 21.4MB/s]
30%|##9 | 50.9M/170M [00:02<00:05, 20.8MB/s]
31%|###1 | 53.0M/170M [00:02<00:06, 19.8MB/s]
33%|###2 | 55.9M/170M [00:02<00:05, 22.0MB/s]
35%|###4 | 58.9M/170M [00:02<00:04, 24.7MB/s]
36%|###6 | 61.4M/170M [00:02<00:04, 23.0MB/s]
37%|###7 | 63.6M/170M [00:02<00:06, 16.3MB/s]
39%|###9 | 66.8M/170M [00:03<00:05, 19.7MB/s]
41%|#### | 69.2M/170M [00:03<00:04, 21.2MB/s]
43%|####2 | 72.9M/170M [00:03<00:03, 25.5MB/s]
45%|####4 | 75.7M/170M [00:03<00:03, 25.0MB/s]
46%|####6 | 78.8M/170M [00:03<00:03, 26.9MB/s]
48%|####7 | 81.5M/170M [00:03<00:03, 23.8MB/s]
49%|####9 | 83.9M/170M [00:03<00:03, 22.6MB/s]
51%|##### | 86.2M/170M [00:03<00:04, 19.4MB/s]
53%|#####2 | 89.3M/170M [00:04<00:03, 22.5MB/s]
55%|#####4 | 93.3M/170M [00:04<00:02, 27.2MB/s]
57%|#####7 | 96.8M/170M [00:04<00:
02, 29.8MB/s]
59%|#####8 | 100M/170M [00:04<00:02, 30.5MB/s]
61%|###### | 103M/170M [00:04<00:02, 25.9MB/s]
62%|######2 | 106M/170M [00:04<00:02, 23.5MB/s]
64%|######3 | 108M/170M [00:04<00:02, 22.3MB/s]
65%|######4 | 110M/170M [00:04<00:02, 21.5MB/s]
67%|######7 | 114M/170M [00:05<00:02, 24.9MB/s]
69%|######8 | 117M/170M [00:05<00:02, 27.3MB/s]
71%|####### | 120M/170M [00:05<00:01, 28.9MB/s]
73%|#######2 | 124M/170M [00:05<00:01, 30.3MB/s]
75%|#######4 | 127M/170M [00:05<00:01, 27.2MB/s]
76%|#######6 | 129M/170M [00:05<00:01, 27.4MB/s]
78%|#######7 | 132M/170M [00:05<00:01, 23.9MB/s]
79%|#######9 | 134M/170M [00:05<00:01, 22.5MB/s]
80%|######## | 137M/170M [00:05<00:01, 21.5MB/s]
82%|########1 | 139M/170M [00:06<00:01, 21.0MB/s]
83%|########3 | 141M/170M [00:06<00:01, 22.9MB/s]
86%|########5 | 146M/170M [00:06<00:00, 28.9MB/s]
87%|########7 | 149M/170M [00:06<00:00, 25
.0MB/s]
89%|########8 | 151M/170M [00:06<00:00, 20.6MB/s]
90%|######### | 153M/170M [00:06<00:00, 20.7MB/s]
91%|#########1| 155M/170M [00:06<00:00, 20.6MB/s]
93%|#########2| 157M/170M [00:07<00:00, 19.0MB/s]
94%|#########3| 160M/170M [00:07<00:00, 19.7MB/s]
95%|#########5| 162M/170M [00:07<00:00, 19.4MB/s]
97%|#########6| 164M/170M [00:07<00:00, 21.5MB/s]
98%|#########7| 166M/170M [00:07<00:00, 21.8MB/s]
100%|#########9| 169M/170M [00:07<00:00, 24.2MB/s]
100%|##########| 170M/170M [00:07<00:00, 23.4MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -262,7 +262,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 56.353 seconds)
+ **Total running time of the script:** ( 3 minutes 4.423 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 4d490fac1..e182ff336 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
17%|#7 | 2.33M/13.6M [00:00<00:00, 24.4MB/s]
34%|###4 | 4.66M/13.6M [00:00<00:00, 22.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 52.6MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
58%|#####8 | 7.91M/13.6M [00:00<00:00, 83.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 114MB/s]
@@ -353,7 +353,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3017 90.1979 94.5337 90.0353 0.5638
+ 90.5176 90.3609 95.9124 90.1418 0.6785
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.673 seconds)
+ **Total running time of the script:** ( 1 minutes 7.985 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 7daa7860c..d17540518 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -360,7 +360,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0483 120.0173 121.7086 119.2413 0.4115
+ 121.9156 121.8679 126.2616 121.1125 0.5568
@@ -394,7 +394,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 58.110 seconds)
+ **Total running time of the script:** ( 1 minutes 52.401 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 bdb7ce771..796f8f6af 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -223,7 +223,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 2.259 seconds)
+ **Total running time of the script:** ( 1 minutes 13.525 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 0183066d2..de3c3080d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5969/132723 [00:00<00:02, 59687.07KB/s]
11%|# | 13997/132723 [00:00<00:01, 71797.33KB/s]
17%|#6 | 22151/132723 [00:00<00:01, 76241.77KB/s]
23%|##2 | 30323/132723 [00:00<00:01, 78401.63KB/s]
29%|##9 | 38501/132723 [00:00<00:01, 79611.16KB/s]
35%|###5 | 46643/132723 [00:00<00:01, 80224.37KB/s]
41%|####1 | 54805/132723 [00:00<00:00, 80675.90KB/s]
47%|####7 | 62873/132723 [00:00<00:00, 80268.83KB/s]
54%|#####3 | 71033/132723 [00:00<00:00, 80682.02KB/s]
60%|#####9 | 79181/132723 [00:01<00:00, 80923.04KB/s]
66%|######5 | 87274/132723 [00:01<00:00, 80919.76KB/s]
72%|#######1 | 95423/132723 [00:01<00:00, 81091.57KB/s]
78%|#######8 | 103610/132723 [00:01<00:00, 81324.14KB/s]
84%|########4 | 111794/132723 [00:01<00:00, 81478.71KB/s]
90%|######### | 120006/132723 [00:01<00:00, 81669.07KB/s]
97%|########
#6| 128253/132723 [00:01<00:00, 81906.74KB/s]
100%|##########| 132723/132723 [00:01<00:00, 80138.91KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6217/132723 [00:00<00:02, 62164.28KB/s]
11%|#1 | 14859/132723 [00:00<00:01, 76429.28KB/s]
18%|#7 | 23429/132723 [00:00<00:01, 80660.78KB/s]
24%|##4 | 32166/132723 [00:00<00:01, 83299.95KB/s]
31%|### | 40846/132723 [00:00<00:01, 84559.90KB/s]
37%|###7 | 49514/132723 [00:00<00:00, 85271.44KB/s]
44%|####3 | 58156/132723 [00:00<00:00, 85644.71KB/s]
50%|##### | 66773/132723 [00:00<00:00, 85807.00KB/s]
57%|#####6 | 75429/132723 [00:00<00:00, 86039.00KB/s]
63%|######3 | 84127/132723 [00:01<00:00, 86326.64KB/s]
70%|######9 | 92792/132723 [00:01<00:00, 86418.62KB/s]
76%|#######6 | 101474/132723 [00:01<00:00, 86537.72KB/s]
83%|########3 | 110173/132723 [00:01<00:00, 86672.49KB/s]
90%|########9 | 118897/132723 [00:01<00:00, 86841.29KB/s]
96%|#########6| 127598/132723 [00:01<00:00, 86890.29KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 85067.40KB/s]
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 16.393 seconds)
+ **Total running time of the script:** ( 2 minutes 22.119 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 1081e7a1a..ddf4bafaf 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**11:09.343** total execution time for **how_to_deploy_models** files:
+**10:32.283** total execution time for **how_to_deploy_models** files:
-- **02:56.353**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:16.393**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:02.259**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:58.110**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:05.673**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.051**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.312**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.192**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:04.423**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:22.119**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:52.401**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:13.525**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:07.985**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.352**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.270**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index e55b2a575..da6147ae8 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -425,7 +425,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7d63bc9c-d6bb-477e-a93c-abb465d487bf from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8b0f5334-6bfb-4ea6-b887-e5aa850764d3 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 43cb90c04..040ea51f8 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:39.408** total execution time for **how_to_extend_tvm** files:
+**00:40.760** total execution time for **how_to_extend_tvm** files:
-- **00:35.763**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.361**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.084**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.201**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:36.919**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.504**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.121**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.215**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9c7e53eaa..332a167ea 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6607us [6607us] (45.58%; 45.58%)
- FoldScaleAxis: 7890us [6us] (54.42%; 54.42%)
- FoldConstant: 7884us [1577us] (54.38%; 99.92%)
- InferType: 6307us [6307us] (43.51%; 80.00%)
+ InferType: 6674us [6674us] (45.28%; 45.28%)
+ FoldScaleAxis: 8067us [7us] (54.72%; 54.72%)
+ FoldConstant: 8060us [1598us] (54.68%; 99.92%)
+ InferType: 6462us [6462us] (43.84%; 80.17%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6282us [6282us] (44.66%; 44.66%)
- FoldScaleAxis: 7783us [5us] (55.34%; 55.34%)
- FoldConstant: 7778us [1599us] (55.30%; 99.94%)
- InferType: 6179us [6179us] (43.94%; 79.44%)
+ InferType: 6606us [6606us] (44.95%; 44.95%)
+ FoldScaleAxis: 8089us [6us] (55.05%; 55.05%)
+ FoldConstant: 8084us [1658us] (55.01%; 99.93%)
+ InferType: 6426us [6426us] (43.73%; 79.49%)
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 36e38994e..03807b3d3 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.140683 ms
+ Convolution: 35.388811 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 c957ab638..44cd5acb6 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 8.908362 ms
+ conv2d with tensor core: 7.945374 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 ad730a804..1a993e2a5 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018261
- Baseline: 3.202010
+ Numpy running time: 0.019266
+ Baseline: 3.281024
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.298678
+ Opt1: 0.302436
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333377
+ Opt2: 0.339850
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120812
+ Opt3: 0.118524
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110605
+ Opt4: 0.112130
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110937
+ Opt5: 0.111390
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144911
+ Opt6: 0.145154
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 fdde9b524..684a73aa3 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:34.347** total execution time for **how_to_optimize_operators** files:
+**00:34.908** total execution time for **how_to_optimize_operators** files:
-- **00:31.712**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.432**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.203**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.198**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.485**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.225**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 4761dfd0c..b9b65a16b 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:11.562** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:35.679**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:19.744**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:42.592**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:16.714**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.494**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.339**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:21.613** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:42.079**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:21.061**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:43.318**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:17.052**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.238**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.865**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 560c57e71..053c3ded1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -187,7 +187,7 @@ file and apply it.
.. code-block:: none
-
+ .T
@@ -222,226 +222,483 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*18)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 21), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 42), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 896), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1120), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1232), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 84), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1456), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 105), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1792), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 119), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1904), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 133), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2128), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 140), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2240), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 154), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2464), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 161), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2576), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 168), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 175), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2800), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 182), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2912), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 196), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 203), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3248), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 210), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 217), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3472), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3584), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 231), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 238), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3808), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 245), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3920), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 259), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4144), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 266), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4256), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 273), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 280), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4480), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4592), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
- }
- for (rc.outer.inner: int32, 0, 16) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 208), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 272), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 304), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 352), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 400), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 416), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 464), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 496), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 544), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 592), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 608), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 656), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 688), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 736), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -494,7 +751,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.247 ms
+ Execution time of this operator: 0.368 ms
@@ -538,36 +795,36 @@ 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=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
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=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_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_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=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ 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=1)
- 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)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=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_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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)
@@ -587,14 +844,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ 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=64)
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=18)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=112)
+ 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=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -612,180 +869,430 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -844,7 +1351,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.679 seconds)
+ **Total running time of the script:** ( 2 minutes 42.079 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 f1c743447..cce9e14d1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -616,7 +616,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7860 9.7881 9.8175 9.7524 0.0266
+ 9.9910 10.0255 10.0279 9.9197 0.0505
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 e2a91d9bd..489410683 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -635,7 +635,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 757.0077 756.6604 758.5732 755.7894 1.1627
+ 761.7415 761.7363 764.4265 759.0616 2.1902
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.744 seconds)
+ **Total running time of the script:** ( 1 minutes 21.061 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 9afccca85..ae0784456 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -362,105 +362,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = ((i.outer.inner*256) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = (i.inner.init*16)
+ {
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = ((i.outer.inner*256) + (i.inner*16))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*256) + (i.inner*16)) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*256) + (i.inner*16)) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*256) + (i.inner*16)) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*256) + (i.inner*16)) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*256) + (i.inner*16)) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*256) + (i.inner*16)) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*256) + (i.inner*16)) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*256) + (i.inner*16)) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*256) + (i.inner*16)) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*256) + (i.inner*16)) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*256) + (i.inner*16)) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*256) + (i.inner*16)) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*256) + (i.inner*16)) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*16)) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*16)) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = (i.inner*16)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = ((i.inner*16) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = ((i.inner*16) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = ((i.inner*16) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = ((i.inner*16) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = ((i.inner*16) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = ((i.inner*16) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = ((i.inner*16) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = ((i.inner*16) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = ((i.inner*16) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = ((i.inner*16) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = ((i.inner*16) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = ((i.inner*16) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = ((i.inner*16) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = ((i.inner*16) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = ((i.inner*16) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
@@ -515,7 +513,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.108 ms
+ Execution time of this operator: 1.761 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 193af62f1..b8ca137af 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.256** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.760** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.406**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.214**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.840**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.240**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.226**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index e3886f9d5..cf5970d00 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
@@ -280,11 +280,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -336,11 +336,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -403,11 +403,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -459,11 +459,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -526,11 +526,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -582,11 +582,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -649,11 +649,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -705,11 +705,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -772,11 +772,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -828,11 +828,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 95.14/95.14 result: MeasureResult(costs=(0.0024332972916666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7711749076843262, timestamp=1654829526.2237127) [('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: 0.00/95.14 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.00/110.00 result: MeasureResult(costs=(0.0021045718958333337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.660846471786499, timestamp=1654830288.6228688) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -896,11 +896,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -952,11 +952,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1019,11 +1019,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1075,11 +1075,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1142,11 +1142,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1198,11 +1198,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1283,11 +1283,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1339,11 +1339,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1406,11 +1406,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1462,11 +1462,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1529,11 +1529,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1585,11 +1585,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1652,11 +1652,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1708,11 +1708,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1775,11 +1775,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1831,11 +1831,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1898,11 +1898,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1954,11 +1954,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2021,11 +2021,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2077,11 +2077,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2144,11 +2144,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2200,11 +2200,11 @@ for this template
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f21657e7fa2
+ 12: 0x00007f6395d54fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.87/143.87 result: MeasureResult(costs=(0.0016091146300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435838222503662, timestamp=1654829552.6920938) [('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: 143.01/143.01 result: MeasureResult(costs=(0.0016188032699999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.448167085647583, timestamp=1654830315.1207933) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.001968
+ Time cost of this operator: 0.001976
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 30ba28fc8..261d50054 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -294,10 +294,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.723 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.981 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 0.297 (1, 1, 10, 10, 3) 1 1
- Total_time - 313.606 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.8 98.746 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.965 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.289 (1, 1, 10, 10, 3) 1 1
+ Total_time - 318.797 - - - -
@@ -359,10 +359,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 90.1 96.84 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.034 2.186 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.974 (1, 1, 10, 10, 3) 1 1
- Total_time - 93.04 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 218.3 98.757 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 0.881 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.362 (1, 3, 10, 10, 1) 1 1
+ Total_time - 221.048 - - - -
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 052f7f636..26078fe86 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -297,8 +297,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpdm8a5676/images/target contains 8144 images
- /tmp/tmpdm8a5676/images/random contains 5000 images
+ /tmp/tmprbiuzyga/images/target contains 8144 images
+ /tmp/tmprbiuzyga/images/random contains 5000 images
@@ -459,11 +459,11 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 54s - loss: 0.2172 - accuracy: 0.9269 - val_loss: 0.1415 - val_accuracy: 0.9588
+ 328/328 - 54s - loss: 0.2114 - accuracy: 0.9290 - val_loss: 0.1325 - val_accuracy: 0.9611
Epoch 2/3
- 328/328 - 52s - loss: 0.1009 - accuracy: 0.9610 - val_loss: 0.1139 - val_accuracy: 0.9641
+ 328/328 - 52s - loss: 0.1005 - accuracy: 0.9637 - val_loss: 0.1097 - val_accuracy: 0.9622
Epoch 3/3
- 328/328 - 52s - loss: 0.0657 - accuracy: 0.9743 - val_loss: 0.1375 - val_accuracy: 0.9554
+ 328/328 - 52s - loss: 0.0619 - accuracy: 0.9772 - val_loss: 0.1015 - val_accuracy: 0.9698
@@ -825,7 +825,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 16.778 seconds)
+ **Total running time of the script:** ( 4 minutes 15.016 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 68c33f11e..089c0bb7e 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:02.561** total execution time for **how_to_work_with_microtvm** files:
-
-- **04:16.778**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
-- **00:41.546**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.643**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.196**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+**05:02.058** total execution time for **how_to_work_with_microtvm** files:
+
+- **04:15.016**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
+- **00:42.739**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.685**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
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 6f89acf93..a3e925271 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:12.136** total execution time for **how_to_work_with_relay** files:
+**00:14.060** total execution time for **how_to_work_with_relay** files:
-- **00:10.204**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.717**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.215**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:11.494**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:02.339**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index 7c3362c27..d5fcf548a 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.680** total execution time for **how_to_work_with_schedules** files:
+**00:06.003** total execution time for **how_to_work_with_schedules** files:
-- **00:02.076**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.168**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.742**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.706**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.300**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.238**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.235**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.215**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.158**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.306**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.747**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.737**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.320**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.251**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.232**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 0fc78764c..1f8cb0ae1 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpy4y86a27/input0.cc'\nsource_filename = \"/tmp/tmpy4y86a27/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/tmpo2wh2n71/input0.cc'\nsource_filename = \"/tmp/tmpo2wh2n71/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 4ee4ca6a8..6fdc0c9f4 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.653** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.424** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.454**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.199**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:21.206**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.218**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index db38439cd..2bc7120bf 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -267,7 +267,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 21.83s!
+ resnet18_v1 inference graph built in 22.69s!
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 f7e16f8e3..555df7c5a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -303,7 +303,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.32s!
+ yolov3-tiny inference graph built in 15.84s!
