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 2022/04/30 05:06:17 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@17b687e400e39d82f9ff92dadd66076cf429f91f)
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 592209179 deploying docs (apache/tvm@17b687e400e39d82f9ff92dadd66076cf429f91f)
592209179 is described below
commit 592209179d255674677e673fe6e83c0041690cff
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Apr 30 05:06:11 2022 +0000
deploying docs (apache/tvm@17b687e400e39d82f9ff92dadd66076cf429f91f)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_onnx.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 +
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../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 | 1400 ++------------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 421 +-----
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 65 +-
.../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 | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 107 +-
docs/how_to/compile_models/from_onnx.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 1 +
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 109 +-
docs/how_to/deploy_models/deploy_prequantized.html | 14 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
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 | 1400 ++------------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 421 +-----
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../reference/api/doxygen/arg__info_8h_source.html | 2 +-
docs/reference/api/doxygen/bytecode_8h_source.html | 2 +-
.../api/doxygen/c__runtime__api_8h_source.html | 2 +-
.../api/doxygen/data__layout_8h_source.html | 2 +-
.../api/doxygen/dataflow__pattern_8h_source.html | 2 +-
.../api/doxygen/detail_2broadcast_8h_source.html | 2 +-
.../api/doxygen/detail_2extern_8h_source.html | 2 +-
.../api/doxygen/device__api_8h_source.html | 2 +-
docs/reference/api/doxygen/einsum_8h_source.html | 2 +-
docs/reference/api/doxygen/elemwise_8h_source.html | 2 +-
docs/reference/api/doxygen/functions_a.html | 9 +-
docs/reference/api/doxygen/functions_func_t.html | 4 +-
docs/reference/api/doxygen/functions_i.html | 4 +-
docs/reference/api/doxygen/functions_m.html | 2 +-
docs/reference/api/doxygen/functions_s.html | 2 +-
docs/reference/api/doxygen/functions_t.html | 4 +-
docs/reference/api/doxygen/functions_vars_a.html | 3 +
.../api/doxygen/index__map_8h_source.html | 2 +-
.../api/doxygen/loop__state_8h_source.html | 2 +-
docs/reference/api/doxygen/measure_8h_source.html | 2 +-
.../api/doxygen/memory__manager_8h_source.html | 2 +-
docs/reference/api/doxygen/metadata_8h_source.html | 2 +-
docs/reference/api/doxygen/ndarray_8h_source.html | 2 +-
docs/reference/api/doxygen/nn_2bnn_8h_source.html | 2 +-
.../reference/api/doxygen/nn_2dense_8h_source.html | 2 +-
.../reference/api/doxygen/operation_8h_source.html | 2 +-
.../reference/api/doxygen/profiling_8h_source.html | 4 +-
.../api/doxygen/ravel__unravel_8h_source.html | 2 +-
.../doxygen/relay_2attrs_2transform_8h_source.html | 253 ++--
.../doxygen/relay_2expr__functor_8h_source.html | 2 +-
docs/reference/api/doxygen/search/all_11.js | 2 +-
docs/reference/api/doxygen/search/all_13.js | 8 +-
docs/reference/api/doxygen/search/all_14.js | 6 +-
docs/reference/api/doxygen/search/all_15.js | 4 +-
docs/reference/api/doxygen/search/all_16.js | 2 +-
docs/reference/api/doxygen/search/all_2.js | 1 +
docs/reference/api/doxygen/search/all_a.js | 2 +-