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 1adb8f262..9d15e63d9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:29.698** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.183** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.430**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:42.268**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:48.718**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:43.464**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index f30b59a78..87938a702 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.577** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.693** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.004**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.572**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.089**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.605**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 006ffae64..d6f8dda9a 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.059** total execution time for **topic_vta_tutorials** files:
+**00:01.116** total execution time for **topic_vta_tutorials** files:
-- **00:00.540**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.519**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.577**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.539**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index e83538156..2b550cf5e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -185,7 +185,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E
+
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.062 ms
+ Execution time of this operator: 93.083 ms
@@ -402,7 +402,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -415,11 +415,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 9.650 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 7bfa4cca3..179c2e342 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 493.83124857999974, 'median': 493.87870235000264, 'std': 1.0390778745483915}
+ {'mean': 494.38559051001903, 'median': 494.0007899000648, 'std': 1.4141552402738997}
@@ -494,31 +494,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.54/ 17.54 GFLOPS | Progress: (4/20) | 5.91 s
[Task 1/25] Current/Best: 6.16/ 17.54 GFLOPS | Progress: (8/20) | 8.85 s
[Task 1/25] Current/Best: 11.53/ 22.81 GFLOPS | Progress: (12/20) | 11.33 s
[Task 1/25] Current/Best: 16.79/ 22.84 GFLOPS | Progress: (16/20) | 13.01 s
[Task 1/25] Current/Best: 11.62/ 23.81 GFLOPS | Progress: (20/20) | 14.73 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.34/ 13.20 GFLOPS | Progress: (4/20) | 3.84 s
[Task 2/25] Current/Best: 14.09/ 17.59 GFLOPS | Progress: (8/20) | 5.15 s
[Task 2/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (12/20) | 6.49 s
[Task 2/25] Current/Best: 12.24/ 21.29 GFLOPS | Progress: (16/20) | 7.74 s
[Task 2/25] Current/Best: 19.42/ 21.29 GFLOPS | Progress: (20/20) | 9.36 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) | 5.77 s
[Task 3/25] Current/Best: 15.44/ 16.91 GFLOPS | Progress: (8/20) | 7.71 s
[Task 3/25] Current/Best: 14.93/ 16.91 GFLOPS | Progress: (12/20) | 9.42 s
[Task 3/25] Current/Best: 7.20/ 23.76 GFLOPS | Progress: (16/20) | 11.31 s
[Task 3/25] Current/Best: 11.96/ 23.76 GFLOPS | Progress: (20/20) | 15.85 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 20.49 GFLOPS | Progress: (4/20) | 2.30 s
[Task 4/25] Current/Best: 6.79/ 20.49 GFLOPS | Progress: (8/20) | 7.02 s
[Task 4/25] Current/Best: 22.37/ 22.37 GFLOPS | Progress: (12/20) | 12.00 s
[Task 4/25] Current/Best: 17.39/ 22.37 GFLOPS | Progress: (16/20) | 14.42 s
[Task 4/25] Current/Best: 13.42/ 22.37 GFLOPS | Progress: (20/20) | 16.38 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.61/ 10.49 GFLOPS | Progress: (4/20) | 2.49 s
[Task 5/25] Current/Best: 11.87/ 12.84 GFLOPS | Progress: (8/20) | 4.52 s
[Task 5/25] Current/Best: 11.84/ 18.08 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 11.92/ 22.68 GFLOPS | Progress: (16/20) | 9.14 s
[Task 5/25] Current/Best: 12.12/ 22.68 GFLOPS | Progress: (20/20) | 11.00 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.17/ 20.77 GFLOPS | Progress: (4/20) | 4.03 s
[Task 6/25] Current/Best: 19.02/ 20.77 GFLOPS | Progress: (8/20) | 5.78 s
[Task 6/25] Current/Best: 13.27/ 20.77 GFLOPS | Progress: (12/20) | 7.72 s
[Task 6/25] Current/Best: 20.07/ 20.77 GFLOPS | Progress: (16/20) | 9.96 s
[Task 6/25] Current/Best: 3.73/ 20.77 GFLOPS | Progress: (20/20) | 12.48 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.28/ 12.96 GFLOPS | Progress: (4/20) | 3.54 s
[Task 7/25] Current/Best: 20.32/ 20.77 GFLOPS | Progress: (8/20) | 5.05 s
[Task 7/25] Current/Best: 15.02/ 20.98 GFLOPS | Progress: (12/20) | 6.95 s
[Task 7/25] Current/Best: 12.28/ 20.98 GFLOPS | Progress: (16/20) | 8.98 s
[Task 7/25] Current/Best: 6.34/ 21.86 GFLOPS | Progress: (20/20) | 11.42 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.14/ 14.00 GFLOPS | Progress: (4/20) | 2.83 s
[Task 8/25] Current/Best: 10.31/ 14.00 GFLOPS | Progress: (8/20) | 7.95 s
[Task 8/25] Current/Best: 12.67/ 14.00 GFLOPS | Progress: (12/20) | 14.42 s
[Task 8/25] Current/Best: 18.83/ 18.83 GFLOPS | Progress: (16/20) | 16.49 s
[Task 8/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (20/20) | 23.55 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.72 GFLOPS | Progress: (4/20) | 11.87 s
[Task 9/25] Current/Best: 23.43/ 23.43 GFLOPS | Progress: (8/20) | 13.62 s
[Task 9/25] Current/Best: 8.28/ 23.43 GFLOPS | Progress: (12/20) | 16.17 s
[Task 9/25] Current/Best: 18.05/ 23.43 GFLOPS | Progress: (16/20) | 19.05 s
[Task 9/25] Current/Best: 9.08/ 23.43 GFLOPS | Progress: (20/20) | 27.78 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) | 2.52 s
[Task 10/25] Current/Best: 15.47/ 18.20 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 12.85/ 19.07 GFLOPS | Progress: (12/20) | 5.70 s
[Task 10/25] Current/Best: 19.13/ 20.49 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.86/ 20.49 GFLOPS | Progress: (20/20
) | 8.31 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.24/ 18.13 GFLOPS | Progress: (4/20) | 3.29 s
[Task 11/25] Current/Best: 16.92/ 18.13 GFLOPS | Progress: (8/20) | 6.14 s
[Task 11/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 8.21 s
[Task 11/25] Current/Best: 13.47/ 21.15 GFLOPS | Progress: (16/20) | 11.08 s
[Task 11/25] Current/Best: 19.52/ 21.24 GFLOPS | Progress: (20/20) | 13.18 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.13 GFLOPS | Progress: (4/20) | 5.72 s
[Task 12/25] Current/Best: 5.30/ 18.13 GFLOPS | Progress: (8/20) | 9.62 s
[Task 12/25] Current/Best: 19.18/ 19.18 GFLOPS | Progress: (12/20) | 11.59 s
[Task 12/25] Current/Best: 15.43/ 19.18 GFLOPS | Progress: (16/20) | 14.55 s
[Task 12/25] Current/Best: 15.05/ 19.18 GFLOPS | Progress: (20/20) | 16.45 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.66/ 17.26 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 16.02/ 21.09 GFLOPS | Progress: (8/20) | 6.25 s
[Task 13/25] Current/Best: 19.55/ 21.73 GFLOPS | Progress: (12/20) | 9.28 s
[Task 13/25] Current/Best: 12.21/ 21.73 GFLOPS | Progress: (16/20) | 12.71 s
[Task 13/25] Current/Best: 18.62/ 21.73 GFLOPS | Progress: (20/20) | 15.03 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.69/ 13.69 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.10/ 13.69 GFLOPS | Progress: (8/20) | 5.40 s
[Task 14/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (12/20) | 8.07 s
[Task 14/25] Current/Best: 16.40/ 20.54 GFLOPS | Progress: (16/20) | 9.71 s Done.
-
[Task 14/25] Current/Best: 17.48/ 20.54 GFLOPS | Progress: (20/20) | 11.41 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.16/ 17.66 GFLOPS | Progress: (4/20) | 2.59 s
[Task 15/25] Current/Best: 14.44/ 17.87 GFLOPS | Progress: (8/20) | 3.91 s
[Task 15/25] Current/Best: 10.35/ 22.40 GFLOPS | Progress: (12/20) | 6.16 s
[Task 15/25] Current/Best: 20.43/ 22.40 GFLOPS | Progress: (16/20) | 9.15 s
[Task 15/25] Current/Best: 9.69/ 22.40 GFLOPS | Progress: (20/20) | 10.11 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (4/20) | 2.87 s
[Task 16/25] Current/Best: 3.04/ 20.63 GFLOPS | Progress: (8/20) | 4.47 s
[Task 16/25] Current/Best: 19.28/ 20.63 GFLOPS | Progress: (12/20) | 5.68 s
[Task 16/25] Current/Best: 17.75/ 20.63 GFLOPS | Progress: (16/20) |
7.05 s
[Task 16/25] Current/Best: 9.94/ 22.37 GFLOPS | Progress: (20/20) | 9.20 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.40/ 18.92 GFLOPS | Progress: (4/20) | 4.75 s
[Task 17/25] Current/Best: 13.76/ 23.27 GFLOPS | Progress: (8/20) | 7.62 s
[Task 17/25] Current/Best: 16.75/ 23.27 GFLOPS | Progress: (12/20) | 9.67 s
[Task 17/25] Current/Best: 16.69/ 23.27 GFLOPS | Progress: (16/20) | 11.89 s
[Task 17/25] Current/Best: 10.05/ 23.27 GFLOPS | Progress: (20/20) | 14.04 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.46/ 17.89 GFLOPS | Progress: (4/20) | 3.73 s
[Task 18/25] Current/Best: 10.55/ 19.05 GFLOPS | Progress: (8/20) | 7.37 s
[Task 18/25] Current/Best: 19.61/ 19.61 GFLOPS | Progress: (12/20) | 9.30 s
[Task 18/25] Current/Best: 10.02/ 19.61 GFLOPS | Progress: (16/20) | 13.15 s
[Task 18/25] Current/Best: 20.41/ 20.41 GFLOPS | Progress: (20/20) | 14.65 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.21/ 20.49 GFLOPS | Progress: (4/20) | 5.98 s
[Task 19/25] Current/Best: 2.61/ 20.49 GFLOPS | Progress: (8/20) | 9.34 s
[Task 19/25] Current/Best: 20.23/ 21.91 GFLOPS | Progress: (12/20) | 12.35 s
[Task 19/25] Current/Best: 14.05/ 21.91 GFLOPS | Progress: (16/20) | 15.47 s
[Task 19/25] Current/Best: 2.70/ 23.58 GFLOPS | Progress: (20/20) | 18.30 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.85/ 15.24 GFLOPS | Progress: (4/20) | 3.23 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (4/20) | 6.10 s
[Task 1/25] Current/Best: 6.14/ 17.43 GFLOPS | Progress: (8/20) | 9.07 s
[Task 1/25] Current/Best: 11.49/ 22.66 GFLOPS | Progress: (12/20) | 11.49 s
[Task 1/25] Current/Best: 16.84/ 22.84 GFLOPS | Progress: (16/20) | 13.17 s
[Task 1/25] Current/Best: 11.55/ 23.82 GFLOPS | Progress: (20/20) | 14.90 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.29/ 13.03 GFLOPS | Progress: (4/20) | 3.71 s
[Task 2/25] Current/Best: 14.21/ 17.90 GFLOPS | Progress: (8/20) | 5.01 s
[Task 2/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 6.35 s
[Task 2/25] Current/Best: 12.26/ 21.22 GFLOPS | Progress: (16/20) | 7.60 s
[Task 2/25] Current/Best: 19.61/ 21.22 GFLOPS | Progress: (20/20) | 9.21 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.52 GFLOPS | Progress: (4/20) | 5.80 s
[Task 3/25] Current/Best: 15.54/ 16.83 GFLOPS | Progress: (8/20) | 7.70 s
[Task 3/25] Current/Best: 14.91/ 16.83 GFLOPS | Progress: (12/20) | 9.44 s
[Task 3/25] Current/Best: 7.20/ 23.81 GFLOPS | Progress: (16/20) | 11.37 s
[Task 3/25] Current/Best: 12.56/ 23.81 GFLOPS | Progress: (20/20) | 15.89 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 19.15 GFLOPS | Progress: (4/20) | 2.32 s
[Task 4/25] Current/Best: 6.68/ 19.15 GFLOPS | Progress: (8/20) | 6.68 s
[Task 4/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (12/20) | 11.10 s
[Task 4/25] Current/Best: 16.53/ 22.05 GFLOPS | Progress: (16/20) | 13.32 s
[Task 4/25] Current/Best: 13.36/ 22.05 GFLOPS | Progress: (20/20) | 15.33 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.67/ 10.45 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.82/ 12.64 GFLOPS | Progress: (8/20) | 4.59 s
[Task 5/25] Current/Best: 11.53/ 18.07 GFLOPS | Progress: (12/20) | 7.52 s
[Task 5/25] Current/Best: 11.88/ 22.55 GFLOPS | Progress: (16/20) | 8.96 s
[Task 5/25] Current/Best: 12.03/ 22.55 GFLOPS | Progress: (20/20) | 10.80 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.73 GFLOPS | Progress: (4/20) | 3.90 s
[Task 6/25] Current/Best: 18.95/ 20.73 GFLOPS | Progress: (8/20) | 5.64 s
[Task 6/25] Current/Best: 13.31/ 20.73 GFLOPS | Progress: (12/20) | 7.55 s
[Task 6/25] Current/Best: 19.90/ 20.73 GFLOPS | Progress: (16/20) | 9.78 s
[Task 6/25] Current/Best: 3.73/ 20.73 GFLOPS | Progress: (20/20) | 12.27 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.20/ 12.85 GFLOPS | Progress: (4/20) | 3.54 s
[Task 7/25] Current/Best: 20.07/ 21.01 GFLOPS | Progress: (8/20) | 5.04 s
[Task 7/25] Current/Best: 15.93/ 21.01 GFLOPS | Progress: (12/20) | 6.94 s
[Task 7/25] Current/Best: 12.24/ 21.01 GFLOPS | Progress: (16/20) | 8.97 s
[Task 7/25] Current/Best: 6.34/ 21.68 GFLOPS | Progress: (20/20) | 11.42 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.16/ 14.32 GFLOPS | Progress: (4/20) | 2.82 s
[Task 8/25] Current/Best: 10.07/ 14.32 GFLOPS | Progress: (8/20) | 7.55 s
[Task 8/25] Current/Best: 12.48/ 14.32 GFLOPS | Progress: (12/20) | 13.71 s
[Task 8/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (16/20) | 15.79 s
[Task 8/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (20/20) | 22.28 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.32/ 14.96 GFLOPS | Progress: (4/20) | 11.89 s
[Task 9/25] Current/Best: 23.49/ 23.49 GFLOPS | Progress: (8/20) | 13.64 s
[Task 9/25] Current/Best: 8.26/ 23.49 GFLOPS | Progress: (12/20) | 15.99 s
[Task 9/25] Current/Best: 17.90/ 23.49 GFLOPS | Progress: (16/20) | 18.65 s
[Task 9/25] Current/Best: 8.99/ 23.49 GFLOPS | Progress: (20/20) | 26.26 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 2.50 s
[Task 10/25] Current/Best: 15.48/ 18.25 GFLOPS | Progress: (8/20) | 4.10 s
[Task 10/25] Current/Best: 12.58/ 18.92 GFLOPS | Progress: (12/20) | 5.61 s
[Task 10/25] Current/Best: 19.15/ 20.46 GFLOPS | Progress: (16/20) | 6.72 s
[Task 10/25] Current/Best: 8.89/ 20.46 GFLOPS | Progress: (20/20
) | 8.24 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.29/ 18.17 GFLOPS | Progress: (4/20) | 3.20 s
[Task 11/25] Current/Best: 15.44/ 18.17 GFLOPS | Progress: (8/20) | 5.94 s
[Task 11/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (12/20) | 7.96 s
[Task 11/25] Current/Best: 13.31/ 21.22 GFLOPS | Progress: (16/20) | 10.65 s
[Task 11/25] Current/Best: 19.54/ 21.57 GFLOPS | Progress: (20/20) | 12.67 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.83/ 18.09 GFLOPS | Progress: (4/20) | 5.30 s
[Task 12/25] Current/Best: 5.28/ 18.09 GFLOPS | Progress: (8/20) | 8.99 s
[Task 12/25] Current/Best: 18.88/ 18.96 GFLOPS | Progress: (12/20) | 10.97 s
[Task 12/25] Current/Best: 15.39/ 18.96 GFLOPS | Progress: (16/20) | 13.73 s
[Task 12/25] Current/Best: 15.10/ 18.96 GFLOPS | Progress: (20/20) | 15.65 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.81/ 17.28 GFLOPS | Progress: (4/20) | 3.60 s
[Task 13/25] Current/Best: 16.02/ 20.95 GFLOPS | Progress: (8/20) | 6.00 s
[Task 13/25] Current/Best: 19.37/ 21.56 GFLOPS | Progress: (12/20) | 8.92 s
[Task 13/25] Current/Best: 12.24/ 21.56 GFLOPS | Progress: (16/20) | 12.35 s
[Task 13/25] Current/Best: 18.78/ 21.56 GFLOPS | Progress: (20/20) | 14.64 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.10/ 13.60 GFLOPS | Progress: (8/20) | 5.40 s
[Task 14/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (12/20) | 7.94 s
[Task 14/25] Current/Best: 15.41/ 20.50 GFLOPS | Progress: (16/20) | 9.60 s Done.
+
[Task 14/25] Current/Best: 17.16/ 20.50 GFLOPS | Progress: (20/20) | 11.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.11/ 17.62 GFLOPS | Progress: (4/20) | 2.64 s
[Task 15/25] Current/Best: 14.49/ 18.05 GFLOPS | Progress: (8/20) | 3.97 s
[Task 15/25] Current/Best: 10.40/ 22.29 GFLOPS | Progress: (12/20) | 6.02 s
[Task 15/25] Current/Best: 20.39/ 22.29 GFLOPS | Progress: (16/20) | 8.94 s
[Task 15/25] Current/Best: 9.68/ 22.29 GFLOPS | Progress: (20/20) | 9.91 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.78/ 19.78 GFLOPS | Progress: (4/20) | 2.87 s
[Task 16/25] Current/Best: 3.04/ 19.78 GFLOPS | Progress: (8/20) | 4.50 s
[Task 16/25] Current/Best: 19.52/ 19.78 GFLOPS | Progress: (12/20) | 5.71 s
[Task 16/25] Current/Best: 17.86/ 19.78 GFLOPS | Progress: (16/20) |
7.04 s
[Task 16/25] Current/Best: 10.01/ 22.21 GFLOPS | Progress: (20/20) | 9.06 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.33/ 18.76 GFLOPS | Progress: (4/20) | 4.65 s
[Task 17/25] Current/Best: 14.40/ 23.18 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 16.82/ 23.18 GFLOPS | Progress: (12/20) | 9.51 s
[Task 17/25] Current/Best: 16.54/ 23.18 GFLOPS | Progress: (16/20) | 11.66 s
[Task 17/25] Current/Best: 10.05/ 23.18 GFLOPS | Progress: (20/20) | 13.78 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.11/ 17.62 GFLOPS | Progress: (4/20) | 3.65 s
[Task 18/25] Current/Best: 10.52/ 20.05 GFLOPS | Progress: (8/20) | 7.15 s
[Task 18/25] Current/Best: 18.86/ 20.05 GFLOPS | Progress: (12/20) | 9.08 s
[Task 18/25] Current/Best: 10.00/ 20.05 GFLOPS | Progress: (16/20) | 12.63 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.13 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.88/ 20.02 GFLOPS | Progress: (4/20) | 5.98 s
[Task 19/25] Current/Best: 2.61/ 20.02 GFLOPS | Progress: (8/20) | 9.24 s
[Task 19/25] Current/Best: 19.47/ 21.24 GFLOPS | Progress: (12/20) | 12.04 s
[Task 19/25] Current/Best: 15.33/ 21.27 GFLOPS | Progress: (16/20) | 14.81 s
[Task 19/25] Current/Best: 2.70/ 23.02 GFLOPS | Progress: (20/20) | 17.57 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.25/ 14.78 GFLOPS | Progress: (4/20) | 3.25 s Done.
Done.
-
[Task 20/25] Current/Best: 9.99/ 15.24 GFLOPS | Progress: (8/20) | 6.74 s
[Task 20/25] Current/Best: 2.32/ 15.96 GFLOPS | Progress: (12/20) | 10.78 s
[Task 20/25] Current/Best: 12.35/ 15.96 GFLOPS | Progress: (16/20) | 14.69 s
[Task 20/25] Current/Best: 13.00/ 22.30 GFLOPS | Progress: (20/20) | 16.82 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.67 GFLOPS | Progress: (4/20) | 3.20 s
[Task 21/25] Current/Best: 14.64/ 17.67 GFLOPS | Progress: (8/20) | 4.77 s
[Task 21/25] Current/Best: 1.61/ 17.67 GFLOPS | Progress: (12/20) | 6.90 s
[Task 21/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (16/20) | 10.41 s
[Task 21/25] Current/Best: 4.47/ 18.16 GFLOPS | Progress: (20/20) | 17.64 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20
) | 2.59 s
[Task 22/25] Current/Best: 8.72/ 21.98 GFLOPS | Progress: (8/20) | 4.62 s
[Task 22/25] Current/Best: 19.98/ 21.98 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 15.54/ 21.98 GFLOPS | Progress: (16/20) | 9.12 s
[Task 22/25] Current/Best: 14.19/ 21.98 GFLOPS | Progress: (20/20) | 10.78 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.40/ 20.88 GFLOPS | Progress: (4/20) | 3.15 s
[Task 23/25] Current/Best: 14.30/ 20.88 GFLOPS | Progress: (8/20) | 6.52 s
[Task 23/25] Current/Best: 21.04/ 21.51 GFLOPS | Progress: (12/20) | 8.34 s
[Task 23/25] Current/Best: 6.48/ 21.51 GFLOPS | Progress: (16/20) | 15.43 s
[Task 23/25] Current/Best: 8.02/ 21.51 GFLOPS | Progress: (20/20) | 19.66 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.60/ 8.60 GFLOPS | Progress: (4/20) | 11.72 s
[Task 24/25] Current/Best: 2.15/ 8.60 GFLOPS | Progress: (8/20) | 22.69 s
[Task 24/25] Current/Best: 4.50/ 8.60 GFLOPS | Progress: (12/20) | 34.16 s Done.
+
[Task 20/25] Current/Best: 10.16/ 14.78 GFLOPS | Progress: (8/20) | 6.66 s
[Task 20/25] Current/Best: 2.33/ 16.52 GFLOPS | Progress: (12/20) | 10.50 s
[Task 20/25] Current/Best: 12.04/ 16.52 GFLOPS | Progress: (16/20) | 14.09 s
[Task 20/25] Current/Best: 12.81/ 21.87 GFLOPS | Progress: (20/20) | 16.18 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.69 GFLOPS | Progress: (4/20) | 3.18 s
[Task 21/25] Current/Best: 14.58/ 17.69 GFLOPS | Progress: (8/20) | 4.76 s
[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 6.87 s
[Task 21/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (16/20) | 10.27 s
[Task 21/25] Current/Best: 4.46/ 18.21 GFLOPS | Progress: (20/20) | 17.45 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20
) | 2.62 s
[Task 22/25] Current/Best: 9.09/ 21.93 GFLOPS | Progress: (8/20) | 4.50 s
[Task 22/25] Current/Best: 19.98/ 21.93 GFLOPS | Progress: (12/20) | 6.83 s
[Task 22/25] Current/Best: 15.41/ 21.93 GFLOPS | Progress: (16/20) | 8.91 s
[Task 22/25] Current/Best: 15.20/ 21.93 GFLOPS | Progress: (20/20) | 10.64 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.42/ 20.40 GFLOPS | Progress: (4/20) | 3.18 s
[Task 23/25] Current/Best: 15.06/ 20.40 GFLOPS | Progress: (8/20) | 6.42 s
[Task 23/25] Current/Best: 20.88/ 21.50 GFLOPS | Progress: (12/20) | 8.21 s
[Task 23/25] Current/Best: 6.19/ 21.50 GFLOPS | Progress: (16/20) | 15.25 s
[Task 23/25] Current/Best: 7.65/ 21.50 GFLOPS | Progress: (20/20) | 19.48 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.54/ 8.54 GFLOPS | Progress: (4/20) | 11.73 s
[Task 24/25] Current/Best: 2.12/ 8.54 GFLOPS | Progress: (8/20) | 22.72 s
[Task 24/25] Current/Best: 4.42/ 8.54 GFLOPS | Progress: (12/20) | 34.21 s Done.
Done.
-
[Task 24/25] Current/Best: 6.35/ 8.79 GFLOPS | Progress: (16/20) | 39.86 s
[Task 24/25] Current/Best: 3.35/ 9.10 GFLOPS | Progress: (20/20) | 45.78 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/ 2.94 GFLOPS | Progress: (4/20) | 11.55 s
[Task 25/25] Current/Best: 6.06/ 8.12 GFLOPS | Progress: (8/20) | 22.79 s
[Task 25/25] Current/Best: 5.95/ 8.12 GFLOPS | Progress: (12/20) | 34.21 s
[Task 25/25] Current/Best: 5.85/ 9.35 GFLOPS | Progress: (16/20) | 36.05 s
[Task 25/25] Current/Best: 2.93/ 9.35 GFLOPS | Progress: (20/20) | 46.75 s
+
[Task 24/25] Current/Best: 6.84/ 8.65 GFLOPS | Progress: (16/20) | 39.90 s
[Task 24/25] Current/Best: 3.31/ 8.87 GFLOPS | Progress: (20/20) | 45.74 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.90 GFLOPS | Progress: (4/20) | 11.54 s
[Task 25/25] Current/Best: 5.65/ 7.95 GFLOPS | Progress: (8/20) | 22.76 s
[Task 25/25] Current/Best: 5.83/ 7.95 GFLOPS | Progress: (12/20) | 34.18 s
[Task 25/25] Current/Best: 5.72/ 9.21 GFLOPS | Progress: (16/20) | 35.91 s
[Task 25/25] Current/Best: 2.91/ 9.21 GFLOPS | Progress: (20/20) | 46.57 s
The output from this tuning process will look something like this:
@@ -660,8 +660,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.9135935800041, 'median': 409.76144020003176, 'std': 0.8093259332125134}
- unoptimized: {'mean': 493.83124857999974, 'median': 493.87870235000264, 'std': 1.0390778745483915}
+ optimized: {'mean': 411.4217706399995, 'median': 411.6572982499292, 'std': 0.5800148917026019}
+ unoptimized: {'mean': 494.38559051001903, 'median': 494.0007899000648, 'std': 1.4141552402738997}
@@ -681,7 +681,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 19.027 seconds)
+ **Total running time of the script:** ( 10 minutes 11.567 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 647a5ba7b..d13821f57 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.224e-07 secs/op
+ 1.243e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index ef3f1856b..57e2e2370 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -232,7 +232,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x1ae38010)), stage(b, placeholder(b, 0x22cb9760)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x6b54b40)), stage(b, placeholder(b, 0x1b0f8330)), 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 e30950190..af38a20f4 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**13:19.970** total execution time for **tutorial** files:
+**12:57.460** total execution time for **tutorial** files:
-- **10:19.027**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:09.650**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:58.267**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:28.201**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.267**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.709**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.545**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.183**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.033**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.030**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.029**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.029**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **10:11.567**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:59.560**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:51.737**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:28.231**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:24.603**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.740**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.622**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.225**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.046**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.044**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.043**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.043**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 1c85eec80..cede61d2a 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -397,7 +397,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000024
+ vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.130619999064948e-06 1.0
- naive 5.838e-06 0.7180264236517501
- parallel 6.075200000000001e-06 0.7472000906079329
- vector 2.4487900000000003e-05 3.0118121376741507
+ numpy 8.177959998647565e-06 1.0
+ naive 5.8407e-06 0.714200118485039
+ parallel 6.2239e-06 0.7610577700342482
+ vector 2.4567499999999998e-05 3.0041110501962422
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017809
+ Numpy running time: 0.019267
@@ -897,7 +897,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.211416
+ none: 3.279954
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.303490
+ blocking: 0.313294
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.334297
+ vectorization: 0.346823
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1160,7 +1160,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.114022
+ loop permutation: 0.118491
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1257,7 +1257,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108416
+ array packing: 0.108216
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1348,7 +1348,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110537
+ block caching: 0.110127
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144124
+ parallelization: 0.144288
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1511,13 +1511,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2114159866999996 1.0
- blocking 0.3034896865 0.09450338659236147
- vectorization 0.3342967753 0.1040963788822382
- loop permutation 0.114022479 0.03550535946517713
- array packing 0.1084157899 0.03375949747681438
- block caching 0.11053706519999999 0.03442003952704556
- parallelization 0.1441237516 0.044878568269226086
+ none 3.2799536868000003 1.0
+ blocking 0.3132937217 0.09551772726573365
+ vectorization 0.3468233414 0.10574031663793673
+ loop permutation 0.1184905767 0.03612568591345026
+ array packing 0.10821571420000001 0.03299306165068989
+ block caching 0.11012685650000001 0.03357573521333539
+ parallelization 0.1442875817 0.04399073751580022
diff --git a/docs/commit_hash b/docs/commit_hash
index e4669e6f0..62b821368 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-0b46efa33e045ab4d892e40c1f5084dd6651c8b6
+53d163c96850c8476d479803c59344c6977ef9e8
diff --git a/docs/genindex.html b/docs/genindex.html
index 3086da3f1..7c8750373 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -2091,6 +2091,8 @@
<li><a href="reference/api/python/tir.html#tvm.tir.transform.InjectDoubleBuffer">InjectDoubleBuffer() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.InjectPrefetch">InjectPrefetch() (in module tvm.tir.transform)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.transform.InjectPTXAsyncCopy">InjectPTXAsyncCopy() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.InjectRollingBuffer">InjectRollingBuffer() (in module tvm.tir.transform)</a>
</li>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 88793f9f8..707f2262f 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip288d684a-0d98-4373-ba6b-d2548f045e80 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip461d1bed-8d19-44ac-88ae-0c414f65a715 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 2cf2d75b3..e3a0ff9be 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,79 +406,64 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<08:08, 89.1kB/s]
- 0%| | 40.0k/41.5M [00:00<06:18, 115kB/s]
- 0%| | 80.0k/41.5M [00:00<04:25, 164kB/s]
- 0%| | 160k/41.5M [00:00<02:38, 274kB/s]
- 1%| | 336k/41.5M [00:00<01:21, 527kB/s]
- 2%|1 | 680k/41.5M [00:01<00:43, 996kB/s]
- 3%|2 | 1.22M/41.5M [00:01<00:24, 1.70MB/s]
- 4%|4 | 1.77M/41.5M [00:01<00:19, 2.16MB/s]
- 6%|5 | 2.33M/41.5M [00:01<00:16, 2.47MB/s]
- 7%|6 | 2.88M/41.5M [00:01<00:15, 2.68MB/s]
- 8%|8 | 3.44M/41.5M [00:02<00:14, 2.82MB/s]
- 10%|9 | 3.99M/41.5M [00:02<00:13, 2.92MB/s]
- 11%|# | 4.55M/41.5M [00:02<00:12, 3.07MB/s]
- 12%|#2 | 5.09M/41.5M [00:02<00:10, 3.58MB/s]
- 13%|#3 | 5.47M/41.5M [00:02<00:10, 3.63MB/s]
- 14%|#4 | 5.84M/41.5M [00:02<00:12, 3.08MB/s]
- 15%|#4 | 6.21M/41.5M [00:02<00:11, 3.18MB/s]
- 16%|#6 | 6.77M/41.5M [00:03<00:11, 3.10MB/s]
- 18%|#7 | 7.33M/41.5M [00:03<00:10, 3.52MB/s]
- 19%|#8 | 7.69M/41.5M [00:03<00:10, 3.39MB/s]
- 19%|#9 | 8.02M/41.5M [00:03<00:12, 2.87MB/s]
- 20%|## | 8.46M/41.5M [00:03<00:12, 2.82MB/s]
- 22%|##1 | 9.02M/41.5M [00:03<00:11, 2.95MB/s]
- 23%|##3 | 9.59M/41.5M [00:04<00:11, 3.03MB/s]
- 24%|##4 | 10.2M/41.5M [00:04<00:10, 3.09MB/s]
- 26%|##5 | 10.7M/41.5M [00:04<00:10, 3.14MB/s]
- 27%|##7 | 11.3M/41.5M [00:04<00:08, 3.53MB/s]
- 29%|##8 | 11.9M/41.5M [00:04<00:08, 3.72MB/s]
- 29%|##9 | 12.2M/41.5M [00:04<00:08, 3.56MB/s]
- 30%|### | 12.6M/41.5M [00:04<00:10, 3.02MB/s]
- 31%|###1 | 13.0M/41.5M [00:05<00:08, 3.36MB/s]
- 33%|###2 | 13.6M/41.5M [00:05<00:07, 3.97MB/s]
- 34%|###3 | 14.0M/41.5M [00:05<00:08, 3.49MB/s]
- 35%|###4 | 14.4M/41.5M [00:05<00:09, 3.00MB/s]
- 36%|###5 | 14.8M/41.5M [00:05<00:08, 3.23MB/s]
- 37%|###7 | 15.4M/41.5M [00:05<00:07, 3.73MB/s]
- 38%|###8 | 15.8M/41.5M [00:05<00:07, 3.50MB/s]
- 39%|###8 | 16.2M/41.5M [00:06<00:08, 2.96MB/s]
- 40%|#### | 16.7M/41.5M [00:06<00:08, 3.05MB/s]
- 42%|####1 | 17.3M/41.5M [00:06<00:07, 3.58MB/s]
- 43%|####3 | 17.9M/41.5M [00:06<00:05, 4.16MB/s]
- 44%|####4 | 18.4M/41.5M [00:06<00:06, 3.78MB/s]
- 45%|####5 | 18.7M/41.5M [00:06<00:07, 3.21MB/s]
- 46%|####6 | 19.2M/41.5M [00:07<00:07, 3.22MB/s]
- 48%|####7 | 19.9M/41.5M [00:07<00:06, 3.40MB/s]
- 50%|####9 | 20.6M/41.5M [00:07<00:06, 3.56MB/s]
- 51%|#####1 | 21.3M/41.5M [00:07<00:05, 3.67MB/s]
- 53%|#####3 | 22.0M/41.5M [00:07<00:05, 3.77MB/s]
- 55%|#####4 | 22.7M/41.5M [00:07<00:05, 3.86MB/s]
- 57%|#####6 | 23.4M/41.5M [00:08<00:04, 3.96MB/s]
- 58%|#####8 | 24.2M/41.5M [00:08<00:04, 4.03MB/s]
- 60%|###### | 25.0M/41.5M [00:08<00:04, 4.13MB/s]
- 62%|######2 | 25.7M/41.5M [00:08<00:03, 4.68MB/s]
- 64%|######3 | 26.5M/41.5M [00:08<00:03, 5.21MB/s]
- 65%|######5 | 27.0M/41.5M [00:08<00:03, 4.73MB/s]
- 66%|######6 | 27.5M/41.5M [00:09<00:03, 4.06MB/s]
- 68%|######7 | 28.2M/41.5M [00:09<00:03, 4.02MB/s]
- 70%|######9 | 29.0M/41.5M [00:09<00:03, 4.28MB/s]
- 72%|#######2 | 29.9M/41.5M [00:09<00:02, 4.50MB/s]
- 74%|#######4 | 30.8M/41.5M [00:09<00:02, 5.21MB/s]
- 76%|#######6 | 31.7M/41.5M [00:09<00:01, 5.71MB/s]
- 78%|#######7 | 32.3M/41.5M [00:09<00:01, 5.48MB/s]
- 79%|#######9 | 32.8M/41.5M [00:10<00:01, 4.65MB/s]
- 81%|########1 | 33.6M/41.5M [00:10<00:01, 4.70MB/s]
- 83%|########3 | 34.6M/41.5M [00:10<00:01, 5.01MB/s]
- 86%|########5 | 35.6M/41.5M [00:10<00:01, 5.26MB/s]
- 88%|########8 | 36.7M/41.5M [00:10<00:00, 5.48MB/s]
- 91%|#########1| 37.8M/41.5M [00:11<00:00, 5.68MB/s]
- 94%|#########3| 38.9M/41.5M [00:11<00:00, 6.52MB/s]
- 96%|#########6| 40.0M/41.5M [00:11<00:00, 7.47MB/s]
- 98%|#########8| 40.7M/41.5M [00:11<00:00, 6.79MB/s]
-100%|#########9| 41.4M/41.5M [00:11<00:00, 5.88MB/s]
-100%|##########| 41.5M/41.5M [00:11<00:00, 3.73MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:15, 87.8kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:12, 139kB/s]
+ 0%| | 80.0k/41.5M [00:00<04:39, 155kB/s]
+ 0%| | 136k/41.5M [00:00<03:22, 215kB/s]
+ 1%| | 288k/41.5M [00:00<01:39, 436kB/s]
+ 1%|1 | 568k/41.5M [00:01<00:53, 807kB/s]
+ 2%|1 | 848k/41.5M [00:01<00:40, 1.04MB/s]
+ 3%|2 | 1.12M/41.5M [00:01<00:34, 1.24MB/s]
+ 3%|3 | 1.44M/41.5M [00:01<00:30, 1.40MB/s]
+ 4%|4 | 1.76M/41.5M [00:01<00:27, 1.52MB/s]
+ 5%|5 | 2.10M/41.5M [00:02<00:25, 1.64MB/s]
+ 6%|5 | 2.46M/41.5M [00:02<00:23, 1.75MB/s]
+ 7%|6 | 2.84M/41.5M [00:02<00:21, 1.86MB/s]
+ 8%|7 | 3.23M/41.5M [00:02<00:20, 1.95MB/s]
+ 9%|8 | 3.63M/41.5M [00:02<00:19, 2.05MB/s]
+ 10%|9 | 4.06M/41.5M [00:03<00:18, 2.16MB/s]
+ 11%|# | 4.52M/41.5M [00:03<00:16, 2.28MB/s]
+ 12%|#2 | 5.00M/41.5M [00:03<00:15, 2.40MB/s]
+ 13%|#3 | 5.50M/41.5M [00:03<00:15, 2.52MB/s]
+ 15%|#4 | 6.02M/41.5M [00:03<00:14, 2.64MB/s]
+ 16%|#5 | 6.58M/41.5M [00:03<00:13, 2.78MB/s]
+ 17%|#7 | 7.16M/41.5M [00:04<00:12, 2.91MB/s]
+ 19%|#8 | 7.77M/41.5M [00:04<00:11, 3.06MB/s]
+ 20%|## | 8.40M/41.5M [00:04<00:10, 3.20MB/s]
+ 22%|##1 | 9.07M/41.5M [00:04<00:10, 3.37MB/s]
+ 24%|##3 | 9.77M/41.5M [00:04<00:09, 3.52MB/s]
+ 25%|##5 | 10.5M/41.5M [00:05<00:08, 3.71MB/s]
+ 27%|##7 | 11.3M/41.5M [00:05<00:08, 3.89MB/s]
+ 29%|##9 | 12.1M/41.5M [00:05<00:07, 4.09MB/s]
+ 31%|###1 | 12.9M/41.5M [00:05<00:06, 4.29MB/s]
+ 33%|###3 | 13.8M/41.5M [00:05<00:06, 4.51MB/s]
+ 36%|###5 | 14.8M/41.5M [00:06<00:05, 4.73MB/s]
+ 38%|###8 | 15.8M/41.5M [00:06<00:05, 4.97MB/s]
+ 41%|#### | 16.8M/41.5M [00:06<00:04, 5.22MB/s]
+ 43%|####3 | 17.9M/41.5M [00:06<00:04, 5.99MB/s]
+ 46%|####5 | 19.0M/41.5M [00:06<00:03, 7.13MB/s]
+ 48%|####7 | 19.8M/41.5M [00:06<00:03, 6.60MB/s]
+ 49%|####9 | 20.4M/41.5M [00:06<00:03, 5.66MB/s]
+ 52%|#####1 | 21.5M/41.5M [00:07<00:03, 6.37MB/s]
+ 55%|#####4 | 22.8M/41.5M [00:07<00:02, 7.76MB/s]
+ 57%|#####6 | 23.6M/41.5M [00:07<00:02, 7.29MB/s]
+ 59%|#####8 | 24.3M/41.5M [00:07<00:02, 6.20MB/s]
+ 62%|######1 | 25.7M/41.5M [00:07<00:02, 7.69MB/s]
+ 65%|######5 | 27.1M/41.5M [00:07<00:01, 9.18MB/s]
+ 68%|######7 | 28.0M/41.5M [00:07<00:01, 8.19MB/s]
+ 70%|######9 | 28.9M/41.5M [00:08<00:01, 7.00MB/s]
+ 73%|#######2 | 30.1M/41.5M [00:08<00:01, 8.02MB/s]
+ 76%|#######5 | 31.5M/41.5M [00:08<00:01, 9.49MB/s]
+ 78%|#######8 | 32.5M/41.5M [00:08<00:01, 8.39MB/s]
+ 80%|######## | 33.4M/41.5M [00:08<00:01, 7.17MB/s]
+ 83%|########3 | 34.5M/41.5M [00:08<00:00, 8.06MB/s]
+ 87%|########6 | 35.9M/41.5M [00:08<00:00, 9.49MB/s]
+ 89%|########9 | 36.9M/41.5M [00:09<00:00, 8.42MB/s]
+ 91%|#########1| 37.8M/41.5M [00:09<00:00, 7.19MB/s]
+ 94%|#########3| 39.0M/41.5M [00:09<00:00, 8.05MB/s]
+ 97%|#########7| 40.4M/41.5M [00:09<00:00, 9.54MB/s]
+100%|#########9| 41.4M/41.5M [00:09<00:00, 8.43MB/s]
+100%|##########| 41.5M/41.5M [00:09<00:00, 4.54MB/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 fb2ad7e2e..92d45c06d 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 7.129 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.661 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index c794f5f40..60535d712 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,28 +387,10 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 4%|4 | 2.01M/44.7M [00:00<00:02, 20.6MB/s]
- 9%|8 | 3.97M/44.7M [00:00<00:02, 16.0MB/s]
- 13%|#3 | 6.00M/44.7M [00:00<00:02, 18.1MB/s]
- 17%|#7 | 7.79M/44.7M [00:00<00:02, 18.1MB/s]
- 22%|##1 | 9.62M/44.7M [00:00<00:01, 18.4MB/s]
- 27%|##6 | 11.9M/44.7M [00:00<00:01, 20.2MB/s]
- 31%|###1 | 13.9M/44.7M [00:00<00:01, 20.1MB/s]
- 36%|###5 | 15.9M/44.7M [00:00<00:01, 20.4MB/s]
- 41%|#### | 18.2M/44.7M [00:00<00:01, 21.5MB/s]
- 45%|####5 | 20.3M/44.7M [00:01<00:01, 20.9MB/s]
- 50%|##### | 22.4M/44.7M [00:01<00:01, 20.7MB/s]
- 55%|#####4 | 24.6M/44.7M [00:01<00:00, 21.3MB/s]
- 60%|#####9 | 26.7M/44.7M [00:01<00:00, 21.5MB/s]
- 64%|######4 | 28.7M/44.7M [00:01<00:00, 20.9MB/s]
- 69%|######8 | 30.8M/44.7M [00:01<00:00, 20.6MB/s]
- 73%|#######3 | 32.8M/44.7M [00:01<00:00, 20.5MB/s]
- 78%|#######7 | 34.7M/44.7M [00:01<00:00, 20.3MB/s]
- 82%|########2 | 36.8M/44.7M [00:01<00:00, 20.5MB/s]
- 87%|########6 | 38.7M/44.7M [00:02<00:00, 20.0MB/s]
- 91%|######### | 40.6M/44.7M [00:02<00:00, 19.3MB/s]
- 96%|#########6| 43.0M/44.7M [00:02<00:00, 20.7MB/s]
-100%|##########| 44.7M/44.7M [00:02<00:00, 20.3MB/s]
+ 29%|##8 | 12.9M/44.7M [00:00<00:00, 129MB/s]
+ 57%|#####6 | 25.3M/44.7M [00:00<00:00, 130MB/s]
+ 94%|#########3| 41.9M/44.7M [00:00<00:00, 149MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 147MB/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 9613ea31d..3c09d9253 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.304 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.695 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 3f4788e11..680037084 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:30.077</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:28.166</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:07.129</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>01:00.304</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:58.175</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:36.918</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
-<li><p><strong>00:24.072</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:23.305</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:22.323</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:20.915</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:14.440</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
-<li><p><strong>00:02.496</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>01:08.661</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>01:01.695</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:57.537</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
+<li><p><strong>00:35.301</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
+<li><p><strong>00:23.932</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:22.900</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:21.964</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:18.952</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:14.316</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
+<li><p><strong>00:02.908</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index c094e6a18..68ef5a850 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -627,7 +627,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7251 15.7260 15.8028 15.6457 0.0499
+ 16.9240 16.1431 22.0168 16.0062 1.8231
</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 1e99318b3..465b2829e 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,53 +409,69 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|2 | 4.62M/170M [00:00<00:03, 47.5MB/s]
- 5%|5 | 9.16M/170M [00:00<00:04, 34.5MB/s]
- 7%|7 | 12.6M/170M [00:00<00:04, 34.3MB/s]
- 9%|9 | 16.0M/170M [00:00<00:04, 33.5MB/s]
- 12%|#2 | 20.7M/170M [00:00<00:04, 38.4MB/s]
- 15%|#5 | 26.2M/170M [00:00<00:03, 44.7MB/s]
- 18%|#8 | 30.6M/170M [00:00<00:03, 42.4MB/s]
- 20%|## | 34.8M/170M [00:00<00:03, 37.5MB/s]
- 23%|##2 | 38.5M/170M [00:01<00:03, 34.7MB/s]
- 25%|##4 | 41.9M/170M [00:01<00:03, 33.9MB/s]
- 27%|##6 | 45.2M/170M [00:01<00:03, 33.1MB/s]
- 29%|##8 | 48.4M/170M [00:01<00:04, 29.3MB/s]
- 30%|### | 51.3M/170M [00:01<00:04, 28.0MB/s]
- 32%|###1 | 54.1M/170M [00:01<00:04, 28.2MB/s]
- 34%|###3 | 57.1M/170M [00:01<00:04, 29.0MB/s]
- 35%|###5 | 59.9M/170M [00:01<00:04, 28.6MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:03, 32.7MB/s]
- 40%|###9 | 67.2M/170M [00:02<00:04, 26.8MB/s]
- 41%|####1 | 69.9M/170M [00:02<00:03, 26.6MB/s]
- 43%|####3 | 73.1M/170M [00:02<00:03, 28.3MB/s]
- 45%|####5 | 76.6M/170M [00:02<00:03, 30.5MB/s]
- 47%|####6 | 79.6M/170M [00:02<00:03, 30.7MB/s]
- 49%|####9 | 83.9M/170M [00:02<00:02, 34.5MB/s]
- 52%|#####1 | 87.8M/170M [00:02<00:02, 36.3MB/s]
- 54%|#####3 | 91.3M/170M [00:02<00:02, 34.8MB/s]
- 56%|#####5 | 94.7M/170M [00:03<00:02, 34.8MB/s]
- 58%|#####7 | 98.0M/170M [00:03<00:02, 33.1MB/s]
- 60%|#####9 | 102M/170M [00:03<00:02, 34.5MB/s]
- 62%|######1 | 105M/170M [00:03<00:02, 30.7MB/s]
- 64%|######3 | 108M/170M [00:03<00:02, 29.9MB/s]
- 66%|######6 | 113M/170M [00:03<00:01, 33.2MB/s]
- 68%|######8 | 116M/170M [00:03<00:01, 33.3MB/s]
- 71%|####### | 121M/170M [00:03<00:01, 36.7MB/s]
- 73%|#######3 | 124M/170M [00:03<00:01, 34.4MB/s]
- 76%|#######6 | 129M/170M [00:04<00:01, 39.9MB/s]
- 79%|#######9 | 135M/170M [00:04<00:00, 44.6MB/s]
- 82%|########1 | 139M/170M [00:04<00:00, 34.7MB/s]
- 85%|########4 | 144M/170M [00:04<00:00, 37.8MB/s]
- 87%|########6 | 148M/170M [00:04<00:00, 34.9MB/s]
- 89%|########8 | 151M/170M [00:04<00:00, 32.2MB/s]
- 91%|######### | 154M/170M [00:04<00:00, 31.6MB/s]
- 93%|#########2| 158M/170M [00:04<00:00, 30.9MB/s]
- 95%|#########4| 161M/170M [00:05<00:00, 29.0MB/s]
- 96%|#########6| 163M/170M [00:05<00:00, 28.5MB/s]
- 98%|#########7| 166M/170M [00:05<00:00, 23.5MB/s]
-100%|#########9| 169M/170M [00:05<00:00, 25.6MB/s]
-100%|##########| 170M/170M [00:05<00:00, 32.4MB/s]
+ 1%|1 | 2.07M/170M [00:00<00:08, 21.1MB/s]
+ 3%|2 | 4.81M/170M [00:00<00:06, 25.4MB/s]
+ 5%|4 | 8.12M/170M [00:00<00:05, 29.4MB/s]
+ 6%|6 | 10.9M/170M [00:00<00:06, 24.3MB/s]
+ 8%|7 | 13.4M/170M [00:00<00:06, 24.0MB/s]
+ 9%|9 | 15.7M/170M [00:00<00:07, 21.6MB/s]
+ 10%|# | 17.8M/170M [00:00<00:07, 21.4MB/s]
+ 12%|#1 | 19.9M/170M [00:00<00:07, 21.5MB/s]
+ 13%|#2 | 22.0M/170M [00:01<00:07, 20.8MB/s]
+ 15%|#4 | 25.3M/170M [00:01<00:06, 24.4MB/s]
+ 18%|#7 | 29.8M/170M [00:01<00:04, 30.8MB/s]
+ 19%|#9 | 32.8M/170M [00:01<00:05, 26.7MB/s]
+ 21%|## | 35.4M/170M [00:01<00:05, 24.0MB/s]
+ 23%|##2 | 38.7M/170M [00:01<00:05, 26.4MB/s]
+ 24%|##4 | 41.3M/170M [00:01<00:05, 26.3MB/s]
+ 26%|##5 | 43.9M/170M [00:01<00:04, 26.4MB/s]
+ 27%|##7 | 46.5M/170M [00:02<00:06, 21.5MB/s]
+ 29%|##8 | 48.8M/170M [00:02<00:05, 21.4MB/s]
+ 30%|##9 | 50.9M/170M [00:02<00:05, 20.8MB/s]
+ 31%|###1 | 53.0M/170M [00:02<00:06, 19.8MB/s]
+ 33%|###2 | 55.9M/170M [00:02<00:05, 22.0MB/s]
+ 35%|###4 | 58.9M/170M [00:02<00:04, 24.7MB/s]
+ 36%|###6 | 61.4M/170M [00:02<00:04, 23.0MB/s]
+ 37%|###7 | 63.6M/170M [00:02<00:06, 16.3MB/s]
+ 39%|###9 | 66.8M/170M [00:03<00:05, 19.7MB/s]
+ 41%|#### | 69.2M/170M [00:03<00:04, 21.2MB/s]
+ 43%|####2 | 72.9M/170M [00:03<00:03, 25.5MB/s]
+ 45%|####4 | 75.7M/170M [00:03<00:03, 25.0MB/s]
+ 46%|####6 | 78.8M/170M [00:03<00:03, 26.9MB/s]
+ 48%|####7 | 81.5M/170M [00:03<00:03, 23.8MB/s]
+ 49%|####9 | 83.9M/170M [00:03<00:03, 22.6MB/s]
+ 51%|##### | 86.2M/170M [00:03<00:04, 19.4MB/s]
+ 53%|#####2 | 89.3M/170M [00:04<00:03, 22.5MB/s]
+ 55%|#####4 | 93.3M/170M [00:04<00:02, 27.2MB/s]
+ 57%|#####7 | 96.8M/170M [00:04<00:02, 29.8MB/s]
+ 59%|#####8 | 100M/170M [00:04<00:02, 30.5MB/s]
+ 61%|###### | 103M/170M [00:04<00:02, 25.9MB/s]
+ 62%|######2 | 106M/170M [00:04<00:02, 23.5MB/s]
+ 64%|######3 | 108M/170M [00:04<00:02, 22.3MB/s]
+ 65%|######4 | 110M/170M [00:04<00:02, 21.5MB/s]
+ 67%|######7 | 114M/170M [00:05<00:02, 24.9MB/s]
+ 69%|######8 | 117M/170M [00:05<00:02, 27.3MB/s]
+ 71%|####### | 120M/170M [00:05<00:01, 28.9MB/s]
+ 73%|#######2 | 124M/170M [00:05<00:01, 30.3MB/s]
+ 75%|#######4 | 127M/170M [00:05<00:01, 27.2MB/s]
+ 76%|#######6 | 129M/170M [00:05<00:01, 27.4MB/s]
+ 78%|#######7 | 132M/170M [00:05<00:01, 23.9MB/s]
+ 79%|#######9 | 134M/170M [00:05<00:01, 22.5MB/s]
+ 80%|######## | 137M/170M [00:05<00:01, 21.5MB/s]
+ 82%|########1 | 139M/170M [00:06<00:01, 21.0MB/s]
+ 83%|########3 | 141M/170M [00:06<00:01, 22.9MB/s]
+ 86%|########5 | 146M/170M [00:06<00:00, 28.9MB/s]
+ 87%|########7 | 149M/170M [00:06<00:00, 25.0MB/s]
+ 89%|########8 | 151M/170M [00:06<00:00, 20.6MB/s]
+ 90%|######### | 153M/170M [00:06<00:00, 20.7MB/s]
+ 91%|#########1| 155M/170M [00:06<00:00, 20.6MB/s]
+ 93%|#########2| 157M/170M [00:07<00:00, 19.0MB/s]
+ 94%|#########3| 160M/170M [00:07<00:00, 19.7MB/s]
+ 95%|#########5| 162M/170M [00:07<00:00, 19.4MB/s]
+ 97%|#########6| 164M/170M [00:07<00:00, 21.5MB/s]
+ 98%|#########7| 166M/170M [00:07<00:00, 21.8MB/s]
+100%|#########9| 169M/170M [00:07<00:00, 24.2MB/s]
+100%|##########| 170M/170M [00:07<00:00, 23.4MB/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').
@@ -553,7 +569,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 56.353 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.423 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index ee464784f..6591fca7a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,8 @@ 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]
- 17%|#7 | 2.33M/13.6M [00:00<00:00, 24.4MB/s]
- 34%|###4 | 4.66M/13.6M [00:00<00:00, 22.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 52.6MB/s]
+ 58%|#####8 | 7.91M/13.6M [00:00<00:00, 83.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 114MB/s]
</pre></div>
</div>
</div>
@@ -546,7 +545,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3017 90.1979 94.5337 90.0353 0.5638
+ 90.5176 90.3609 95.9124 90.1418 0.6785
</pre></div>
</div>
<div class="admonition note">