docs/reference/api/doxygen/search/all_e.js | 6 +-
docs/reference/api/doxygen/search/functions_10.js | 2 +-
docs/reference/api/doxygen/search/functions_12.js | 6 +-
docs/reference/api/doxygen/search/functions_14.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 2 +-
docs/reference/api/doxygen/search/functions_d.js | 4 +-
docs/reference/api/doxygen/search/variables_1.js | 1 +
.../api/doxygen/shape__tuple_8h_source.html | 2 +-
.../api/doxygen/strided__slice_8h_source.html | 2 +-
...structtvm_1_1relay_1_1ReshapeAttrs-members.html | 73 +-
.../structtvm_1_1relay_1_1ReshapeAttrs.html | 18 +-
...cttvm_1_1relay_1_1ReshapeAttrs__coll__graph.svg | 2 +-
...vm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg | 153 +--
docs/reference/api/doxygen/tensor_8h_source.html | 2 +-
.../api/doxygen/tensor__type_8h_source.html | 2 +-
docs/reference/api/doxygen/topi_2nn_8h_source.html | 4 +-
.../api/doxygen/topi_2transform_8h_source.html | 64 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/relay/index.html | 7 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 2 +-
docs/tutorial/autotvm_relay_x86.html | 173 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
172 files changed, 1548 insertions(+), 4477 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 7dc649b08..8f54e0bf1 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.zipeccbf69f-00ae-4432-87a2-b99dccae5fad from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0aba8440-1535-4da1-85fb-146681a0a832 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 cc520cc78..f13307dc8 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<08:33, 84.6kB/s]
0%| | 48.0k/41.5M [00:00<05:34, 130kB/s]
0%| | 96.0k/41.5M [00:00<04:10, 174kB/s]
0%| | 160k/41.5M [00:00<03:09, 229kB/s]
1%| | 328k/41.5M [00:01<01:36, 447kB/s]
1%|1 | 544k/41.5M [00:01<01:04, 666kB/s]
3%|2 | 1.06M/41.5M [00:01<00:31, 1.33MB/s]
5%|4 | 1.99M/41.5M [00:01<00:16, 2.45MB/s]
8%|8 | 3.46M/41.5M [00:01<00:09, 4.11MB/s]
12%|#1 | 4.93M/41.5M [00:02<00:07, 5.14MB/s]
15%|#5 | 6.41M/41.5M [00:02<00:06, 5.87MB/s]
19%|#8 | 7.88M/41.5M [00:02<00:05, 6.31MB/s]
23%|##2 | 9.34M/41.5M [00:02<00:05, 6.54MB/s]
26%|##6 | 10.8M/41.5M [00:02<00:04, 6.78MB/s]
30%|##9 | 12.3M/41.5M [00:03<00:04, 6.93MB/s]
33%|###3 | 13.8M/41.5M [00:03<00:04, 7.10MB/s]
37%|###6 | 15.2M/41.5M [00:03<00
:03, 8.35MB/s]
39%|###8 | 16.1M/41.5M [00:03<00:03, 8.38MB/s]
41%|#### | 17.0M/41.5M [00:03<00:03, 7.00MB/s]
44%|####3 | 18.1M/41.5M [00:03<00:03, 7.99MB/s]
46%|####5 | 19.0M/41.5M [00:03<00:02, 8.13MB/s]
48%|####7 | 19.8M/41.5M [00:04<00:03, 6.49MB/s]
51%|##### | 21.1M/41.5M [00:04<00:03, 6.29MB/s]
54%|#####4 | 22.6M/41.5M [00:04<00:03, 6.52MB/s]
58%|#####7 | 24.0M/41.5M [00:04<00:02, 6.63MB/s]
61%|######1 | 25.5M/41.5M [00:05<00:02, 6.67MB/s]
65%|######4 | 26.9M/41.5M [00:05<00:01, 8.04MB/s]
67%|######7 | 27.8M/41.5M [00:05<00:01, 8.03MB/s]
69%|######9 | 28.6M/41.5M [00:05<00:01, 6.78MB/s]
72%|#######1 | 29.9M/41.5M [00:05<00:01, 7.96MB/s]
74%|#######4 | 30.7M/41.5M [00:05<00:01, 8.08MB/s]
76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.58MB/s]
79%|#######9 | 32.8M/41.5M [00:05<00:01, 7.81MB/s]
81%|########1 | 33.6M/41.5M [00:06<00:01, 7.76MB/s]
83%|####
####3 | 34.5M/41.5M [00:06<00:01, 6.42MB/s]
86%|########6 | 35.8M/41.5M [00:06<00:00, 7.64MB/s]
89%|########9 | 36.9M/41.5M [00:06<00:00, 8.74MB/s]
91%|#########1| 37.9M/41.5M [00:06<00:00, 7.65MB/s]
93%|#########3| 38.7M/41.5M [00:06<00:00, 7.37MB/s]
96%|#########6| 39.9M/41.5M [00:06<00:00, 8.41MB/s]