@@ -585,7 +584,7 @@ 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 5.673 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.985 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 2206a4d22..c1ffb7868 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -545,7 +545,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0483 120.0173 121.7086 119.2413 0.4115
+ 121.9156 121.8679 126.2616 121.1125 0.5568
</pre></div>
</div>
<div class="admonition note">
@@ -573,7 +573,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.110 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.401 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index ec6edfce7..188491ed6 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -482,7 +482,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 2.259 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.525 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index ef3a9ac44..4e42d1573 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,23 +415,22 @@ 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]
- 4%|4 | 5969/132723 [00:00<00:02, 59687.07KB/s]
- 11%|# | 13997/132723 [00:00<00:01, 71797.33KB/s]
- 17%|#6 | 22151/132723 [00:00<00:01, 76241.77KB/s]
- 23%|##2 | 30323/132723 [00:00<00:01, 78401.63KB/s]
- 29%|##9 | 38501/132723 [00:00<00:01, 79611.16KB/s]
- 35%|###5 | 46643/132723 [00:00<00:01, 80224.37KB/s]
- 41%|####1 | 54805/132723 [00:00<00:00, 80675.90KB/s]
- 47%|####7 | 62873/132723 [00:00<00:00, 80268.83KB/s]
- 54%|#####3 | 71033/132723 [00:00<00:00, 80682.02KB/s]
- 60%|#####9 | 79181/132723 [00:01<00:00, 80923.04KB/s]
- 66%|######5 | 87274/132723 [00:01<00:00, 80919.76KB/s]
- 72%|#######1 | 95423/132723 [00:01<00:00, 81091.57KB/s]
- 78%|#######8 | 103610/132723 [00:01<00:00, 81324.14KB/s]
- 84%|########4 | 111794/132723 [00:01<00:00, 81478.71KB/s]
- 90%|######### | 120006/132723 [00:01<00:00, 81669.07KB/s]
- 97%|#########6| 128253/132723 [00:01<00:00, 81906.74KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 80138.91KB/s]
+ 5%|4 | 6217/132723 [00:00<00:02, 62164.28KB/s]
+ 11%|#1 | 14859/132723 [00:00<00:01, 76429.28KB/s]
+ 18%|#7 | 23429/132723 [00:00<00:01, 80660.78KB/s]
+ 24%|##4 | 32166/132723 [00:00<00:01, 83299.95KB/s]
+ 31%|### | 40846/132723 [00:00<00:01, 84559.90KB/s]
+ 37%|###7 | 49514/132723 [00:00<00:00, 85271.44KB/s]
+ 44%|####3 | 58156/132723 [00:00<00:00, 85644.71KB/s]
+ 50%|##### | 66773/132723 [00:00<00:00, 85807.00KB/s]
+ 57%|#####6 | 75429/132723 [00:00<00:00, 86039.00KB/s]
+ 63%|######3 | 84127/132723 [00:01<00:00, 86326.64KB/s]
+ 70%|######9 | 92792/132723 [00:01<00:00, 86418.62KB/s]
+ 76%|#######6 | 101474/132723 [00:01<00:00, 86537.72KB/s]
+ 83%|########3 | 110173/132723 [00:01<00:00, 86672.49KB/s]
+ 90%|########9 | 118897/132723 [00:01<00:00, 86841.29KB/s]
+ 96%|#########6| 127598/132723 [00:01<00:00, 86890.29KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 85067.40KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -476,7 +475,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 16.393 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.119 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index e9bd5a77a..7a11c87c3 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:09.343</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:32.283</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:56.353</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
-<li><p><strong>02:16.393</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>02:02.259</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
-<li><p><strong>01:58.110</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
-<li><p><strong>01:05.673</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:28.051</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
-<li><p><strong>00:22.312</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
-<li><p><strong>00:00.192</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>03:04.423</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:22.119</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>01:52.401</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
+<li><p><strong>01:13.525</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
+<li><p><strong>01:07.985</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:29.352</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
+<li><p><strong>00:22.270</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
+<li><p><strong>00:00.207</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index ea77f6c42..6c293c516 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -590,7 +590,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7d63bc9c-d6bb-477e-a93c-abb465d487bf 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.zip8b0f5334-6bfb-4ea6-b887-e5aa850764d3 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 dc668b0ec..97a6e5f1e 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.408</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.760</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:35.763</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
-<li><p><strong>00:02.361</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
-<li><p><strong>00:01.084</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.201</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:36.919</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
+<li><p><strong>00:02.504</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
+<li><p><strong>00:01.121</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.215</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 4ad8736a3..84b8e36d1 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6607us [6607us] (45.58%; 45.58%)
-FoldScaleAxis: 7890us [6us] (54.42%; 54.42%)
- FoldConstant: 7884us [1577us] (54.38%; 99.92%)
- InferType: 6307us [6307us] (43.51%; 80.00%)
+InferType: 6674us [6674us] (45.28%; 45.28%)
+FoldScaleAxis: 8067us [7us] (54.72%; 54.72%)
+ FoldConstant: 8060us [1598us] (54.68%; 99.92%)
+ InferType: 6462us [6462us] (43.84%; 80.17%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6282us [6282us] (44.66%; 44.66%)
-FoldScaleAxis: 7783us [5us] (55.34%; 55.34%)
- FoldConstant: 7778us [1599us] (55.30%; 99.94%)
- InferType: 6179us [6179us] (43.94%; 79.44%)
+InferType: 6606us [6606us] (44.95%; 44.95%)
+FoldScaleAxis: 8089us [6us] (55.05%; 55.05%)
+ FoldConstant: 8084us [1658us] (55.01%; 99.93%)
+ InferType: 6426us [6426us] (43.73%; 79.49%)
</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 97f8a45ac..0d685eb18 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.140683 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.388811 ms
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 33f333541..992fd8b76 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.908362 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.945374 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 afcc681fe..96c1ed8a7 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018261
-Baseline: 3.202010
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019266
+Baseline: 3.281024
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298678
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302436
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339850
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120812
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118524
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110605
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112130
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110937
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111390
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144911
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145154
</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 e0abc9bbf..2cf0b6531 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.347</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.908</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:31.712</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
-<li><p><strong>00:01.432</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
-<li><p><strong>00:01.203</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
+<li><p><strong>00:32.198</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.485</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.225</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index d17cdedea..395e6025b 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:11.562</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:21.613</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:35.679</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>01:19.744</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:42.592</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
-<li><p><strong>00:16.714</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
-<li><p><strong>00:08.494</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
-<li><p><strong>00:08.339</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
+<li><p><strong>02:42.079</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>01:21.061</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:43.318</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:17.052</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
+<li><p><strong>00:09.238</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
+<li><p><strong>00:08.865</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 84d0ec0c7..94d09bca9 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -450,7 +450,7 @@ file and apply it.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
</pre></div>
</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
@@ -470,226 +470,483 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[12] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*144)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*18)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 1)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 2)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 3)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 4)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 5)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 6)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 7)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1*2), 9)) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*2), 9)*49)) + (floormod((threadIdx.x_1*2), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 8)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 9)] = 0f32
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 10)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 7)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 11)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 6)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 12)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 5)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 13)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 4)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 14)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 3)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 15)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 2)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 16)] = @tir.if_then_else(((1 <= floormod(((threadIdx.x_1*2) + 1), 9)) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*2) + 1), 9)*49)) + (floormod(((threadIdx.x_1*2) + 1), 9)*7)) - 1)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 72), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*18) + 17)] = 0f32
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 7), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 14), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 21), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 28), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 35), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 42), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 56), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 896), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 70), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1120), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 77), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1232), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 84), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 91), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1456), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 105), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1792), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 119), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1904), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 133), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2128), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 140), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2240), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 154), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2464), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 161), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2576), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 168), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 175), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2800), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 182), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2912), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 196), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 203), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3248), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 210), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 217), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3472), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3584), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 231), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 238), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3808), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 245), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3920), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(threadIdx.x_2, 3)*3)) + floormod(threadIdx.x_2, 3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 259), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4144), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 266), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4256), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 273), 9)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 48)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 16) + 280), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4480), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4592), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
- }
- for (rc.outer.inner: int32, 0, 16) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*81) + (ry.inner*9)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*9)) + (ry.inner*3)) + 146)]))
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 208), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 272), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 304), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 352), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 400), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 416), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 464), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 496), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 544), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 592), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 608), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 656), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 688), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 736), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -727,7 +984,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.247 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.368 ms
</pre></div>
</div>
</div>
@@ -757,36 +1014,36 @@ 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=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
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=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_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_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=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+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=1)
-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)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=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_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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)
@@ -806,14 +1063,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+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=64)
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=18)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
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=112)
+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=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -831,180 +1088,430 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[(((int)threadIdx.x) * 18)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((1 <= ((((int)threadIdx.x) * 2) % 9)) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 9) * 49)) + (((((int)threadIdx.x) * 2) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = 0.000000e+00f;
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 7)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 6)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 5)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 4)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 3)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 2)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((1 <= (((((int)threadIdx.x) * 2) + 1) % 9)) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 9) * 49)) + ((((((int)threadIdx.x) * 2) + 1) % 9) * 7)) - 1)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 72) {
- pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = 0.000000e+00f;
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 16) % 48) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 81) + (ry_inner * 9)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 9)) + (ry_inner * 3)) + 146)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -1042,7 +1549,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.679 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 42.079 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index a3d908abd..63f4e3639 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -878,7 +878,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7860 9.7881 9.8175 9.7524 0.0266
+ 9.9910 10.0255 10.0279 9.9197 0.0505
</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 f3634709d..a628da759 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -897,7 +897,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 757.0077 756.6604 758.5732 755.7894 1.1627
+ 761.7415 761.7363 764.4265 759.0616 2.1902
</pre></div>
</div>
</div>
@@ -919,7 +919,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.744 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.061 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index bf71e7b40..890e496d8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,105 +600,103 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = ((i.outer.inner*256) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- }
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = (i.inner.init*16)
+ {
+ compute_5: Buffer(compute_4, float32, [512], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
- {
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_4: int32 = ((i.outer.inner*256) + (i.inner*16))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*256) + (i.inner*16)) + 1)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*256) + (i.inner*16)) + 2)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*256) + (i.inner*16)) + 3)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*256) + (i.inner*16)) + 4)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*256) + (i.inner*16)) + 5)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*256) + (i.inner*16)) + 6)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*256) + (i.inner*16)) + 7)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*256) + (i.inner*16)) + 8)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*256) + (i.inner*16)) + 9)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*256) + (i.inner*16)) + 10)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*256) + (i.inner*16)) + 11)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*256) + (i.inner*16)) + 12)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*256) + (i.inner*16)) + 13)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*16)) + 14)
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
- let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*16)) + 15)
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
- }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 32) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ {
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_4: int32 = (i.inner*16)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[((placeholder_3[cse_var_3]*16) + (elem_idx*16))]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_5: int32 = ((i.inner*16) + 1)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_6: int32 = ((i.inner*16) + 2)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_7: int32 = ((i.inner*16) + 3)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_8: int32 = ((i.inner*16) + 4)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_9: int32 = ((i.inner*16) + 5)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_10: int32 = ((i.inner*16) + 6)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_11: int32 = ((i.inner*16) + 7)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_12: int32 = ((i.inner*16) + 8)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_13: int32 = ((i.inner*16) + 9)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_14: int32 = ((i.inner*16) + 10)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_15: int32 = ((i.inner*16) + 11)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_16: int32 = ((i.inner*16) + 12)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_17: int32 = ((i.inner*16) + 13)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_18: int32 = ((i.inner*16) + 14)
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_3 + 1)] - placeholder_3[cse_var_3])), dtype=bool) {
+ let cse_var_19: int32 = ((i.inner*16) + 15)
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_20: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
}
}