98%|#########8| 40.7M/41.5M [00:07<00:00, 7.30MB/s]
100%|##########| 41.5M/41.5M [00:07<00:00, 6.10MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:03, 90.0kB/s]
0%| | 48.0k/41.5M [00:00<05:04, 143kB/s]
0%| | 96.0k/41.5M [00:00<03:38, 198kB/s]
0%| | 168k/41.5M [00:00<02:34, 280kB/s]
1%| | 304k/41.5M [00:00<01:37, 444kB/s]
1%|1 | 496k/41.5M [00:01<01:07, 637kB/s]
2%|1 | 728k/41.5M [00:01<00:53, 804kB/s]
2%|2 | 968k/41.5M [00:01<00:45, 935kB/s]
3%|2 | 1.20M/41.5M [00:01<00:39, 1.06MB/s]
4%|3 | 1.45M/41.5M [00:01<00:35, 1.19MB/s]
4%|4 | 1.72M/41.5M [00:02<00:32, 1.30MB/s]
5%|4 | 2.01M/41.5M [00:02<00:29, 1.40MB/s]
6%|5 | 2.30M/41.5M [00:02<00:28, 1.46MB/s]
6%|6 | 2.61M/41.5M [00:02<00:26, 1.54MB/s]
7%|7 | 2.93M/41.5M [00:02<00:25, 1.60MB/s]
8%|7 | 3.27M/41.5M [00:03<00:24, 1.67MB/s]
9%|8 | 3.62M/41.5M [00:03<00:22,
1.76MB/s]
10%|9 | 3.98M/41.5M [00:03<00:21, 1.86MB/s]
11%|# | 4.37M/41.5M [00:03<00:19, 1.96MB/s]
12%|#1 | 4.77M/41.5M [00:03<00:18, 2.07MB/s]
13%|#2 | 5.20M/41.5M [00:03<00:17, 2.18MB/s]
14%|#3 | 5.65M/41.5M [00:04<00:16, 2.27MB/s]
15%|#4 | 6.12M/41.5M [00:04<00:15, 2.36MB/s]
16%|#5 | 6.62M/41.5M [00:04<00:14, 2.46MB/s]
17%|#7 | 7.13M/41.5M [00:04<00:13, 2.57MB/s]
18%|#8 | 7.67M/41.5M [00:04<00:11, 3.14MB/s]
20%|#9 | 8.23M/41.5M [00:04<00:09, 3.51MB/s]
21%|## | 8.60M/41.5M [00:05<00:10, 3.22MB/s]
22%|##1 | 8.93M/41.5M [00:05<00:12, 2.77MB/s]
23%|##2 | 9.48M/41.5M [00:05<00:11, 2.88MB/s]
24%|##4 | 10.1M/41.5M [00:05<00:08, 3.66MB/s]
26%|##6 | 10.8M/41.5M [00:05<00:07, 4.39MB/s]
27%|##7 | 11.3M/41.5M [00:05<00:07, 4.01MB/s]
28%|##8 | 11.7M/41.5M [00:06<00:09, 3.39MB/s]
30%|##9
| 12.3M/41.5M [00:06<00:07, 4.02MB/s]
32%|###1 | 13.1M/41.5M [00:06<00:06, 4.84MB/s]
33%|###2 | 13.6M/41.5M [00:06<00:06, 4.26MB/s]
34%|###3 | 14.1M/41.5M [00:06<00:07, 3.61MB/s]
36%|###5 | 14.8M/41.5M [00:06<00:06, 4.53MB/s]
38%|###7 | 15.7M/41.5M [00:06<00:04, 5.43MB/s]
39%|###9 | 16.3M/41.5M [00:06<00:05, 4.81MB/s]
41%|#### | 16.8M/41.5M [00:07<00:06, 4.07MB/s]
43%|####2 | 17.8M/41.5M [00:07<00:05, 4.65MB/s]
45%|####5 | 18.8M/41.5M [00:07<00:04, 5.82MB/s]
47%|####6 | 19.4M/41.5M [00:07<00:04, 5.54MB/s]
48%|####8 | 20.0M/41.5M [00:07<00:04, 4.76MB/s]
50%|##### | 20.9M/41.5M [00:07<00:04, 5.03MB/s]
53%|#####3 | 22.1M/41.5M [00:08<00:03, 5.55MB/s]
56%|#####6 | 23.3M/41.5M [00:08<00:03, 5.99MB/s]
59%|#####9 | 24.6M/41.5M [00:08<00:02, 6.33MB/s]
62%|######2 | 25.9M/41.5M [00:08<00:02, 6.74MB/s]
66%|######5 | 27.3M/41.5M [00:08<00:02
, 7.23MB/s]
69%|######9 | 28.7M/41.5M [00:08<00:01, 8.52MB/s]
73%|#######2 | 30.2M/41.5M [00:09<00:01, 9.78MB/s]
75%|#######5 | 31.2M/41.5M [00:09<00:01, 8.89MB/s]
77%|#######7 | 32.1M/41.5M [00:09<00:01, 7.66MB/s]
80%|#######9 | 33.1M/41.5M [00:09<00:01, 8.32MB/s]
83%|########3 | 34.5M/41.5M [00:09<00:00, 9.73MB/s]
86%|########5 | 35.6M/41.5M [00:09<00:00, 8.78MB/s]
88%|########7 | 36.5M/41.5M [00:09<00:00, 7.45MB/s]
90%|######### | 37.5M/41.5M [00:10<00:00, 8.14MB/s]
94%|#########3| 38.9M/41.5M [00:10<00:00, 9.58MB/s]
96%|#########6| 39.9M/41.5M [00:10<00:00, 8.48MB/s]
98%|#########8| 40.8M/41.5M [00:10<00:00, 7.23MB/s]
100%|##########| 41.5M/41.5M [00:10<00:00, 4.13MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_onnx.rst.txt b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
index 35ccdb900..76561e025 100644
--- a/docs/_sources/how_to/compile_models/from_onnx.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
@@ -128,7 +128,7 @@ provides a static definition of the input size.
.. code-block:: none
- /workspace/python/tvm/relay/frontend/onnx.py:5595: UserWarning: Mismatched attribute type in ' : kernel_shape'
+ /workspace/python/tvm/relay/frontend/onnx.py:5596: UserWarning: Mismatched attribute type in ' : kernel_shape'
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
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 a1f092bf0..08df14e4e 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.918 seconds)
+ **Total running time of the script:** ( 21 minutes 58.059 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 483f8898d..d96db8326 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]
37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
83%|########3 | 37.2M/44.7M [00:00<00:00, 198MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 186MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
30%|##9 | 13.2M/44.7M [00:00<00:00, 138MB/s]
77%|#######6 | 34.2M/44.7M [00:00<00:00, 186MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 184MB/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 43d9b260b..791354984 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -370,6 +370,11 @@ Run the corresponding model on tensorflow
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 4.010 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 1dddb1509..a87e8f375 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
=================
-**05:15.477** total execution time for **how_to_compile_models** files:
+**26:18.836** total execution time for **how_to_compile_models** files:
-- **01:06.918**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **00:59.815**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:55.491**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:31.087**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:25.177**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.531**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:20.848**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:18.629**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:13.297**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.684**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **21:58.059**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:04.010**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:56.771**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:35.024**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.485**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.711**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:21.707**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:19.580**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.739**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.749**: :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 afce61c18..f7c0a9f1e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9735 15.9725 16.1387 15.8400 0.0920
+ 16.1572 16.1322 16.3299 16.0403 0.0952
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 33537b230..fa9422e3b 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]
6%|5 | 9.83M/170M [00:00<00:01, 103MB/s]
12%|#1 | 19.7M/170M [00:00<00:01, 92.6MB/s]
17%|#7 | 28.9M/170M [00:00<00:01, 94.6MB/s]
23%|##2 | 38.8M/170M [00:00<00:01, 97.8MB/s]
28%|##8 | 48.1M/170M [00:00<00:01, 86.4MB/s]
33%|###3 | 56.6M/170M [00:00<00:01, 84.6MB/s]
39%|###8 | 65.8M/170M [00:00<00:01, 88.1MB/s]
44%|####4 | 74.8M/170M [00:00<00:01, 90.0MB/s]
49%|####9 | 83.5M/170M [00:00<00:01, 83.4MB/s]
55%|#####5 | 93.8M/170M [00:01<00:00, 89.8MB/s]
60%|###### | 103M/170M [00:01<00:00, 90.1MB/s]
65%|######5 | 111M/170M [00:01<00:00, 84.9MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 90.6MB/s]
77%|#######6 | 131M/170M [00:01<00:00, 93.1MB/s]
83%|########3 | 142M/170M [00:01<00:00, 99.3MB/s]
89%|########9 | 152M/170M [00:01<00:00, 101MB/s]
95%|#########5| 162M/170M [00:01<00:00, 90.9MB/s]
100%|##########| 170M/170M [00:01<00:00, 89.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%| | 1.25M/170M [00:00<00:13, 12.7MB/s]
1%|1 | 2.46M/170M [00:00<00:15, 11.4MB/s]
2%|2 | 3.88M/170M [00:00<00:13, 12.5MB/s]
4%|3 | 6.38M/170M [00:00<00:11, 15.0MB/s]
5%|4 | 8.01M/170M [00:00<00:10, 15.5MB/s]
6%|5 | 9.77M/170M [00:00<00:10, 16.4MB/s]
7%|7 | 12.6M/170M [00:00<00:08, 20.3MB/s]
9%|8 | 14.6M/170M [00:00<00:09, 17.4MB/s]
10%|9 | 16.3M/170M [00:01<00:10, 14.6MB/s]
11%|# | 18.0M/170M [00:01<00:11, 14.1MB/s]
11%|#1 | 19.5M/170M [00:01<00:11, 13.8MB/s]
12%|#2 | 20.8M/170M [00:01<00:12, 13.0MB/s]
13%|#3 | 22.1M/170M [00:01<00:11, 12.9MB/s]
14%|#3 | 23.4M/170M [00:01<00:11, 12.9MB/s]
15%|#5 | 25.7M/170M [00:01<00:09, 15.8MB/s]
16%|#6 | 27.8M/170M [00:01<00:09, 16.5MB/s]
17%|#7 | 29.4M/170M [00:02<00:09, 15.3MB/
s]
18%|#8 | 31.1M/170M [00:02<00:09, 15.8MB/s]
19%|#9 | 32.6M/170M [00:02<00:10, 14.0MB/s]
20%|## | 34.4M/170M [00:02<00:09, 14.8MB/s]
22%|##2 | 37.4M/170M [00:02<00:07, 19.4MB/s]
23%|##3 | 39.7M/170M [00:02<00:06, 20.5MB/s]