@@ -738,7 +736,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.108 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.761 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 f91f7b2bd..1ebdcfeed 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.256</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.760</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.406</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.224</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.214</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.209</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.203</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:43.840</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.240</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.226</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 16fbd8bc5..87f064461 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -563,11 +563,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -619,11 +619,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -686,11 +686,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -742,11 +742,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -809,11 +809,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -865,11 +865,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -932,11 +932,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -988,11 +988,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1055,11 +1055,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1111,11 +1111,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 95.14/95.14 result: MeasureResult(costs=(0.0024332972916666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7711749076843262, timestamp=1654829526.2237127) [('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: 0.00/95.14 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.00/110.00 result: MeasureResult(costs=(0.0021045718958333337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.660846471786499, timestamp=1654830288.6228688) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1179,11 +1179,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1235,11 +1235,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1302,11 +1302,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1358,11 +1358,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1425,11 +1425,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1481,11 +1481,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/95.14 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: 0.00/95.14 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1566,11 +1566,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1622,11 +1622,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1689,11 +1689,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1745,11 +1745,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1812,11 +1812,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1868,11 +1868,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1935,11 +1935,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -1991,11 +1991,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2058,11 +2058,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2114,11 +2114,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2181,11 +2181,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2237,11 +2237,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2304,11 +2304,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2360,11 +2360,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2427,11 +2427,11 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2483,11 +2483,11 @@ Traceback (most recent call last):
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
- at ../src/driver/driver_api.cc:390
+ at ../src/driver/driver_api.cc:391
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
- at ../src/driver/driver_api.cc:377
+ at ../src/driver/driver_api.cc:378
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:277
+ at ../src/driver/driver_api.cc:278
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/95.14 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f21657e7fa2
+ 12: 0x00007f6395d54fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.87/143.87 result: MeasureResult(costs=(0.0016091146300000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435838222503662, timestamp=1654829552.6920938) [('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: 143.01/143.01 result: MeasureResult(costs=(0.0016188032699999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.448167085647583, timestamp=1654830315.1207933) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.001968
+Time cost of this operator: 0.001976
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 713501c38..3f3c2c026 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -556,10 +556,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.6 98.723 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.981 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 0.297 (1, 1, 10, 10, 3) 1 1
-Total_time - 313.606 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.8 98.746 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.965 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.289 (1, 1, 10, 10, 3) 1 1
+Total_time - 318.797 - - - -
</pre></div>
</div>
</div>
@@ -611,10 +611,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 90.1 96.84 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.034 2.186 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 0.974 (1, 1, 10, 10, 3) 1 1
-Total_time - 93.04 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 218.3 98.757 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.948 0.881 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.362 (1, 3, 10, 10, 1) 1 1
+Total_time - 221.048 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 47b4d68e8..560480155 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -552,8 +552,8 @@ objects to other stuff? We can display some examples from our datasets using <co
</div>
<img alt="../../_images/sphx_glr_micro_train_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_micro_train_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpdm8a5676/images/target contains 8144 images
-/tmp/tmpdm8a5676/images/random contains 5000 images
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmprbiuzyga/images/target contains 8144 images
+/tmp/tmprbiuzyga/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -666,11 +666,11 @@ the time on our validation set).</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 54s - loss: 0.2172 - accuracy: 0.9269 - val_loss: 0.1415 - val_accuracy: 0.9588
+328/328 - 54s - loss: 0.2114 - accuracy: 0.9290 - val_loss: 0.1325 - val_accuracy: 0.9611
Epoch 2/3
-328/328 - 52s - loss: 0.1009 - accuracy: 0.9610 - val_loss: 0.1139 - val_accuracy: 0.9641
+328/328 - 52s - loss: 0.1005 - accuracy: 0.9637 - val_loss: 0.1097 - val_accuracy: 0.9622
Epoch 3/3
-328/328 - 52s - loss: 0.0657 - accuracy: 0.9743 - val_loss: 0.1375 - val_accuracy: 0.9554
+328/328 - 52s - loss: 0.0619 - accuracy: 0.9772 - val_loss: 0.1015 - val_accuracy: 0.9698
</pre></div>
</div>
</div>
@@ -959,7 +959,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 16.778 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 15.016 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 6ede888bb..1e742ecf2 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.561</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:02.058</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>04:16.778</strong>: <a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></li>
-<li><p><strong>00:41.546</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
-<li><p><strong>00:03.643</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
-<li><p><strong>00:00.200</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.197</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.196</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>04:15.016</strong>: <a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></li>
+<li><p><strong>00:42.739</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
+<li><p><strong>00:03.685</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.207</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.206</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.206</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 1fa943a8b..21a2c757e 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:12.136</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:14.060</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:10.204</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
-<li><p><strong>00:01.717</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.215</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:11.494</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
+<li><p><strong>00:02.339</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 92e6638df..9fb951c72 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:05.680</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.003</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.076</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
-<li><p><strong>00:01.168</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
-<li><p><strong>00:00.742</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
-<li><p><strong>00:00.706</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.300</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.238</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
-<li><p><strong>00:00.235</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
-<li><p><strong>00:00.215</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.158</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
+<li><p><strong>00:01.306</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
+<li><p><strong>00:00.747</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
+<li><p><strong>00:00.737</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
+<li><p><strong>00:00.320</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
+<li><p><strong>00:00.252</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
+<li><p><strong>00:00.251</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
+<li><p><strong>00:00.232</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 14a4b040a..275143e22 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/tmpy4y86a27/input0.cc'\nsource_filename = \"/tmp/tmpy4y86a27/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/tmpo2wh2n71/input0.cc'\nsource_filename = \"/tmp/tmpo2wh2n71/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/objects.inv b/docs/objects.inv
index 7c6525258..8eeadf316 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/doxygen/namespacemembers.html b/docs/reference/api/doxygen/namespacemembers.html
index 2109bb171..4e40e164c 100644
--- a/docs/reference/api/doxygen/namespacemembers.html
+++ b/docs/reference/api/doxygen/namespacemembers.html
@@ -189,6 +189,9 @@ $(function() {
<li>AsText()
: <a class="el" href="namespacetvm.html#ad0e4314dd85303aa5e10d452e4c9db54">tvm</a>
</li>
+<li>async_scope
+: <a class="el" href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">tvm::tir::attr</a>
+</li>
<li>atan()
: <a class="el" href="namespacetvm.html#a475b388b9a19d05dca849707d74636a7">tvm</a>
, <a class="el" href="namespacetvm_1_1topi.html#aa14a4c203d817e58d5c0ecad426e0745">tvm::topi</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_i.html b/docs/reference/api/doxygen/namespacemembers_func_i.html
index 3c9b075ff..58e29572f 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_i.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_i.html
@@ -99,6 +99,9 @@ $(function() {
<li>InjectPrefetch()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a20aa23d8985679d2e09685729c644f0f">tvm::tir::transform</a>
</li>
+<li>InjectPTXAsyncCopy()
+: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">tvm::tir::transform</a>
+</li>
<li>InjectSoftwarePipeline()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a1b90f3ff7f983452fb3a4f7181043ae8">tvm::tir::transform</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_func_p.html b/docs/reference/api/doxygen/namespacemembers_func_p.html
index 7c33a5248..803915cb0 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_p.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_p.html
@@ -67,12 +67,12 @@ $(function() {
<li>PackImportsToLLVM()
: <a class="el" href="namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6">tvm::codegen</a>
</li>
-<li>pad()
-: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
-</li>
<li>Pad()
: <a class="el" href="namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121">tvm::topi</a>
</li>
+<li>pad()
+: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
+</li>
<li>parallel_for()
: <a class="el" href="namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c">tvm::support</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_i.html b/docs/reference/api/doxygen/namespacemembers_i.html
index 619763d6d..711cecd1f 100644
--- a/docs/reference/api/doxygen/namespacemembers_i.html
+++ b/docs/reference/api/doxygen/namespacemembers_i.html
@@ -111,6 +111,9 @@ $(function() {
<li>InjectPrefetch()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a20aa23d8985679d2e09685729c644f0f">tvm::tir::transform</a>
</li>
+<li>InjectPTXAsyncCopy()
+: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">tvm::tir::transform</a>
+</li>
<li>InjectSoftwarePipeline()
: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a1b90f3ff7f983452fb3a4f7181043ae8">tvm::tir::transform</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_p.html b/docs/reference/api/doxygen/namespacemembers_p.html
index eb3b32fd5..33cb466d5 100644
--- a/docs/reference/api/doxygen/namespacemembers_p.html
+++ b/docs/reference/api/doxygen/namespacemembers_p.html
@@ -67,12 +67,12 @@ $(function() {
<li>PackImportsToLLVM()
: <a class="el" href="namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6">tvm::codegen</a>
</li>
-<li>pad()
-: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
-</li>
<li>Pad()
: <a class="el" href="namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121">tvm::topi</a>
</li>
+<li>pad()
+: <a class="el" href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi</a>
+</li>
<li>parallel_for()
: <a class="el" href="namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c">tvm::support</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacemembers_vars.html b/docs/reference/api/doxygen/namespacemembers_vars.html
index 94f8d201b..1582f6995 100644
--- a/docs/reference/api/doxygen/namespacemembers_vars.html
+++ b/docs/reference/api/doxygen/namespacemembers_vars.html
@@ -61,6 +61,9 @@ $(function() {
 
<h3><a id="index_a"></a>- a -</h3><ul>
+<li>async_scope
+: <a class="el" href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">tvm::tir::attr</a>
+</li>
<li>AUTO_SCHEDULER_LOG_VERSION
: <a class="el" href="namespacetvm_1_1auto__scheduler.html#a04029f3b293fba232218203167b2ef63">tvm::auto_scheduler</a>
</li>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1attr.html b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1attr.html
index 0f0e654d3..8d80a1d4d 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1attr.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1attr.html
@@ -207,6 +207,9 @@ Variables</h2></td></tr>
<tr class="memitem:a36db026f638ad3d951c302796ddcae24"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#a36db026f638ad3d951c302796ddcae24">device_scope</a> = "device_scope"</td></tr>
<tr class="memdesc:a36db026f638ad3d951c302796ddcae24"><td class="mdescLeft"> </td><td class="mdescRight">Mark that it is in the device scope. <a href="#a36db026f638ad3d951c302796ddcae24">More...</a><br /></td></tr>
<tr class="separator:a36db026f638ad3d951c302796ddcae24"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:af86552e1cc4180ec1c8e14b582e49c16"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">async_scope</a> = "async_scope"</td></tr>
+<tr class="memdesc:af86552e1cc4180ec1c8e14b582e49c16"><td class="mdescLeft"> </td><td class="mdescRight">Mark that the attached statement runs asynchronously. <a href="#af86552e1cc4180ec1c8e14b582e49c16">More...</a><br /></td></tr>
+<tr class="separator:af86552e1cc4180ec1c8e14b582e49c16"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a93d76d80fd7252d66991dc650693c0ef"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#a93d76d80fd7252d66991dc650693c0ef">fragment_shape</a> = "fragment_shape"</td></tr>
<tr class="memdesc:a93d76d80fd7252d66991dc650693c0ef"><td class="mdescLeft"> </td><td class="mdescRight">Mark that the shape of TensorCore fragment. <a href="#a93d76d80fd7252d66991dc650693c0ef">More...</a><br /></td></tr>
<tr class="separator:a93d76d80fd7252d66991dc650693c0ef"><td class="memSeparator" colspan="2"> </td></tr>
@@ -300,6 +303,22 @@ Variables</h2></td></tr>
</div>
</div>
<h2 class="groupheader">Variable Documentation</h2>
+<a id="af86552e1cc4180ec1c8e14b582e49c16"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#af86552e1cc4180ec1c8e14b582e49c16">◆ </a></span>async_scope</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">constexpr const char* tvm::tir::attr::async_scope = "async_scope"</td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Mark that the attached statement runs asynchronously. </p>
+
+</div>
+</div>
<a id="acf23614bc95ff92e0aa41a519eec08e4"></a>
<h2 class="memtitle"><span class="permalink"><a href="#acf23614bc95ff92e0aa41a519eec08e4">◆ </a></span>axis_separators</h2>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
index 34b0086ec..bf03dd876 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
@@ -245,6 +245,9 @@ Functions</h2></td></tr>
<tr class="memitem:a70bda35bb43e9420c8115bb1ec977811"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a70bda35bb43e9420c8115bb1ec977811">Filter</a> (<a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc.html">runtime::TypedPackedFunc</a>< bool(<a class="el" href="classtvm_1_1tir_1_1PrimFunc.html">PrimFunc< [...]
<tr class="memdesc:a70bda35bb43e9420c8115bb1ec977811"><td class="mdescLeft"> </td><td class="mdescRight">Filter PrimFuncs with a given condition. <a href="#a70bda35bb43e9420c8115bb1ec977811">More...</a><br /></td></tr>
<tr class="separator:a70bda35bb43e9420c8115bb1ec977811"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac804d5f6bd95449af8d09f26b804db4a"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">InjectPTXAsyncCopy</a> ()</td></tr>
+<tr class="memdesc:ac804d5f6bd95449af8d09f26b804db4a"><td class="mdescLeft"> </td><td class="mdescRight">Pass to rewrite global to shared memory copy on CUDA with asyncronous copy. <a href="#ac804d5f6bd95449af8d09f26b804db4a">More...</a><br /></td></tr>
+<tr class="separator:ac804d5f6bd95449af8d09f26b804db4a"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<h2 class="groupheader">Function Documentation</h2>
<a id="a776c657ccb30ff327c5dd0d6940a836a"></a>
@@ -703,6 +706,26 @@ Functions</h2></td></tr>
<p>Inject prefetch instructions into stmt. </p>
<dl class="section return"><dt>Returns</dt><dd>The pass. </dd></dl>
+</div>
+</div>
+<a id="ac804d5f6bd95449af8d09f26b804db4a"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ac804d5f6bd95449af8d09f26b804db4a">◆ </a></span>InjectPTXAsyncCopy()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> tvm::tir::transform::InjectPTXAsyncCopy </td>
+ <td>(</td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+<p>Pass to rewrite global to shared memory copy on CUDA with asyncronous copy. </p>
+<dl class="section return"><dt>Returns</dt><dd>The pass. </dd></dl>
+
</div>
</div>
<a id="a1b90f3ff7f983452fb3a4f7181043ae8"></a>
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index 760c05438..b358c3bb3 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -21,7 +21,7 @@ var searchData=
['packetfieldsizebytes',['PacketFieldSizeBytes',['../classtvm_1_1runtime_1_1micro__rpc_1_1PacketFieldSizeBytes.html',1,'tvm::runtime::micro_rpc']]],
['packimportstoc',['PackImportsToC',['../namespacetvm_1_1codegen.html#abf02059ebadcdb8bbbe5c840b646d67b',1,'tvm::codegen']]],
['packimportstollvm',['PackImportsToLLVM',['../namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6',1,'tvm::codegen']]],
- ['pad',['Pad',['../namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121',1,'tvm::topi::Pad(const Array< PrimExpr > shape, int odim)'],['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElement [...]
+ ['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElementWise, std::string pad_mode="constant", const Array< PrimExpr > *dyn_output_shape=nullptr)'],['../namespacetvm_1_1topi [...]
['pad_5fmode',['pad_mode',['../structtvm_1_1relay_1_1PadAttrs.html#a5b524c3add781cd2da894e81553079f8',1,'tvm::relay::PadAttrs']]],
['pad_5futils_2eh',['pad_utils.h',['../pad__utils_8h.html',1,'']]],
['pad_5fvalue',['pad_value',['../structtvm_1_1relay_1_1SpaceToBatchNDAttrs.html#a7c0fbd47621c925a45e1074f85a6b70f',1,'tvm::relay::SpaceToBatchNDAttrs']]],
diff --git a/docs/reference/api/doxygen/search/all_2.js b/docs/reference/api/doxygen/search/all_2.js
index 23fd92d19..1925c6f8a 100644
--- a/docs/reference/api/doxygen/search/all_2.js
+++ b/docs/reference/api/doxygen/search/all_2.js
@@ -223,6 +223,7 @@ var searchData=
['assigntypedlambda',['AssignTypedLambda',['../classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a11985d7fdcf9ac60ff34faef89382284',1,'tvm::runtime::TypedPackedFunc< R(Args...)>::AssignTypedLambda(FType flambda, std::string name)'],['../classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a617bb54ee3fbe9704131229efd0d903c',1,'tvm::runtime::TypedPackedFunc< R(Args...)>::AssignTypedLambda(FType flambda)']]],
['astable',['AsTable',['../classtvm_1_1runtime_1_1profiling_1_1ReportNode.html#a0e4562c552d973853fb01d7bc501d591',1,'tvm::runtime::profiling::ReportNode']]],
['astext',['AsText',['../namespacetvm.html#ad0e4314dd85303aa5e10d452e4c9db54',1,'tvm']]],
+ ['async_5fscope',['async_scope',['../namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16',1,'tvm::tir::attr']]],
['at',['at',['../classtvm_1_1runtime_1_1ArrayNode.html#a410953f5ac23f6ca5caa257def8b08bd',1,'tvm::runtime::ArrayNode::at()'],['../classtvm_1_1runtime_1_1MapNode.html#a49edd4ddc34a4e0b097c34560b9b3b4e',1,'tvm::runtime::MapNode::at(const key_type &key) const'],['../classtvm_1_1runtime_1_1MapNode.html#a29503ec61af7a5bb9b030a00cfdff01a',1,'tvm::runtime::MapNode::at(const key_type &key)'],['../classtvm_1_1runtime_1_1SmallMapNode.html#a0593c84ceb05afb1a3f87045a3dc3a59',1,'tvm::runtim [...]
['atan',['atan',['../namespacetvm.html#a475b388b9a19d05dca849707d74636a7',1,'tvm::atan()'],['../namespacetvm_1_1topi.html#aa14a4c203d817e58d5c0ecad426e0745',1,'tvm::topi::atan()']]],
['atan2',['atan2',['../namespacetvm.html#a350f9808d53b5fd9ad5c4c50bb76d700',1,'tvm']]],
diff --git a/docs/reference/api/doxygen/search/all_a.js b/docs/reference/api/doxygen/search/all_a.js
index 72424a989..1101a67eb 100644
--- a/docs/reference/api/doxygen/search/all_a.js
+++ b/docs/reference/api/doxygen/search/all_a.js
@@ -73,6 +73,7 @@ var searchData=
['injectdoublebuffer',['InjectDoubleBuffer',['../namespacetvm_1_1tir_1_1transform.html#a55f70a1b3cfc63c52b462fba772b8370',1,'tvm::tir::transform']]],
['injective_2eh',['injective.h',['../cuda_2injective_8h.html',1,'(Global Namespace)'],['../generic_2injective_8h.html',1,'(Global Namespace)'],['../rocm_2injective_8h.html',1,'(Global Namespace)'],['../x86_2injective_8h.html',1,'(Global Namespace)']]],
['injectprefetch',['InjectPrefetch',['../namespacetvm_1_1tir_1_1transform.html#a20aa23d8985679d2e09685729c644f0f',1,'tvm::tir::transform']]],
+ ['injectptxasynccopy',['InjectPTXAsyncCopy',['../namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a',1,'tvm::tir::transform']]],
['injectsoftwarepipeline',['InjectSoftwarePipeline',['../namespacetvm_1_1tir_1_1transform.html#a1b90f3ff7f983452fb3a4f7181043ae8',1,'tvm::tir::transform']]],
['injectvirtualthread',['InjectVirtualThread',['../namespacetvm_1_1tir_1_1transform.html#a37ade618ab7572f92bd37f69049966c7',1,'tvm::tir::transform']]],
['inline',['Inline',['../namespacetvm_1_1relay_1_1transform.html#aba5e588279a3b19a119c9aa28c364bbe',1,'tvm::relay::transform']]],
diff --git a/docs/reference/api/doxygen/search/functions_10.js b/docs/reference/api/doxygen/search/functions_10.js
index 31570fa39..4c7808bdc 100644
--- a/docs/reference/api/doxygen/search/functions_10.js
+++ b/docs/reference/api/doxygen/search/functions_10.js
@@ -7,7 +7,7 @@ var searchData=
['packetdone',['PacketDone',['../classtvm_1_1runtime_1_1micro__rpc_1_1WriteStream.html#a1745b7d9d5a0e094e129eb7a4c363ac9',1,'tvm::runtime::micro_rpc::WriteStream']]],
['packimportstoc',['PackImportsToC',['../namespacetvm_1_1codegen.html#abf02059ebadcdb8bbbe5c840b646d67b',1,'tvm::codegen']]],
['packimportstollvm',['PackImportsToLLVM',['../namespacetvm_1_1codegen.html#ab2cd2a65bac4b26427a8ca0abe4e0bd6',1,'tvm::codegen']]],
- ['pad',['Pad',['../namespacetvm_1_1topi.html#a97c798d0a0ec20a95d351618b83d5121',1,'tvm::topi::Pad(const Array< PrimExpr > shape, int odim)'],['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElement [...]
+ ['pad',['pad',['../namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5',1,'tvm::topi::pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElementWise, std::string pad_mode="constant", const Array< PrimExpr > *dyn_output_shape=nullptr)'],['../namespacetvm_1_1topi [...]