25%|##4 | 41.9M/170M [00:02<00:06, 20.4MB/s]
26%|##5 | 43.9M/170M [00:02<00:06, 20.1MB/s]
27%|##7 | 45.9M/170M [00:02<00:06, 20.3MB/s]
28%|##8 | 47.9M/170M [00:03<00:07, 17.3MB/s]
29%|##9 | 49.6M/170M [00:03<00:07, 17.4MB/s]
30%|### | 51.3M/170M [00:03<00:07, 16.1MB/s]
31%|###1 | 52.9M/170M [00:03<00:07, 15.4MB/s]
32%|###2 | 54.4M/170M [00:03<00:07, 15.3MB/s]
33%|###3 | 56.4M/170M [00:03<00:07, 16.5MB/s]
34%|###4 | 58.0M/170M [00:03<00:07, 16.0MB/s]
35%|###5 | 59.5M/170M [00:03<00:08, 13.0MB/s]
36%|###6 | 61.8M/170M [00:04<00:07, 15.6MB/s]
37%|###7 | 63.4M/170M [00:04<00:
07, 15.4MB/s]
38%|###8 | 65.0M/170M [00:04<00:07, 14.8MB/s]
40%|###9 | 67.5M/170M [00:04<00:06, 17.7MB/s]
42%|####1 | 70.7M/170M [00:04<00:04, 22.0MB/s]
43%|####2 | 72.9M/170M [00:04<00:04, 20.9MB/s]
44%|####4 | 75.0M/170M [00:04<00:04, 20.5MB/s]
46%|####6 | 78.3M/170M [00:04<00:03, 24.0MB/s]
47%|####7 | 80.6M/170M [00:05<00:04, 20.3MB/s]
49%|####8 | 82.7M/170M [00:05<00:06, 15.1MB/s]
50%|####9 | 84.4M/170M [00:05<00:06, 14.5MB/s]
51%|#####1 | 86.9M/170M [00:05<00:05, 16.8MB/s]
52%|#####2 | 88.7M/170M [00:05<00:05, 15.9MB/s]
53%|#####3 | 90.5M/170M [00:05<00:05, 16.6MB/s]
54%|#####4 | 92.2M/170M [00:05<00:04, 16.9MB/s]
55%|#####5 | 93.9M/170M [00:05<00:05, 15.8MB/s]
56%|#####6 | 95.7M/170M [00:06<00:04, 16.3MB/s]
57%|#####7 | 97.3M/170M [00:06<00:04, 15.4MB/s]
58%|#####8 | 98.8M/170M [00:06<00:04, 15.4MB/s]
59%|#####9 | 100M/170M
[00:06<00:04, 14.9MB/s]
60%|###### | 103M/170M [00:06<00:03, 17.8MB/s]
62%|######1 | 104M/170M [00:06<00:04, 13.9MB/s]
62%|######2 | 106M/170M [00:06<00:04, 13.8MB/s]
64%|######3 | 108M/170M [00:06<00:04, 14.7MB/s]
64%|######4 | 109M/170M [00:07<00:04, 14.0MB/s]
65%|######5 | 111M/170M [00:07<00:04, 14.1MB/s]
66%|######6 | 112M/170M [00:07<00:04, 14.3MB/s]
67%|######7 | 114M/170M [00:07<00:03, 16.5MB/s]
69%|######8 | 117M/170M [00:07<00:02, 19.7MB/s]
71%|####### | 120M/170M [00:07<00:02, 21.8MB/s]
72%|#######2 | 123M/170M [00:07<00:01, 25.1MB/s]
74%|#######3 | 126M/170M [00:07<00:02, 22.1MB/s]
75%|#######5 | 128M/170M [00:08<00:02, 19.8MB/s]
76%|#######6 | 130M/170M [00:08<00:02, 18.7MB/s]
77%|#######7 | 132M/170M [00:08<00:02, 18.7MB/s]
79%|#######8 | 134M/170M [00:08<00:01, 19.1MB/s]
80%|######## | 136M/170M [00:08<00:01, 20.5MB/s]
81%|########1 | 138M/170M [00:08
<00:01, 18.1MB/s]
82%|########2 | 140M/170M [00:08<00:02, 14.4MB/s]
83%|########3 | 141M/170M [00:08<00:01, 15.3MB/s]
84%|########4 | 143M/170M [00:09<00:02, 14.0MB/s]
85%|########5 | 144M/170M [00:09<00:01, 14.2MB/s]
86%|########6 | 146M/170M [00:09<00:01, 15.6MB/s]
87%|########7 | 148M/170M [00:09<00:01, 15.5MB/s]
88%|########8 | 150M/170M [00:09<00:01, 14.9MB/s]
89%|########9 | 151M/170M [00:09<00:01, 16.3MB/s]
90%|######### | 153M/170M [00:09<00:01, 17.0MB/s]
91%|#########1| 155M/170M [00:09<00:00, 16.9MB/s]
93%|#########2| 157M/170M [00:09<00:00, 18.1MB/s]
94%|#########3| 159M/170M [00:10<00:00, 16.8MB/s]
95%|#########4| 161M/170M [00:10<00:00, 16.6MB/s]
96%|#########5| 163M/170M [00:10<00:00, 18.6MB/s]
97%|#########7| 165M/170M [00:10<00:00, 19.0MB/s]
98%|#########8| 167M/170M [00:10<00:00, 17.2MB/s]
99%|#########9| 168M/170M [00:10<00:00, 16.4MB/s]
100%|##########| 170M/170M [00:10<00:00,
16.7MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 4.101 seconds)
+ **Total running time of the script:** ( 3 minutes 20.108 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 2dbff2f83..b7a1b9899 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
12%|#2 | 1.69M/13.6M [00:00<00:00, 17.2MB/s]
25%|##4 | 3.33M/13.6M [00:00<00:00, 11.5MB/s]
39%|###8 | 5.27M/13.6M [00:00<00:00, 14.1MB/s]
52%|#####1 | 6.99M/13.6M [00:00<00:00, 15.1MB/s]
63%|######2 | 8.52M/13.6M [00:00<00:00, 15.4MB/s]
74%|#######4 | 10.0M/13.6M [00:00<00:00, 15.3MB/s]
85%|########5 | 11.5M/13.6M [00:01<00:00, 9.41MB/s]
94%|#########3| 12.7M/13.6M [00:01<00:00, 9.57MB/s]
100%|##########| 13.6M/13.6M [00:01<00:00, 11.8MB/s]
@@ -344,7 +344,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3897 90.2330 92.7423 89.9795 0.3807
+ 90.7954 90.6947 100.4582 90.1987 1.0365
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.622 seconds)
+ **Total running time of the script:** ( 1 minutes 7.781 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 cd0bd55dc..64427e60e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.5120 119.4274 121.5809 118.4995 0.4991
+ 120.0622 119.9243 126.6465 119.0002 0.9385
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 56.016 seconds)
+ **Total running time of the script:** ( 2 minutes 0.709 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 fb8f2f7c7..68ad8f26d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.968 seconds)
+ **Total running time of the script:** ( 1 minutes 12.520 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 f7230dd04..0bdf462c0 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3469/132723 [00:00<00:03, 34420.94KB/s]
7%|6 | 8811/132723 [00:00<00:02, 45556.38KB/s]
13%|#2 | 16679/132723 [00:00<00:01, 60652.65KB/s]
19%|#8 | 24681/132723 [00:00<00:01, 68288.44KB/s]
25%|##4 | 32729/132723 [00:00<00:01, 72675.72KB/s]
31%|### | 40742/132723 [00:00<00:01, 75206.24KB/s]
37%|###6 | 48808/132723 [00:00<00:01, 76987.35KB/s]
43%|####2 | 56841/132723 [00:00<00:00, 78048.74KB/s]
49%|####8 | 64647/132723 [00:00<00:00, 77763.41KB/s]
55%|#####4 | 72448/132723 [00:01<00:00, 77835.59KB/s]
60%|###### | 80248/132723 [00:01<00:00, 77876.25KB/s]
66%|######6 | 88037/132723 [00:01<00:00, 77740.81KB/s]
72%|#######2 | 95812/132723 [00:01<00:00, 77595.04KB/s]
78%|#######8 | 103608/132723 [00:01<00:00, 77701.18KB/s]
84%|########3 | 111379/132723 [00:01<00:00, 77457.54KB/s]
90%|########9
| 119126/132723 [00:01<00:00, 77329.54KB/s]
96%|#########5| 126864/132723 [00:01<00:00, 77340.81KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74499.40KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3930/132723 [00:00<00:03, 39296.38KB/s]
8%|7 | 10091/132723 [00:00<00:02, 52419.00KB/s]
14%|#3 | 18506/132723 [00:00<00:01, 66905.93KB/s]
20%|## | 26876/132723 [00:00<00:01, 73533.10KB/s]
27%|##6 | 35391/132723 [00:00<00:01, 77719.85KB/s]
33%|###3 | 43988/132723 [00:00<00:01, 80518.98KB/s]
39%|###9 | 52377/132723 [00:00<00:00, 81619.58KB/s]
46%|####5 | 60864/132723 [00:00<00:00, 82646.66KB/s]
52%|#####2 | 69289/132723 [00:00<00:00, 83144.51KB/s]
59%|#####8 | 77776/132723 [00:01<00:00, 83670.53KB/s]
65%|######5 | 86293/132723 [00:01<00:00, 84126.95KB/s]
71%|#######1 | 94827/132723 [00:01<00:00, 84492.65KB/s]
78%|#######7 | 103302/132723 [00:01<00:00, 84568.55KB/s]
84%|########4 | 111759/132723 [00:01<00:00, 84558.54KB/s]
91%|######### | 120215/132723 [00:01<00:00, 79103.22KB/s]
97%|########
#7| 128749/132723 [00:01<00:00, 80890.78KB/s]
100%|##########| 132723/132723 [00:01<00:00, 79396.11KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 22.450 seconds)
+ **Total running time of the script:** ( 2 minutes 25.953 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 6d9425c0c..342e2907d 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**10:27.704** total execution time for **how_to_deploy_models** files:
+**10:59.591** total execution time for **how_to_deploy_models** files:
-- **03:04.101**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:22.450**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:56.016**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:10.968**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:04.622**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:27.896**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.451**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:20.108**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:25.953**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **02:00.709**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:12.520**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:07.781**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.552**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.757**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.211**: :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 34bc87b99..6e011036b 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -423,7 +423,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb1c37f6d-754c-4b34-aca9-d8ed44396371 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip754d81c8-ba1a-4c89-a8dd-418c23c8656b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -525,7 +525,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
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 9968ab331..2ac9ffb95 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
=================
-**00:37.957** total execution time for **how_to_extend_tvm** files:
+**00:38.848** total execution time for **how_to_extend_tvm** files:
-- **00:34.493**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.229**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.040**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.194**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:35.221**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.297**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.107**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.222**: :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 e6af86a44..6d9ac023d 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: 5847us [5847us] (44.94%; 44.94%)
- FoldScaleAxis: 7163us [2us] (55.06%; 55.06%)
- FoldConstant: 7161us [1488us] (55.04%; 99.97%)
- InferType: 5673us [5673us] (43.61%; 79.22%)
+ InferType: 6268us [6268us] (45.79%; 45.79%)
+ FoldScaleAxis: 7421us [2us] (54.21%; 54.21%)
+ FoldConstant: 7418us [1525us] (54.19%; 99.97%)
+ InferType: 5893us [5893us] (43.05%; 79.44%)
@@ -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: 5683us [5683us] (44.20%; 44.20%)