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
['parallel',['Parallel',['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()'],['../classtvm_1_1auto__scheduler_1_1State.html#a2376f0180bc5b5dd4b456f2a75d4a366',1,'tvm::auto_scheduler::State::parallel()'],['../classtvm_1_1te_1_1Stage.html#a60a6be10a1a96cb594c1399efabafef3',1,'tvm::te::Stage::parallel()']]],
['parallel_5ffor',['parallel_for',['../namespacetvm_1_1support.html#a8bf1225e8bb1db575578ca2d645fb23c',1,'tvm::support']]],
diff --git a/docs/reference/api/doxygen/search/functions_9.js b/docs/reference/api/doxygen/search/functions_9.js
index e81d8d041..b590ededc 100644
--- a/docs/reference/api/doxygen/search/functions_9.js
+++ b/docs/reference/api/doxygen/search/functions_9.js
@@ -34,6 +34,7 @@ var searchData=
['injectcopyintrin',['InjectCopyIntrin',['../namespacetvm_1_1tir_1_1transform.html#ae70d9af70526908167101609baaf4142',1,'tvm::tir::transform']]],
['injectdoublebuffer',['InjectDoubleBuffer',['../namespacetvm_1_1tir_1_1transform.html#a55f70a1b3cfc63c52b462fba772b8370',1,'tvm::tir::transform']]],
['injectprefetch',['InjectPrefetch',['../namespacetvm_1_1tir_1_1transform.html#a20aa23d8985679d2e09685729c644f0f',1,'tvm::tir::transform']]],
+ ['injectptxasynccopy',['InjectPTXAsyncCopy',['../namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a',1,'tvm::tir::transform']]],
['injectsoftwarepipeline',['InjectSoftwarePipeline',['../namespacetvm_1_1tir_1_1transform.html#a1b90f3ff7f983452fb3a4f7181043ae8',1,'tvm::tir::transform']]],
['injectvirtualthread',['InjectVirtualThread',['../namespacetvm_1_1tir_1_1transform.html#a37ade618ab7572f92bd37f69049966c7',1,'tvm::tir::transform']]],
['inline',['Inline',['../namespacetvm_1_1relay_1_1transform.html#aba5e588279a3b19a119c9aa28c364bbe',1,'tvm::relay::transform']]],
diff --git a/docs/reference/api/doxygen/search/variables_1.js b/docs/reference/api/doxygen/search/variables_1.js
index 047051268..90e01e3d5 100644
--- a/docs/reference/api/doxygen/search/variables_1.js
+++ b/docs/reference/api/doxygen/search/variables_1.js
@@ -33,6 +33,7 @@ var searchData=
['array',['array',['../classtvm_1_1runtime_1_1metadata_1_1MetadataArrayNode.html#abdd57cd8a05b571866df6871b782e8f2',1,'tvm::runtime::metadata::MetadataArrayNode']]],
['artifact_5fpath',['artifact_path',['../classtvm_1_1meta__schedule_1_1BuilderResultNode.html#a983cc8bd9acfdfdbafa27be4ba1909b2',1,'tvm::meta_schedule::BuilderResultNode::artifact_path()'],['../classtvm_1_1meta__schedule_1_1RunnerInputNode.html#aac63cc8e4abddd517917978a88130473',1,'tvm::meta_schedule::RunnerInputNode::artifact_path()']]],
['assert_5fshape',['assert_shape',['../structtvm_1_1relay_1_1AllocTensorAttrs.html#a5ebde62563fb62eefed70239e8a9c818',1,'tvm::relay::AllocTensorAttrs']]],
+ ['async_5fscope',['async_scope',['../namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16',1,'tvm::tir::attr']]],
['attach_5fivar',['attach_ivar',['../classtvm_1_1te_1_1StageNode.html#ad8a1f14b199103ecf22e7bf021eff8d4',1,'tvm::te::StageNode']]],
['attach_5fmap',['attach_map',['../classtvm_1_1auto__scheduler_1_1StateNode.html#afeeed629e92cb00c36c4da224ffa5022',1,'tvm::auto_scheduler::StateNode']]],
['attach_5fstage',['attach_stage',['../classtvm_1_1te_1_1StageNode.html#a75c8cf7d913a913e34abcaf6797540a5',1,'tvm::te::StageNode']]],
diff --git a/docs/reference/api/doxygen/stmt_8h.html b/docs/reference/api/doxygen/stmt_8h.html
index a6a1a682a..22f776b22 100644
--- a/docs/reference/api/doxygen/stmt_8h.html
+++ b/docs/reference/api/doxygen/stmt_8h.html
@@ -378,6 +378,9 @@ Variables</h2></td></tr>
<tr class="memitem:a36db026f638ad3d951c302796ddcae24"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#a36db026f638ad3d951c302796ddcae24">tvm::tir::attr::device_scope</a> = "device_scope"</td></tr>
<tr class="memdesc:a36db026f638ad3d951c302796ddcae24"><td class="mdescLeft"> </td><td class="mdescRight">Mark that it is in the device scope. <a href="namespacetvm_1_1tir_1_1attr.html#a36db026f638ad3d951c302796ddcae24">More...</a><br /></td></tr>
<tr class="separator:a36db026f638ad3d951c302796ddcae24"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:af86552e1cc4180ec1c8e14b582e49c16"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">tvm::tir::attr::async_scope</a> = "async_scope"</td></tr>
+<tr class="memdesc:af86552e1cc4180ec1c8e14b582e49c16"><td class="mdescLeft"> </td><td class="mdescRight">Mark that the attached statement runs asynchronously. <a href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">More...</a><br /></td></tr>
+<tr class="separator:af86552e1cc4180ec1c8e14b582e49c16"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a93d76d80fd7252d66991dc650693c0ef"><td class="memItemLeft" align="right" valign="top">constexpr const char * </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1attr.html#a93d76d80fd7252d66991dc650693c0ef">tvm::tir::attr::fragment_shape</a> = "fragment_shape"</td></tr>
<tr class="memdesc:a93d76d80fd7252d66991dc650693c0ef"><td class="mdescLeft"> </td><td class="mdescRight">Mark that the shape of TensorCore fragment. <a href="namespacetvm_1_1tir_1_1attr.html#a93d76d80fd7252d66991dc650693c0ef">More...</a><br /></td></tr>
<tr class="separator:a93d76d80fd7252d66991dc650693c0ef"><td class="memSeparator" colspan="2"> </td></tr>
diff --git a/docs/reference/api/doxygen/stmt_8h_source.html b/docs/reference/api/doxygen/stmt_8h_source.html
index 08d799804..c729fae6e 100644
--- a/docs/reference/api/doxygen/stmt_8h_source.html
+++ b/docs/reference/api/doxygen/stmt_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">stmt.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="stmt_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more contri [...]
+<a href="stmt_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more contri [...]
<div class="ttc" id="classtvm_1_1tir_1_1WhileNode_html_ae897db210a499a29a66aef4eaafcd043"><div class="ttname"><a href="classtvm_1_1tir_1_1WhileNode.html#ae897db210a499a29a66aef4eaafcd043">tvm::tir::WhileNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const WhileNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:998</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a2823f2e8c3ae9eec6c8f797752d1f9b5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a2823f2e8c3ae9eec6c8f797752d1f9b5">tvm::tir::attr::pragma_import_c</a></div><div class="ttdeci">constexpr const char * pragma_import_c</div><div class="ttdoc">Import C source or file into the final code gen module. </div><div class="ttdef"><b>Definition:</b> stmt.h:1367</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Store_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Store.html">tvm::tir::Store</a></div><div class="ttdoc">Managed reference to StoreNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:268</div></div>
@@ -113,7 +113,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ac62a341bfebe5448f290aa54b0f84cac"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ac62a341bfebe5448f290aa54b0f84cac">tvm::tir::attr::coproc_scope</a></div><div class="ttdeci">constexpr const char * coproc_scope</div><div class="ttdoc">Mark region is processed by a co-proccesor. </div><div class="ttdef"><b>Definition:</b> stmt.h:1329</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ProducerRealize_html"><div class="ttname"><a href="classtvm_1_1tir_1_1ProducerRealize.html">tvm::tir::ProducerRealize</a></div><div class="ttdoc">Managed reference to ProducerRealizeNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:502</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1IfThenElse_html"><div class="ttname"><a href="classtvm_1_1tir_1_1IfThenElse.html">tvm::tir::IfThenElse</a></div><div class="ttdoc">Managed reference to IfThenElseNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:818</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a16f0de00900235f9c158f20f345604a4"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a16f0de00900235f9c158f20f345604a4">tvm::tir::attr::meta_schedule_auto_tensorize</a></div><div class="ttdeci">constexpr const char * meta_schedule_auto_tensorize</div><div class="ttdoc">Mark that a block should be further rewritten using tensorization. </div><div class="ttdef"><b>Definition:</b> stmt.h:1515</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a16f0de00900235f9c158f20f345604a4"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a16f0de00900235f9c158f20f345604a4">tvm::tir::attr::meta_schedule_auto_tensorize</a></div><div class="ttdeci">constexpr const char * meta_schedule_auto_tensorize</div><div class="ttdoc">Mark that a block should be further rewritten using tensorization. </div><div class="ttdef"><b>Definition:</b> stmt.h:1520</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_a8ab45a20cd77a3c80187355aa211a9b9"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#a8ab45a20cd77a3c80187355aa211a9b9">tvm::tir::BufferRealizeNode::condition</a></div><div class="ttdeci">PrimExpr condition</div><div class="ttdoc">Only realize if condition holds. </div><div class="ttdef"><b>Definition:</b> stmt.h:348</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ac76fd8d0227265617e2f2bb8402d1e19"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ac76fd8d0227265617e2f2bb8402d1e19">tvm::tir::attr::buffer_bound</a></div><div class="ttdeci">constexpr const char * buffer_bound</div><div class="ttdoc">Mark stores/loads with theirs bounds. </div><div class="ttdef"><b>Definition:</b> stmt.h:1414</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html_a67693c4e97ae49890ea74605fe1b1f74"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html#a67693c4e97ae49890ea74605fe1b1f74">tvm::tir::StmtNode::StmtNode</a></div><div class="ttdeci">StmtNode(Span span)</div><div class="ttdef"><b>Definition:</b> stmt.h:47</div></div>
@@ -122,7 +122,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a0497d7cff1d672920c2fbd4d92869e62"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a0497d7cff1d672920c2fbd4d92869e62">tvm::tir::attr::buffer_bind_scope</a></div><div class="ttdeci">constexpr const char * buffer_bind_scope</div><div class="ttdoc">Bind the buffer specification to the region of the op When this scope occurs, the stmt...</div><div class="ttdef"><b>Definition:</b> stmt.h:1424</div></div>
<div class="ttc" id="namespacetvm_html_a1c4f14382b85bcfa57d9a3460db2354a"><div class="ttname"><a href="namespacetvm.html#a1c4f14382b85bcfa57d9a3460db2354a">tvm::equal</a></div><div class="ttdeci">PrimExpr equal(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">equal </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StoreNode_html_ab12bb36ca67086e7d3baf6f48f1c21fe"><div class="ttname"><a href="classtvm_1_1tir_1_1StoreNode.html#ab12bb36ca67086e7d3baf6f48f1c21fe">tvm::tir::StoreNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const StoreNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:248</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a07e62a6db9189700e996599541506e7c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a07e62a6db9189700e996599541506e7c">tvm::tir::attr::meta_schedule_unroll_explicit</a></div><div class="ttdeci">constexpr const char * meta_schedule_unroll_explicit</div><div class="ttdoc">Mark auto-unroll setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1507</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a07e62a6db9189700e996599541506e7c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a07e62a6db9189700e996599541506e7c">tvm::tir::attr::meta_schedule_unroll_explicit</a></div><div class="ttdeci">constexpr const char * meta_schedule_unroll_explicit</div><div class="ttdoc">Mark auto-unroll setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1512</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Var_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Var.html">tvm::tir::Var</a></div><div class="ttdoc">a named variable in TIR </div><div class="ttdef"><b>Definition:</b> var.h:88</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Evaluate_html_a3b7fb8cd8d3260eb76b3c6f0e68219b7"><div class="ttname"><a href="classtvm_1_1tir_1_1Evaluate.html#a3b7fb8cd8d3260eb76b3c6f0e68219b7">tvm::tir::Evaluate::Evaluate</a></div><div class="ttdeci">Evaluate(int value, Span span=Span())</div><div class="ttdef"><b>Definition:</b> stmt.h:860</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AssertStmtNode_html_ad4b51bee8779971bed4bdfeb72006d99"><div class="ttname"><a href="classtvm_1_1tir_1_1AssertStmtNode.html#ad4b51bee8779971bed4bdfeb72006d99">tvm::tir::AssertStmtNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:178</div></div>
@@ -137,9 +137,9 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1BufferRegionNode_html_aeb84cac3b7e0e349a0c36e479ae30307"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRegionNode.html#aeb84cac3b7e0e349a0c36e479ae30307">tvm::tir::BufferRegionNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:1085</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1MatchBufferRegionNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1MatchBufferRegionNode.html">tvm::tir::MatchBufferRegionNode</a></div><div class="ttdoc">Match introduces a constraint that the source buffer region can be remapped to the data layout specif...</div><div class="ttdef"><b>Definition:</b> stmt.h:1132</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ForNode_html_a4fe09a4b1fb71a8ae8d5e7c807d8540b"><div class="ttname"><a href="classtvm_1_1tir_1_1ForNode.html#a4fe09a4b1fb71a8ae8d5e7c807d8540b">tvm::tir::ForNode::kind</a></div><div class="ttdeci">ForKind kind</div><div class="ttdoc">The kind of the for loop. </div><div class="ttdef"><b>Definition:</b> stmt.h:912</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ad73f6ad441e1be3b2e71dead1e89f4bb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ad73f6ad441e1be3b2e71dead1e89f4bb">tvm::tir::attr::meta_schedule_thread_extent_high_inclusive</a></div><div class="ttdeci">constexpr const char * meta_schedule_thread_extent_high_inclusive</div><div class="ttdoc">The allowed range of thread extent in thread bindings. </div><div class="ttdef"><b>Definition:</b> stmt.h:1493</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ad73f6ad441e1be3b2e71dead1e89f4bb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ad73f6ad441e1be3b2e71dead1e89f4bb">tvm::tir::attr::meta_schedule_thread_extent_high_inclusive</a></div><div class="ttdeci">constexpr const char * meta_schedule_thread_extent_high_inclusive</div><div class="ttdoc">The allowed range of thread extent in thread bindings. </div><div class="ttdef"><b>Definition:</b> stmt.h:1498</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af00ba402645b1def7c543af3c48be80d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af00ba402645b1def7c543af3c48be80d">tvm::tir::attr::pragma_import_llvm</a></div><div class="ttdeci">constexpr const char * pragma_import_llvm</div><div class="ttdoc">Import llvm source or file into the final code gen module. </div><div class="ttdef"><b>Definition:</b> stmt.h:1369</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a385e883a7cecc309d063786e5fdf2c4b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a385e883a7cecc309d063786e5fdf2c4b">tvm::tir::attr::IsPragmaKey</a></div><div class="ttdeci">bool IsPragmaKey(const std::string &attr_key)</div><div class="ttdoc">Check if attr_key is a pragma key extension. </div><div class="ttdef"><b>Definition:</b> stmt.h:1522</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a385e883a7cecc309d063786e5fdf2c4b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a385e883a7cecc309d063786e5fdf2c4b">tvm::tir::attr::IsPragmaKey</a></div><div class="ttdeci">bool IsPragmaKey(const std::string &attr_key)</div><div class="ttdoc">Check if attr_key is a pragma key extension. </div><div class="ttdef"><b>Definition:</b> stmt.h:1527</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateNode_html_a05bb509b87de2d9de5bfbbcc7f71f97b"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateNode.html#a05bb509b87de2d9de5bfbbcc7f71f97b">tvm::tir::AllocateNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const AllocateNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:543</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ForNode_html_a014d871983a05a0c16efd6deb83a7472"><div class="ttname"><a href="classtvm_1_1tir_1_1ForNode.html#a014d871983a05a0c16efd6deb83a7472">tvm::tir::ForNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:930</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_a4925065f0bffd3221376be78150658c3"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#a4925065f0bffd3221376be78150658c3">tvm::tir::BufferRealizeNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const BufferRealizeNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:360</div></div>
@@ -152,7 +152,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html_af5d8bc86681742ef0bca9625751baccc"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html#af5d8bc86681742ef0bca9625751baccc">tvm::tir::StmtNode::_type_key</a></div><div class="ttdeci">static constexpr const char * _type_key</div><div class="ttdef"><b>Definition:</b> stmt.h:49</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRegion_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRegion.html">tvm::tir::BufferRegion</a></div><div class="ttdoc">Managed reference to BufferRegionNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:1100</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a3c66b2c968e985c3f4264979c18622e8"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a3c66b2c968e985c3f4264979c18622e8">tvm::tir::attr::script_parsing_detect_access</a></div><div class="ttdeci">constexpr const char * script_parsing_detect_access</div><div class="ttdoc">Mark whether the script-completer need to fill in missing access region during script parsing...</div><div class="ttdef"><b>Definition:</b> stmt.h:1466</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a3c66b2c968e985c3f4264979c18622e8"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a3c66b2c968e985c3f4264979c18622e8">tvm::tir::attr::script_parsing_detect_access</a></div><div class="ttdeci">constexpr const char * script_parsing_detect_access</div><div class="ttdoc">Mark whether the script-completer need to fill in missing access region during script parsing...</div><div class="ttdef"><b>Definition:</b> stmt.h:1471</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AttrStmtNode_html_a67c1ae1a8a7e7032f080aa3f5ae092fb"><div class="ttname"><a href="classtvm_1_1tir_1_1AttrStmtNode.html#a67c1ae1a8a7e7032f080aa3f5ae092fb">tvm::tir::AttrStmtNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body statement to be executed. </div><div class="ttdef"><b>Definition:</b> stmt.h:126</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1SeqStmtNode_html_a0e548955529d35c56e646fcaac38f865"><div class="ttname"><a href="classtvm_1_1tir_1_1SeqStmtNode.html#a0e548955529d35c56e646fcaac38f865">tvm::tir::SeqStmtNode::seq</a></div><div class="ttdeci">Array< Stmt > seq</div><div class="ttdoc">internal sequence content. </div><div class="ttdef"><b>Definition:</b> stmt.h:689</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a4bd38b620e1e9907216f3e583839dea3"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a4bd38b620e1e9907216f3e583839dea3">tvm::tir::attr::extern_scope</a></div><div class="ttdeci">constexpr const char * extern_scope</div><div class="ttdoc">Mark the scope as generated by extern primitive. such scope can contain arbitrary ir program and we n...</div><div class="ttdef"><b>Definition:</b> stmt.h:1342</div></div>
@@ -165,7 +165,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1AssertStmt_html"><div class="ttname"><a href="classtvm_1_1tir_1_1AssertStmt.html">tvm::tir::AssertStmt</a></div><div class="ttdoc">Managed reference to AssertStmtNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:204</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ProducerStoreNode_html_a309eb2fa800a2862c111024eebb05603"><div class="ttname"><a href="classtvm_1_1tir_1_1ProducerStoreNode.html#a309eb2fa800a2862c111024eebb05603">tvm::tir::ProducerStoreNode::producer</a></div><div class="ttdeci">DataProducer producer</div><div class="ttdoc">The producer to store the results into. </div><div class="ttdef"><b>Definition:</b> stmt.h:407</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRegionNode_html_a91c3f1c701a3a0fd2cba3d93f5c3296d"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRegionNode.html#a91c3f1c701a3a0fd2cba3d93f5c3296d">tvm::tir::BufferRegionNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:1076</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af7d82995b58b837ac941af54bb70afec"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af7d82995b58b837ac941af54bb70afec">tvm::tir::attr::meta_schedule_vectorize</a></div><div class="ttdeci">constexpr const char * meta_schedule_vectorize</div><div class="ttdoc">Mark auto-vectorize setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1504</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af7d82995b58b837ac941af54bb70afec"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af7d82995b58b837ac941af54bb70afec">tvm::tir::attr::meta_schedule_vectorize</a></div><div class="ttdeci">constexpr const char * meta_schedule_vectorize</div><div class="ttdoc">Mark auto-vectorize setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1509</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a61b1ef1047fb722a4e5ec2167c9963d7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a61b1ef1047fb722a4e5ec2167c9963d7">tvm::tir::attr::device_id</a></div><div class="ttdeci">constexpr const char * device_id</div><div class="ttdoc">The allocation device for global malloc in host. </div><div class="ttdef"><b>Definition:</b> stmt.h:1353</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1LetStmtNode_html_a7850acd81a91e2f2af31066a5f58c273"><div class="ttname"><a href="classtvm_1_1tir_1_1LetStmtNode.html#a7850acd81a91e2f2af31066a5f58c273">tvm::tir::LetStmtNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const LetStmtNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:81</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRegionNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRegionNode.html">tvm::tir::BufferRegionNode</a></div><div class="ttdoc">Representing the region of multi-dimensional buffer access. </div><div class="ttdef"><b>Definition:</b> stmt.h:1069</div></div>
@@ -208,14 +208,14 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1AllocateConstNode_html_ae7f699117366d84d30e8e02656b0afd6"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateConstNode.html#ae7f699117366d84d30e8e02656b0afd6">tvm::tir::AllocateConstNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:621</div></div>
<div class="ttc" id="tir_2expr_8h_html"><div class="ttname"><a href="tir_2expr_8h.html">expr.h</a></div><div class="ttdoc">TIR expressions. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html">tvm::runtime::Array</a></div><div class="ttdoc">Array, container representing a contiguous sequence of ObjectRefs. </div><div class="ttdef"><b>Definition:</b> array.h:270</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a9b33cc65f756817e691b49782ee103bd"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a9b33cc65f756817e691b49782ee103bd">tvm::tir::attr::fragment_layout</a></div><div class="ttdeci">constexpr const char * fragment_layout</div><div class="ttdoc">Mark that the layout of TensorCore fragment. </div><div class="ttdef"><b>Definition:</b> stmt.h:1452</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a9b33cc65f756817e691b49782ee103bd"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a9b33cc65f756817e691b49782ee103bd">tvm::tir::attr::fragment_layout</a></div><div class="ttdeci">constexpr const char * fragment_layout</div><div class="ttdoc">Mark that the layout of TensorCore fragment. </div><div class="ttdef"><b>Definition:</b> stmt.h:1457</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a50fc9633b9cfbcefa2393dbb2ece1846"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a50fc9633b9cfbcefa2393dbb2ece1846">tvm::tir::attr::reduce_scope</a></div><div class="ttdeci">constexpr const char * reduce_scope</div><div class="ttdoc">Mark of reduce scope. </div><div class="ttdef"><b>Definition:</b> stmt.h:1359</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateNode_html_a99fdb058ac50da40885f5261f476b07d"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateNode.html#a99fdb058ac50da40885f5261f476b07d">tvm::tir::AllocateNode::ConstantAllocationSize</a></div><div class="ttdeci">int64_t ConstantAllocationSize() const</div><div class="ttdoc">If the buffer size is constant, return the size. Otherwise return 0. </div><div class="ttdef"><b>Definition:</b> stmt.h:563</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1WhileNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1WhileNode.html">tvm::tir::WhileNode</a></div><div class="ttdoc">A While loop. </div><div class="ttdef"><b>Definition:</b> stmt.h:985</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ForNode_html_ac92e3680d0609f7789b08cc235095de5"><div class="ttname"><a href="classtvm_1_1tir_1_1ForNode.html#ac92e3680d0609f7789b08cc235095de5">tvm::tir::ForNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body of the for loop. </div><div class="ttdef"><b>Definition:</b> stmt.h:914</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1SeqStmtNode_html_ab4b4714e5e29a083787e11444b06a9eb"><div class="ttname"><a href="classtvm_1_1tir_1_1SeqStmtNode.html#ab4b4714e5e29a083787e11444b06a9eb">tvm::tir::SeqStmtNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:707</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AttrStmtNode_html_a57866773c4482d9d4836f42b9ab3d002"><div class="ttname"><a href="classtvm_1_1tir_1_1AttrStmtNode.html#a57866773c4482d9d4836f42b9ab3d002">tvm::tir::AttrStmtNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:141</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a694f6b5653f5e1ee916abf107462cd7b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a694f6b5653f5e1ee916abf107462cd7b">tvm::tir::attr::meta_schedule_thread_extent_low_inclusive</a></div><div class="ttdeci">constexpr const char * meta_schedule_thread_extent_low_inclusive</div><div class="ttdoc">The allowed range of thread extent in thread bindings. </div><div class="ttdef"><b>Definition:</b> stmt.h:1489</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a694f6b5653f5e1ee916abf107462cd7b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a694f6b5653f5e1ee916abf107462cd7b">tvm::tir::attr::meta_schedule_thread_extent_low_inclusive</a></div><div class="ttdeci">constexpr const char * meta_schedule_thread_extent_low_inclusive</div><div class="ttdoc">The allowed range of thread extent in thread bindings. </div><div class="ttdef"><b>Definition:</b> stmt.h:1494</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ac95fbd1c09a60b10c7a5d07f6c4b68a6"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ac95fbd1c09a60b10c7a5d07f6c4b68a6">tvm::tir::attr::prefetch_scope</a></div><div class="ttdeci">constexpr const char * prefetch_scope</div><div class="ttdoc">Mark of prefetch scope, value=offset, run prefetch of Tensor on the current loop scope. </div><div class="ttdef"><b>Definition:</b> stmt.h:1376</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1WhileNode_html_a5d50916f22cd25b9723b178cf818be62"><div class="ttname"><a href="classtvm_1_1tir_1_1WhileNode.html#a5d50916f22cd25b9723b178cf818be62">tvm::tir::WhileNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body of the while loop. </div><div class="ttdef"><b>Definition:</b> stmt.h:990</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_ab332fa7cb914acec5456d63a698c7d34"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#ab332fa7cb914acec5456d63a698c7d34">tvm::tir::BufferRealizeNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body of realization. </div><div class="ttdef"><b>Definition:</b> stmt.h:350</div></div>
@@ -225,10 +225,11 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1AssertStmtNode_html_ad861e0e3a9f7d7aefe60cba36241d226"><div class="ttname"><a href="classtvm_1_1tir_1_1AssertStmtNode.html#ad861e0e3a9f7d7aefe60cba36241d226">tvm::tir::AssertStmtNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">Body which this assertion holds true. Will be executed after the assertion. </div><div class="ttdef"><b>Definition:</b> stmt.h:176</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1MatchBufferRegionNode_html_a670c1468d4b099fd35247c94555413b7"><div class="ttname"><a href="classtvm_1_1tir_1_1MatchBufferRegionNode.html#a670c1468d4b099fd35247c94555413b7">tvm::tir::MatchBufferRegionNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:1139</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1SeqStmtNode_html_a3196bba617d63bab596f363ae1f932d1"><div class="ttname"><a href="classtvm_1_1tir_1_1SeqStmtNode.html#a3196bba617d63bab596f363ae1f932d1">tvm::tir::SeqStmtNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:698</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a350918383cf7d7c9a95114ab7fda7781"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a350918383cf7d7c9a95114ab7fda7781">tvm::tir::attr::meta_schedule_random_compute_producer</a></div><div class="ttdeci">constexpr const char * meta_schedule_random_compute_producer</div><div class="ttdoc">Mark the block whose producer needs to be applied by rule Random-Compute-Location. </div><div class="ttdef"><b>Definition:</b> stmt.h:1497 [...]