- FoldScaleAxis: 7173us [2us] (55.80%; 55.80%)
- FoldConstant: 7171us [1510us] (55.78%; 99.98%)
- InferType: 5661us [5661us] (44.04%; 78.94%)
+ InferType: 6026us [6026us] (44.82%; 44.82%)
+ FoldScaleAxis: 7419us [2us] (55.18%; 55.18%)
+ FoldConstant: 7417us [1540us] (55.17%; 99.98%)
+ InferType: 5877us [5877us] (43.71%; 79.23%)
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 0b2fcf796..75af66113 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: 54.134968 ms
+ Convolution: 37.018735 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 ae4f18a19..898529b41 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: 7.091136 ms
+ conv2d with tensor core: 7.421299 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 bd22967c6..71fef393e 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: 0.018117
- Baseline: 3.197863
+ Numpy running time: 0.018893
+ Baseline: 3.444817
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.302272
+ Opt1: 0.297772
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.341488
+ Opt2: 0.333955
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120279
+ Opt3: 0.117961
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111055
+ Opt4: 0.110713
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111010
+ Opt5: 0.111482
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144610
+ Opt6: 0.145078
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 785453133..c5b8898da 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
=================
-**00:34.438** total execution time for **how_to_optimize_operators** files:
+**00:35.304** total execution time for **how_to_optimize_operators** files:
-- **00:31.826**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.414**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.197**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.535**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.493**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.276**: :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 1c6530c20..ed6d87d1c 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
=================
-**04:55.482** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:20.906**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:19.998**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.306**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.326**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.590**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.355**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:04.820** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:28.498**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:21.539**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:41.053**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.092**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.124**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.513**: :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 2970f2f48..5bcb4e9a1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -222,689 +222,70 @@ 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" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*196)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 9)*7)) + (floormod(blockIdx.x, 7)*7 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 100), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[(threadIdx.x_2*6)] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 5)]
+ }
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ for (xx.outer.inner: int32, 0, 7) {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 29)]))
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
@@ -956,7 +337,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.260 ms
+ Execution time of this operator: 0.268 ms
@@ -1002,35 +383,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=64)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_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=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_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=7)
+ 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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1047,16 +428,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
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=64)
+ 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)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ 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)
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", 1024)
+ 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, "unroll_explicit", True)
CUDA source code:
@@ -1074,10 +455,10 @@ 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__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[576];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1085,599 +466,52 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] [...]