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a350918383cf7d7c9a95114ab7fda7781"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a350918383cf7d7c9a95114ab7fda7781">tvm::tir::attr::meta_schedule_random_compute_producer</a></div><div class="ttdeci">constexpr const char * meta_schedule_random_compute_producer</div><div class="ttdoc">Mark the block whose producer needs to be applied by rule Random-Compute-Location. </div><div class="ttdef"><b>Definition:</b> stmt.h:1502 [...]
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html_ab7e026e32383e67e620719b025e00056"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html#ab7e026e32383e67e620719b025e00056">tvm::tir::StmtNode::_type_has_method_shash_reduce</a></div><div class="ttdeci">static constexpr const bool _type_has_method_shash_reduce</div><div class="ttdef"><b>Definition:</b> stmt.h:51</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_a9f59694e9c3912cc5e80654ddbc1e40aa037de60b0cc37e063125a29b487104b7"><div class="ttname"><a href="namespacetvm_1_1tir.html#a9f59694e9c3912cc5e80654ddbc1e40aa037de60b0cc37e063125a29b487104b7">tvm::tir::ForKind::kThreadBinding</a></div><div class="ttdoc">The loop variable is bound to a thread in an environment. In the final stage of lowering, the loop is simply removed and the loop variable is mapped to the corresponding context thread. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af86552e1cc4180ec1c8e14b582e49c16"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af86552e1cc4180ec1c8e14b582e49c16">tvm::tir::attr::async_scope</a></div><div class="ttdeci">constexpr const char * async_scope</div><div class="ttdoc">Mark that the attached statement runs asynchronously. </div><div class="ttdef"><b>Definition:</b> stmt.h:1447</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a9231fc0afe37a8d46a90a1c5fdf522bb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a9231fc0afe37a8d46a90a1c5fdf522bb">tvm::tir::attr::double_buffer_scope</a></div><div class="ttdeci">constexpr const char * double_buffer_scope</div><div class="ttdoc">Marks production of double buffer data. </div><div class="ttdef"><b>Definition:</b> stmt.h:1395</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockRealizeNode_html_ac3b02808faa6243c3ce8075491bc19af"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockRealizeNode.html#ac3b02808faa6243c3ce8075491bc19af">tvm::tir::BlockRealizeNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:1287</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealize_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealize.html">tvm::tir::BufferRealize</a></div><div class="ttdoc">Managed reference to BufferRealizeNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:385</div></div>
@@ -260,7 +261,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_a7499147f235dea4d214584c7ea1e13a0"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#a7499147f235dea4d214584c7ea1e13a0">tvm::tir::BufferRealizeNode::BufferRealizeNode</a></div><div class="ttdeci">BufferRealizeNode(Buffer buffer, Array< Range > bounds, PrimExpr condition, Stmt body, Span span=Span())</div><div class="ttdef"><b>Definition:</b> stmt.h:373</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="object_8h_html_af8330e3864503fb7c4133ae4d48fe4a2"><div class="ttname"><a href="object_8h.html#af8330e3864503fb7c4133ae4d48fe4a2">TVM_DEFINE_OBJECT_REF_COW_METHOD</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_COW_METHOD(ObjectName)</div><div class="ttdoc">Define CopyOnWrite function in an ObjectRef. </div><div class="ttdef"><b>Definition:</b> object.h:785</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a064b547bf5b0579f9b42906c6a9c581d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a064b547bf5b0579f9b42906c6a9c581d">tvm::tir::attr::software_pipeline_order</a></div><div class="ttdeci">constexpr const char * software_pipeline_order</div><div class="ttdoc">Mark the order of a statement in the software pipeline. </div><div class="ttdef"><b>Definition:</b> stmt.h:1477</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a064b547bf5b0579f9b42906c6a9c581d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a064b547bf5b0579f9b42906c6a9c581d">tvm::tir::attr::software_pipeline_order</a></div><div class="ttdeci">constexpr const char * software_pipeline_order</div><div class="ttdoc">Mark the order of a statement in the software pipeline. </div><div class="ttdef"><b>Definition:</b> stmt.h:1482</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1EvaluateNode_html_a1caeaa3ef59c8ffb2938931359c1a9a9"><div class="ttname"><a href="classtvm_1_1tir_1_1EvaluateNode.html#a1caeaa3ef59c8ffb2938931359c1a9a9">tvm::tir::EvaluateNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:846</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StoreNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1StoreNode.html">tvm::tir::StoreNode</a></div><div class="ttdoc">Store value to the buffer. </div><div class="ttdef"><b>Definition:</b> stmt.h:229</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1DataProducer_html"><div class="ttname"><a href="classtvm_1_1tir_1_1DataProducer.html">tvm::tir::DataProducer</a></div><div class="ttdoc">Managed reference to DataProducerNode. </div><div class="ttdef"><b>Definition:</b> buffer.h:293</div></div>
@@ -274,7 +275,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1AttrStmtNode_html_a4228adcc9320d1f1ce5f9caba1e4faf9"><div class="ttname"><a href="classtvm_1_1tir_1_1AttrStmtNode.html#a4228adcc9320d1f1ce5f9caba1e4faf9">tvm::tir::AttrStmtNode::value</a></div><div class="ttdeci">PrimExpr value</div><div class="ttdoc">The attribute value, value is well defined at current scope. </div><div class="ttdef"><b>Definition:</b> stmt.h:124</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockNode_html_ab6392a2ebeb339844c292007f91ea1c5"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockNode.html#ab6392a2ebeb339844c292007f91ea1c5">tvm::tir::BlockNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:1239</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateNode_html_ace9d920ce4eb49f8b774734870f462f6"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateNode.html#ace9d920ce4eb49f8b774734870f462f6">tvm::tir::AllocateNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:549</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a2e695603b89f78f4a481817dbaf7a082"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a2e695603b89f78f4a481817dbaf7a082">tvm::tir::attr::software_pipeline_stage</a></div><div class="ttdeci">constexpr const char * software_pipeline_stage</div><div class="ttdoc">Mark the stage of a statement in the software pipeline. </div><div class="ttdef"><b>Definition:</b> stmt.h:1474</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a2e695603b89f78f4a481817dbaf7a082"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a2e695603b89f78f4a481817dbaf7a082">tvm::tir::attr::software_pipeline_stage</a></div><div class="ttdeci">constexpr const char * software_pipeline_stage</div><div class="ttdoc">Mark the stage of a statement in the software pipeline. </div><div class="ttdef"><b>Definition:</b> stmt.h:1479</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html_aa6df02a086d50e504f45a6b55566cff9"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html#aa6df02a086d50e504f45a6b55566cff9">tvm::tir::StmtNode::span</a></div><div class="ttdeci">Span span</div><div class="ttdoc">Span that points to the original source code. Reserved debug information. </div><div class="ttdef"><b>Definition:</b> stmt.h:44</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferStoreNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferStoreNode.html">tvm::tir::BufferStoreNode</a></div><div class="ttdoc">Store value to the high dimension buffer. </div><div class="ttdef"><b>Definition:</b> stmt.h:286</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferStore_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferStore.html">tvm::tir::BufferStore</a></div><div class="ttdoc">Managed reference to BufferStoreNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:321</div></div>
@@ -289,13 +290,13 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_a1e66d8e7ccb2d0ab73a44775edabb38d"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#a1e66d8e7ccb2d0ab73a44775edabb38d">tvm::tir::BufferRealizeNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:352</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AssertStmtNode_html_a016ff228d0c944b8d295223f54858493"><div class="ttname"><a href="classtvm_1_1tir_1_1AssertStmtNode.html#a016ff228d0c944b8d295223f54858493">tvm::tir::AssertStmtNode::condition</a></div><div class="ttdeci">PrimExpr condition</div><div class="ttdoc">Condition to be checked. </div><div class="ttdef"><b>Definition:</b> stmt.h:169</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html_a79e21b14d3ab57209577bf4a8f694a87"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html#a79e21b14d3ab57209577bf4a8f694a87">tvm::tir::StmtNode::StmtNode</a></div><div class="ttdeci">StmtNode()=default</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_afdc8510abcf9d0c3b3dd9f30046b5c0f"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#afdc8510abcf9d0c3b3dd9f30046b5c0f">tvm::tir::attr::meta_schedule_parallel</a></div><div class="ttdeci">constexpr const char * meta_schedule_parallel</div><div class="ttdoc">Mark auto-parallel setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1501</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_afdc8510abcf9d0c3b3dd9f30046b5c0f"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#afdc8510abcf9d0c3b3dd9f30046b5c0f">tvm::tir::attr::meta_schedule_parallel</a></div><div class="ttdeci">constexpr const char * meta_schedule_parallel</div><div class="ttdoc">Mark auto-parallel setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1506</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockRealizeNode_html_a0966ff56032dfb62ff35165fe4e3f6b5"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockRealizeNode.html#a0966ff56032dfb62ff35165fe4e3f6b5">tvm::tir::BlockRealizeNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const BlockRealizeNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:1293</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Map_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Map.html">tvm::runtime::Map</a></div><div class="ttdoc">Map container of NodeRef->NodeRef in DSL graph. Map implements copy on write semantics, which means map is mutable but copy will happen when array is referenced in more than two places. </div><div class="ttdef"><b>Definition:</b> map.h:1268</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af84871a6d841168f8501f141676dfaeb"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af84871a6d841168f8501f141676dfaeb">tvm::tir::attr::double_buffer_write</a></div><div class="ttdeci">constexpr const char * double_buffer_write</div><div class="ttdoc">Marks region used by double buffer write. </div><div class="ttdef"><b>Definition:</b> stmt.h:1399</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateNode_html_a797e50c85f4bc016bcf3a3a22737980e"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateNode.html#a797e50c85f4bc016bcf3a3a22737980e">tvm::tir::AllocateNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body to be executed. </div><div class="ttdef"><b>Definition:</b> stmt.h:524</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a0d026645d3f86d9cc2e693fa232fddec"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a0d026645d3f86d9cc2e693fa232fddec">tvm::tir::attr::hand_threaded</a></div><div class="ttdeci">constexpr const char * hand_threaded</div><div class="ttdoc">Mark that the kernel is hand threaded and doesn&#39;t need syncs inserted. </div><div class="ttdef"><b>Definition:</b> stmt.h:1457</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a5267857a903d20285f4e0af38d2d9004"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a5267857a903d20285f4e0af38d2d9004">tvm::tir::attr::meta_schedule_unroll_implicit</a></div><div class="ttdeci">constexpr const char * meta_schedule_unroll_implicit</div><div class="ttdoc">Mark auto-unroll setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1510</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a0d026645d3f86d9cc2e693fa232fddec"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a0d026645d3f86d9cc2e693fa232fddec">tvm::tir::attr::hand_threaded</a></div><div class="ttdeci">constexpr const char * hand_threaded</div><div class="ttdoc">Mark that the kernel is hand threaded and doesn&#39;t need syncs inserted. </div><div class="ttdef"><b>Definition:</b> stmt.h:1462</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a5267857a903d20285f4e0af38d2d9004"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a5267857a903d20285f4e0af38d2d9004">tvm::tir::attr::meta_schedule_unroll_implicit</a></div><div class="ttdeci">constexpr const char * meta_schedule_unroll_implicit</div><div class="ttdoc">Mark auto-unroll setting on the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1515</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockNode_html_a7025783637b84afdb3317940ebbe5825"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockNode.html#a7025783637b84afdb3317940ebbe5825">tvm::tir::BlockNode::writes</a></div><div class="ttdeci">Array< BufferRegion > writes</div><div class="ttdoc">The write buffer regions of the block. </div><div class="ttdef"><b>Definition:</b> stmt.h:1198</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1LetStmtNode_html_a91c45a2872aa76e40b39328ce7b7888c"><div class="ttname"><a href="classtvm_1_1tir_1_1LetStmtNode.html#a91c45a2872aa76e40b39328ce7b7888c">tvm::tir::LetStmtNode::body</a></div><div class="ttdeci">Stmt body</div><div class="ttdoc">The body block. </div><div class="ttdef"><b>Definition:</b> stmt.h:72</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a9125ab905a93924ee79269aa808ed517"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a9125ab905a93924ee79269aa808ed517">tvm::tir::attr::loop_scope</a></div><div class="ttdeci">constexpr const char * loop_scope</div><div class="ttdoc">Mark of loop scope. </div><div class="ttdef"><b>Definition:</b> stmt.h:1357</div></div>
@@ -323,15 +324,15 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1SeqStmt_html"><div class="ttname"><a href="classtvm_1_1tir_1_1SeqStmt.html">tvm::tir::SeqStmt</a></div><div class="ttdoc">Sequence statement. </div><div class="ttdef"><b>Definition:</b> stmt.h:714</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateNode_html_ab476a2f1664e28a6da78dfa1d7bc2889"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateNode.html#ab476a2f1664e28a6da78dfa1d7bc2889">tvm::tir::AllocateNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> stmt.h:533</div></div>
<div class="ttc" id="namespacetvm_html_aae7034e3e41c18e7fb78ff32bfc6a318"><div class="ttname"><a href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">tvm::NullOpt</a></div><div class="ttdeci">constexpr runtime::NullOptType NullOpt</div><div class="ttdef"><b>Definition:</b> optional.h:160</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a82bba3064a40ce62c958db4b120471a7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a82bba3064a40ce62c958db4b120471a7">tvm::tir::attr::meta_schedule_cooperative_fetch</a></div><div class="ttdeci">constexpr const char * meta_schedule_cooperative_fetch</div><div class="ttdoc">Mark that the loop should be further skip and bound to environment threads to enable cooperative fetc...</div><div class="ttdef"><b>Definition:</b> st [...]
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a82bba3064a40ce62c958db4b120471a7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a82bba3064a40ce62c958db4b120471a7">tvm::tir::attr::meta_schedule_cooperative_fetch</a></div><div class="ttdeci">constexpr const char * meta_schedule_cooperative_fetch</div><div class="ttdoc">Mark that the loop should be further skip and bound to environment threads to enable cooperative fetc...</div><div class="ttdef"><b>Definition:</b> st [...]
<div class="ttc" id="classtvm_1_1tir_1_1AllocateConstNode_html_a39f1c1d601f09c52fc947f094234f1e8"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateConstNode.html#a39f1c1d601f09c52fc947f094234f1e8">tvm::tir::AllocateConstNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> stmt.h:638</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRegionNode_html_a4714e33793013f82799569848e96398b"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRegionNode.html#a4714e33793013f82799569848e96398b">tvm::tir::BufferRegionNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const BufferRegionNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> stmt.h:1081</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a2aa4a05a037f033dfdf56f8d19dd7f3d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a2aa4a05a037f033dfdf56f8d19dd7f3d">tvm::tir::attr::meta_schedule_tiling_structure</a></div><div class="ttdeci">constexpr const char * meta_schedule_tiling_structure</div><div class="ttdoc">Mark the tiling structure of blocks that are applied by rule Multi-Level-Tiling. </div><div class="ttdef"><b>Definition:</b> stmt.h:1480</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a2aa4a05a037f033dfdf56f8d19dd7f3d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a2aa4a05a037f033dfdf56f8d19dd7f3d">tvm::tir::attr::meta_schedule_tiling_structure</a></div><div class="ttdeci">constexpr const char * meta_schedule_tiling_structure</div><div class="ttdoc">Mark the tiling structure of blocks that are applied by rule Multi-Level-Tiling. </div><div class="ttdef"><b>Definition:</b> stmt.h:1485</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Evaluate_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Evaluate.html">tvm::tir::Evaluate</a></div><div class="ttdoc">Managed reference to EvaluateNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:856</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a93d76d80fd7252d66991dc650693c0ef"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a93d76d80fd7252d66991dc650693c0ef">tvm::tir::attr::fragment_shape</a></div><div class="ttdeci">constexpr const char * fragment_shape</div><div class="ttdoc">Mark that the shape of TensorCore fragment. </div><div class="ttdef"><b>Definition:</b> stmt.h:1447</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a93d76d80fd7252d66991dc650693c0ef"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a93d76d80fd7252d66991dc650693c0ef">tvm::tir::attr::fragment_shape</a></div><div class="ttdeci">constexpr const char * fragment_shape</div><div class="ttdoc">Mark that the shape of TensorCore fragment. </div><div class="ttdef"><b>Definition:</b> stmt.h:1452</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1ForNode_html_ab54798257255b682a1aad74cec33e070"><div class="ttname"><a href="classtvm_1_1tir_1_1ForNode.html#ab54798257255b682a1aad74cec33e070">tvm::tir::ForNode::extent</a></div><div class="ttdeci">PrimExpr extent</div><div class="ttdoc">The extent of the iteration. </div><div class="ttdef"><b>Definition:</b> stmt.h:910</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_a2d76fa1fb628ff276a284e61123589c5"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#a2d76fa1fb628ff276a284e61123589c5">tvm::runtime::ObjectRef::as</a></div><div class="ttdeci">const ObjectType * as() const</div><div class="ttdoc">Try to downcast the internal Object to a raw pointer of a corresponding type. </div><div class="ttdef"><b>Definition:</b> object.h:865</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_html_a03c36414c1be2960099e023ffba09f6e"><div class="ttname"><a href="namespacetvm_1_1tir.html#a03c36414c1be2960099e023ffba09f6e">tvm::tir::ForKind2String</a></div><div class="ttdeci">const char * ForKind2String(ForKind t)</div><div class="ttdef"><b>Definition:</b> stmt.h:1539</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_html_a03c36414c1be2960099e023ffba09f6e"><div class="ttname"><a href="namespacetvm_1_1tir.html#a03c36414c1be2960099e023ffba09f6e">tvm::tir::ForKind2String</a></div><div class="ttdeci">const char * ForKind2String(ForKind t)</div><div class="ttdef"><b>Definition:</b> stmt.h:1544</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_af08d3d2b645a914f1a64d81e45f3b86a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#af08d3d2b645a914f1a64d81e45f3b86a">tvm::tir::attr::pragma_scope_prefix</a></div><div class="ttdeci">constexpr const char * pragma_scope_prefix</div><div class="ttdoc">Mark region is guarded by the pragma extension. </div><div class="ttdef"><b>Definition:</b> stmt.h:1365</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BufferRealizeNode_html_ac111908806003589f64a8eb7b068272f"><div class="ttname"><a href="classtvm_1_1tir_1_1BufferRealizeNode.html#ac111908806003589f64a8eb7b068272f">tvm::tir::BufferRealizeNode::bounds</a></div><div class="ttdeci">Array< Range > bounds</div><div class="ttdoc">Bounds to be realized. </div><div class="ttdef"><b>Definition:</b> stmt.h:346</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a84f5d42e968fd8f4cdd7a4aac7ba2137"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a84f5d42e968fd8f4cdd7a4aac7ba2137">tvm::tir::attr::scan_update_scope</a></div><div class="ttdeci">constexpr const char * scan_update_scope</div><div class="ttdoc">Mark of scan update scope. </div><div class="ttdef"><b>Definition:</b> stmt.h:1403</div></div>
@@ -358,7 +359,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1StoreNode_html_aed2fc3d3c119126a61182666930e8729"><div class="ttname"><a href="classtvm_1_1tir_1_1StoreNode.html#aed2fc3d3c119126a61182666930e8729">tvm::tir::StoreNode::buffer_var</a></div><div class="ttdeci">Var buffer_var</div><div class="ttdoc">The buffer variable. </div><div class="ttdef"><b>Definition:</b> stmt.h:232</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a464533c1560ace5e0b5071ba6902482e"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a464533c1560ace5e0b5071ba6902482e">tvm::tir::attr::virtual_thread</a></div><div class="ttdeci">constexpr const char * virtual_thread</div><div class="ttdoc">Mark launching of a virtual thread. </div><div class="ttdef"><b>Definition:</b> stmt.h:1327</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1AllocateConstNode_html_ad540975cdb5def27f3aa3564b2f427db"><div class="ttname"><a href="classtvm_1_1tir_1_1AllocateConstNode.html#ad540975cdb5def27f3aa3564b2f427db">tvm::tir::AllocateConstNode::ConstantAllocationSize</a></div><div class="ttdeci">int64_t ConstantAllocationSize() const</div><div class="ttdoc">If the buffer size is constant, return the size. Otherwise return 0. </div><div class="ttdef"><b>Definition:</b> stmt.h:652</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ae6bb4bdf780d88ac330ad27c6c94e0f7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ae6bb4bdf780d88ac330ad27c6c94e0f7">tvm::tir::attr::pragma_loop_partition_hint</a></div><div class="ttdeci">constexpr const char * pragma_loop_partition_hint</div><div class="ttdoc">Mark that the loop should be partitioned. </div><div class="ttdef"><b>Definition:</b> stmt.h:1471</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_ae6bb4bdf780d88ac330ad27c6c94e0f7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#ae6bb4bdf780d88ac330ad27c6c94e0f7">tvm::tir::attr::pragma_loop_partition_hint</a></div><div class="ttdeci">constexpr const char * pragma_loop_partition_hint</div><div class="ttdoc">Mark that the loop should be partitioned. </div><div class="ttdef"><b>Definition:</b> stmt.h:1476</div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/tir_2transform_8h.html b/docs/reference/api/doxygen/tir_2transform_8h.html
index ba6c433fe..e2a67f8dd 100644
--- a/docs/reference/api/doxygen/tir_2transform_8h.html
+++ b/docs/reference/api/doxygen/tir_2transform_8h.html
@@ -264,6 +264,9 @@ Functions</h2></td></tr>
<tr class="memitem:a70bda35bb43e9420c8115bb1ec977811"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a70bda35bb43e9420c8115bb1ec977811">tvm::tir::transform::Filter</a> (runtime::TypedPackedFunc< bool(PrimFunc)> fcond)</td></tr>
<tr class="memdesc:a70bda35bb43e9420c8115bb1ec977811"><td class="mdescLeft"> </td><td class="mdescRight">Filter PrimFuncs with a given condition. <a href="namespacetvm_1_1tir_1_1transform.html#a70bda35bb43e9420c8115bb1ec977811">More...</a><br /></td></tr>
<tr class="separator:a70bda35bb43e9420c8115bb1ec977811"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac804d5f6bd95449af8d09f26b804db4a"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">tvm::tir::transform::InjectPTXAsyncCopy</a> ()</td></tr>
+<tr class="memdesc:ac804d5f6bd95449af8d09f26b804db4a"><td class="mdescLeft"> </td><td class="mdescRight">Pass to rewrite global to shared memory copy on CUDA with asyncronous copy. <a href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">More...</a><br /></td></tr>
+<tr class="separator:ac804d5f6bd95449af8d09f26b804db4a"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
<div class="textblock"><p>TIR specific transformation passes. </p>
diff --git a/docs/reference/api/doxygen/tir_2transform_8h_source.html b/docs/reference/api/doxygen/tir_2transform_8h_source.html
index 00e707ac7..9040e0467 100644
--- a/docs/reference/api/doxygen/tir_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/tir_2transform_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="tir_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
+<a href="tir_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a0979c9d3bf0e64205f16aa00d331c6b5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a0979c9d3bf0e64205f16aa00d331c6b5">tvm::tir::transform::LowerIntrin</a></div><div class="ttdeci">Pass LowerIntrin()</div><div class="ttdoc">Lower the target specific function intrinsics in each of the function. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ae10fc2ab38a0cdfe79cb7f718549f532"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ae10fc2ab38a0cdfe79cb7f718549f532">tvm::tir::transform::InferFragment</a></div><div class="ttdeci">Pass InferFragment()</div><div class="ttdoc">Infer the TensorCore fragment infomation using tensor intrinsics. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a778d3e1efecdff97e7bcf0e6a5406e61"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a778d3e1efecdff97e7bcf0e6a5406e61">tvm::tir::transform::StorageFlatten</a></div><div class="ttdeci">Pass StorageFlatten(int cache_line_size, bool create_bound_attribute=false)</div><div class="ttdoc">Flatten the multi-dimensional read/write to single dimensional Load/Store. </div></div>
@@ -131,6 +131,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a0d6b2682a93ca4136ed4fa6d8fa7bc2f"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a0d6b2682a93ca4136ed4fa6d8fa7bc2f">tvm::tir::transform::LowerCustomDatatypes</a></div><div class="ttdeci">Pass LowerCustomDatatypes()</div><div class="ttdoc">Lower custom datatypes. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a55f70a1b3cfc63c52b462fba772b8370"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a55f70a1b3cfc63c52b462fba772b8370">tvm::tir::transform::InjectDoubleBuffer</a></div><div class="ttdeci">Pass InjectDoubleBuffer()</div><div class="ttdoc">Inject double buffer statements. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a0010cbc20ee308819046d77ad58b62cf"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a0010cbc20ee308819046d77ad58b62cf">tvm::tir::transform::ThreadSync</a></div><div class="ttdeci">Pass ThreadSync(String storage_scope)</div><div class="ttdoc">Insert sync between parallel read/write of shared buffers. </div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ac804d5f6bd95449af8d09f26b804db4a"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ac804d5f6bd95449af8d09f26b804db4a">tvm::tir::transform::InjectPTXAsyncCopy</a></div><div class="ttdeci">Pass InjectPTXAsyncCopy()</div><div class="ttdoc">Pass to rewrite global to shared memory copy on CUDA with asyncronous copy. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a82c5b1caff09436701fb9b9e7f672571"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a82c5b1caff09436701fb9b9e7f672571">tvm::tir::transform::CommonSubexprElimTIR</a></div><div class="ttdeci">Pass CommonSubexprElimTIR(bool enable_cse_tir=true, bool identify_equiv_terms=false)</div><div class="ttdoc">Implements a Common Subexpression Elimination (CSE) for TIR which introduces let-in bindings for dupl...</div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_a72900733e0d3510ae61a1c287c2ec125"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#a72900733e0d3510ae61a1c287c2ec125">tvm::relay::transform::PassContextNode</a></div><div class="ttdeci">tvm::transform::PassContextNode PassContextNode</div><div class="ttdef"><b>Definition:</b> transform.h:48</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a6fdd5910b00af823071dcdddd21cd2d3"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a6fdd5910b00af823071dcdddd21cd2d3">tvm::tir::transform::SkipAssert</a></div><div class="ttdeci">Pass SkipAssert()</div><div class="ttdoc">skip assert stmt. </div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index e08f1471b..0413d982e 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1715,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1752,7 +1752,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index a69b401f2..18106a946 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -6500,112 +6500,115 @@ reads/writes of the block.</p>
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectDoubleBuffer" title="tvm.tir.transform.InjectDoubleBuffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectDoubleBuffer</span></code></a>()</p></td>
<td><p>Inject double buffer statements.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectPrefetch" title="tvm.tir.transform.InjectPrefetch"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectPrefetch</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectPTXAsyncCopy" title="tvm.tir.transform.InjectPTXAsyncCopy"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectPTXAsyncCopy</span></code></a>()</p></td>
+<td><p>Rewrite global to shared memory copy on CUDA with asyncronous copy.</p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectPrefetch" title="tvm.tir.transform.InjectPrefetch"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectPrefetch</span></code></a>()</p></td>
<td><p>Inject prefetch instructions into stmt.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectRollingBuffer" title="tvm.tir.transform.InjectRollingBuffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectRollingBuffer</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectRollingBuffer" title="tvm.tir.transform.InjectRollingBuffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectRollingBuffer</span></code></a>()</p></td>
<td><p>Inject rolling buffer statements.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectSoftwarePipeline" title="tvm.tir.transform.InjectSoftwarePipeline"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectSoftwarePipeline</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectSoftwarePipeline" title="tvm.tir.transform.InjectSoftwarePipeline"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectSoftwarePipeline</span></code></a>()</p></td>
<td><p>Transform annotated loops into pipelined one that parallelize producers and consumers</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectVirtualThread" title="tvm.tir.transform.InjectVirtualThread"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectVirtualThread</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InjectVirtualThread" title="tvm.tir.transform.InjectVirtualThread"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InjectVirtualThread</span></code></a>()</p></td>
<td><p>Inject virtual thread loops.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.InstrumentBoundCheckers" title="tvm.tir.transform.InstrumentBoundCheckers"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InstrumentBoundCheckers</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.InstrumentBoundCheckers" title="tvm.tir.transform.InstrumentBoundCheckers"><code class="xref py py-obj docutils literal notranslate"><span class="pre">InstrumentBoundCheckers</span></code></a>()</p></td>
<td><p>Instruments bound checkers.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LegalizePackedCalls" title="tvm.tir.transform.LegalizePackedCalls"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LegalizePackedCalls</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LegalizePackedCalls" title="tvm.tir.transform.LegalizePackedCalls"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LegalizePackedCalls</span></code></a>()</p></td>
<td><p>Legalize packed calls to have its arguments wrapped in TVMValues</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LiftAttrScope" title="tvm.tir.transform.LiftAttrScope"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LiftAttrScope</span></code></a>(attr_key)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LiftAttrScope" title="tvm.tir.transform.LiftAttrScope"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LiftAttrScope</span></code></a>(attr_key)</p></td>
<td><p>Lift common attrs with attr_key to outer scope.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LoopPartition" title="tvm.tir.transform.LoopPartition"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LoopPartition</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LoopPartition" title="tvm.tir.transform.LoopPartition"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LoopPartition</span></code></a>()</p></td>
<td><p>Inject virtual thread loops.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerCrossThreadReduction" title="tvm.tir.transform.LowerCrossThreadReduction"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerCrossThreadReduction</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerCrossThreadReduction" title="tvm.tir.transform.LowerCrossThreadReduction"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerCrossThreadReduction</span></code></a>()</p></td>
<td><p>Lower cross-thread reduction from thread bindings to intrinsic function calls.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerCustomDatatypes" title="tvm.tir.transform.LowerCustomDatatypes"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerCustomDatatypes</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerCustomDatatypes" title="tvm.tir.transform.LowerCustomDatatypes"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerCustomDatatypes</span></code></a>()</p></td>
<td><p>Lower custom datatypes.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerDeviceStorageAccessInfo" title="tvm.tir.transform.LowerDeviceStorageAccessInfo"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerDeviceStorageAccessInfo</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerDeviceStorageAccessInfo" title="tvm.tir.transform.LowerDeviceStorageAccessInfo"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerDeviceStorageAccessInfo</span></code></a>()</p></td>
<td><p>Lower attached storage access information on device.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerInitBlock" title="tvm.tir.transform.LowerInitBlock"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerInitBlock</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerInitBlock" title="tvm.tir.transform.LowerInitBlock"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerInitBlock</span></code></a>()</p></td>
<td><p>Lower block init stmt into IfThenElse statements.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerIntrin" title="tvm.tir.transform.LowerIntrin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerIntrin</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerIntrin" title="tvm.tir.transform.LowerIntrin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerIntrin</span></code></a>()</p></td>
<td><p>Lower target specific intrinsic calls.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerMatchBuffer" title="tvm.tir.transform.LowerMatchBuffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerMatchBuffer</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerMatchBuffer" title="tvm.tir.transform.LowerMatchBuffer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerMatchBuffer</span></code></a>()</p></td>
<td><p>Remove match buffers inside the block.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerTVMBuiltin" title="tvm.tir.transform.LowerTVMBuiltin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerTVMBuiltin</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerTVMBuiltin" title="tvm.tir.transform.LowerTVMBuiltin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerTVMBuiltin</span></code></a>()</p></td>
<td><p>Lower tvm builtin intrinsics.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerThreadAllreduce" title="tvm.tir.transform.LowerThreadAllreduce"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerThreadAllreduce</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerThreadAllreduce" title="tvm.tir.transform.LowerThreadAllreduce"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerThreadAllreduce</span></code></a>()</p></td>
<td><p>Lower cross thread alleduce.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerWarpMemory" title="tvm.tir.transform.LowerWarpMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerWarpMemory</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerWarpMemory" title="tvm.tir.transform.LowerWarpMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerWarpMemory</span></code></a>()</p></td>
<td><p>Lower warp memory access to low-level device related function calls.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.MakePackedAPI" title="tvm.tir.transform.MakePackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakePackedAPI</span></code></a>([num_unpacked_params])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.MakePackedAPI" title="tvm.tir.transform.MakePackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakePackedAPI</span></code></a>([num_unpacked_params])</p></td>
<td><p>Transform the PrimFuncs in the module to a packed func API.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.MakeUnpackedAPI" title="tvm.tir.transform.MakeUnpackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakeUnpackedAPI</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.MakeUnpackedAPI" title="tvm.tir.transform.MakeUnpackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakeUnpackedAPI</span></code></a>()</p></td>
<td><p>Transform the PrimFuncs in the module to a C API compatible with internal calls.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.MergeDynamicSharedMemoryAllocations" title="tvm.tir.transform.MergeDynamicSharedMemoryAllocations"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MergeDynamicSharedMemoryAllocations</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.MergeDynamicSharedMemoryAllocations" title="tvm.tir.transform.MergeDynamicSharedMemoryAllocations"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MergeDynamicSharedMemoryAllocations</span></code></a>()</p></td>
<td><p>This pass merges multiple TIR-level dynamic shared memory allocations into one allocation.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.NarrowDataType" title="tvm.tir.transform.NarrowDataType"><code class="xref py py-obj docutils literal notranslate"><span class="pre">NarrowDataType</span></code></a>(target_bits)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.NarrowDataType" title="tvm.tir.transform.NarrowDataType"><code class="xref py py-obj docutils literal notranslate"><span class="pre">NarrowDataType</span></code></a>(target_bits)</p></td>
<td><p>Narrow down PrimExpr datatype in stmt to target_bits.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.PlanAndUpdateBufferAllocationLocation" title="tvm.tir.transform.PlanAndUpdateBufferAllocationLocation"><code class="xref py py-obj docutils literal notranslate"><span class="pre">PlanAndUpdateBufferAllocationLocation</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.PlanAndUpdateBufferAllocationLocation" title="tvm.tir.transform.PlanAndUpdateBufferAllocationLocation"><code class="xref py py-obj docutils literal notranslate"><span class="pre">PlanAndUpdateBufferAllocationLocation</span></code></a>()</p></td>
<td><p>Locate the buffer allocation to the exact position (usually is the lca of buffer access).</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveNoOp" title="tvm.tir.transform.RemoveNoOp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveNoOp</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RemoveNoOp" title="tvm.tir.transform.RemoveNoOp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RemoveNoOp</span></code></a>()</p></td>
<td><p>Remove No Op from the Stmt.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RenormalizeSplitPattern" title="tvm.tir.transform.RenormalizeSplitPattern"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RenormalizeSplitPattern</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RenormalizeSplitPattern" title="tvm.tir.transform.RenormalizeSplitPattern"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RenormalizeSplitPattern</span></code></a>()</p></td>
<td><p>Renormalize the split pattern from floordiv(floormod()) to floormod(floordiv())</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.RewriteUnsafeSelect" title="tvm.tir.transform.RewriteUnsafeSelect"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RewriteUnsafeSelect</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.RewriteUnsafeSelect" title="tvm.tir.transform.RewriteUnsafeSelect"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RewriteUnsafeSelect</span></code></a>()</p></td>
<td><p>Detect and rewrite unsafe select that contains memory access.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.Simplify" title="tvm.tir.transform.Simplify"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Simplify</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.Simplify" title="tvm.tir.transform.Simplify"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Simplify</span></code></a>()</p></td>
<td><p>Run arithmetic simplifications on the statements and expressions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.SkipAssert" title="tvm.tir.transform.SkipAssert"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SkipAssert</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.SkipAssert" title="tvm.tir.transform.SkipAssert"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SkipAssert</span></code></a>()</p></td>
<td><p>Skip assert stmt.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.SplitHostDevice" title="tvm.tir.transform.SplitHostDevice"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SplitHostDevice</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.SplitHostDevice" title="tvm.tir.transform.SplitHostDevice"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SplitHostDevice</span></code></a>()</p></td>
<td><p>Split the function into a host function and device functions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageFlatten" title="tvm.tir.transform.StorageFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageFlatten</span></code></a>(cache_line_size[, ...])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageFlatten" title="tvm.tir.transform.StorageFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageFlatten</span></code></a>(cache_line_size[, ...])</p></td>
<td><p>Flatten the multi-dimensional read/write to 1D.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageRewrite" title="tvm.tir.transform.StorageRewrite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageRewrite</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.StorageRewrite" title="tvm.tir.transform.StorageRewrite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">StorageRewrite</span></code></a>()</p></td>
<td><p>Rewrite storage allocation pattern.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.TextureFlatten" title="tvm.tir.transform.TextureFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TextureFlatten</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.TextureFlatten" title="tvm.tir.transform.TextureFlatten"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TextureFlatten</span></code></a>()</p></td>
<td><p>Flatten the multi-dimensional read/write to 2D.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.ThreadSync" title="tvm.tir.transform.ThreadSync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ThreadSync</span></code></a>(storage_scope)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.ThreadSync" title="tvm.tir.transform.ThreadSync"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ThreadSync</span></code></a>(storage_scope)</p></td>
<td><p>Insert sync between parallel read/write of shared buffers.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.UnifyThreadBinding" title="tvm.tir.transform.UnifyThreadBinding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnifyThreadBinding</span></code></a>()</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.UnifyThreadBinding" title="tvm.tir.transform.UnifyThreadBinding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnifyThreadBinding</span></code></a>()</p></td>
<td><p>Unify all the thread bindings for "blockIdx.x/y/z", "threadIdx.x/y/z", and "vthread.x/y/z".</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.UnrollLoop" title="tvm.tir.transform.UnrollLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnrollLoop</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.UnrollLoop" title="tvm.tir.transform.UnrollLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">UnrollLoop</span></code></a>()</p></td>
<td><p>Unroll the constant loop marked by unroll.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.VectorizeLoop" title="tvm.tir.transform.VectorizeLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VectorizeLoop</span></code></a>([enable_vectorize])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.VectorizeLoop" title="tvm.tir.transform.VectorizeLoop"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VectorizeLoop</span></code></a>([enable_vectorize])</p></td>
<td><p>Lower vectorization loops.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.VerifyMemory" title="tvm.tir.transform.VerifyMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VerifyMemory</span></code></a>()</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.VerifyMemory" title="tvm.tir.transform.VerifyMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">VerifyMemory</span></code></a>()</p></td>
<td><p>Verify if func contains illegal host side direct memory access.</p></td>
</tr>
</tbody>
@@ -7066,6 +7069,20 @@ supported with control with PassContext configs like below:</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.transform.InjectPTXAsyncCopy">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">InjectPTXAsyncCopy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.transform.InjectPTXAsyncCopy" title="Permalink to this definition">¶</a></dt>
+<dd><p>Rewrite global to shared memory copy on CUDA with asyncronous copy.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p><strong>fpass</strong> – The result pass</p>
+</dd>
+<dt class="field-even">Return type</dt>
+<dd class="field-even"><p><a class="reference internal" href="ir.html#tvm.transform.Pass" title="tvm.transform.Pass">tvm.transform.Pass</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<dl class="py function">
<dt class="sig sig-object py" id="tvm.tir.transform.InjectPrefetch">
<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">InjectPrefetch</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.transform.InjectPrefetch" title="Permalink to this definition">¶</a></dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index ba8eafe31..2a61594ba 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/0b46efa33/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 b8c708ee1..091ba9883 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/0b46efa33/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 b541ad9af..c30cc05db 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/0b46efa33/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 de8dc2eb5..c12f27e03 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/0b46efa33/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 a14fb94dc..c8ba1e531 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/0b46efa33/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 28e7bad46..6db2f49e0 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/0b46efa33/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 67297d0a0..8d110be9a 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/0b46efa33/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 17b689f9a..dbaa20aa2 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/0b46efa33/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 363160fa5..61e61bc29 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/0b46efa33/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 fe1572a9f..f16390132 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/0b46efa33/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 acd5942e1..86842f0e3 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/0b46efa33/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 d7ebd1cb1..2f6ec3e89 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/0b46efa33/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 ff9b1bdb7..f85b24cea 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/0b46efa33/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 6d2e15a1c..587c45ba1 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/0b46efa33/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 3ff4e1367..76688bc53 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/0b46efa33/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 98c6eb7f3..1d00e48af 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/0b46efa33/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 4c6fc0fe7..10ce84ded 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/0b46efa33/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 d2bca94ad..c0f1a14b5 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/0b46efa33/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 75c6f1e14..83672824f 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/0b46efa33/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 5ae2df745..60f83cab7 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/0b46efa33/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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 f3cef410d..574be2f9a 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/0b46efa33/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/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/0b46efa33/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/53d163c96/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
... 742 lines suppressed ...