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : [...]
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 100) {
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[(((int)threadIdx.x) * 6)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 1)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 2)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 3)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 4)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 5)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3))]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 29)]));
+ }
+ }
+ }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
- compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
@@ -1735,7 +569,7 @@ 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 20.906 seconds)
+ **Total running time of the script:** ( 2 minutes 28.498 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 45ee3108d..7e7a6238c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -614,7 +614,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7771 9.7825 9.8053 9.7436 0.0255
+ 9.8268 9.8703 9.8707 9.7394 0.0618
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 e52f75d20..9e4e34f85 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -633,7 +633,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 765.3085 765.3539 767.8644 762.7072 2.1057
+ 769.2630 769.7279 772.1471 765.9140 2.5658
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.998 seconds)
+ **Total running time of the script:** ( 1 minutes 21.539 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 81bada5c7..6dc577db0 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
@@ -362,407 +362,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = (nb_j.inner*16)
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- compute_5[(cse_var_2 + 64)] = 0f32
- compute_5[(cse_var_2 + 65)] = 0f32
- compute_5[(cse_var_2 + 66)] = 0f32
- compute_5[(cse_var_2 + 67)] = 0f32
- compute_5[(cse_var_2 + 68)] = 0f32
- compute_5[(cse_var_2 + 69)] = 0f32
- compute_5[(cse_var_2 + 70)] = 0f32
- compute_5[(cse_var_2 + 71)] = 0f32
- compute_5[(cse_var_2 + 72)] = 0f32
- compute_5[(cse_var_2 + 73)] = 0f32
- compute_5[(cse_var_2 + 74)] = 0f32
- compute_5[(cse_var_2 + 75)] = 0f32
- compute_5[(cse_var_2 + 76)] = 0f32
- compute_5[(cse_var_2 + 77)] = 0f32
- compute_5[(cse_var_2 + 78)] = 0f32
- compute_5[(cse_var_2 + 79)] = 0f32
- compute_5[(cse_var_2 + 96)] = 0f32
- compute_5[(cse_var_2 + 97)] = 0f32
- compute_5[(cse_var_2 + 98)] = 0f32
- compute_5[(cse_var_2 + 99)] = 0f32
- compute_5[(cse_var_2 + 100)] = 0f32
- compute_5[(cse_var_2 + 101)] = 0f32
- compute_5[(cse_var_2 + 102)] = 0f32
- compute_5[(cse_var_2 + 103)] = 0f32
- compute_5[(cse_var_2 + 104)] = 0f32
- compute_5[(cse_var_2 + 105)] = 0f32
- compute_5[(cse_var_2 + 106)] = 0f32
- compute_5[(cse_var_2 + 107)] = 0f32
- compute_5[(cse_var_2 + 108)] = 0f32
- compute_5[(cse_var_2 + 109)] = 0f32
- compute_5[(cse_var_2 + 110)] = 0f32
- compute_5[(cse_var_2 + 111)] = 0f32
- compute_5[(cse_var_2 + 128)] = 0f32
- compute_5[(cse_var_2 + 129)] = 0f32
- compute_5[(cse_var_2 + 130)] = 0f32
- compute_5[(cse_var_2 + 131)] = 0f32
- compute_5[(cse_var_2 + 132)] = 0f32
- compute_5[(cse_var_2 + 133)] = 0f32
- compute_5[(cse_var_2 + 134)] = 0f32
- compute_5[(cse_var_2 + 135)] = 0f32
- compute_5[(cse_var_2 + 136)] = 0f32
- compute_5[(cse_var_2 + 137)] = 0f32
- compute_5[(cse_var_2 + 138)] = 0f32
- compute_5[(cse_var_2 + 139)] = 0f32
- compute_5[(cse_var_2 + 140)] = 0f32
- compute_5[(cse_var_2 + 141)] = 0f32
- compute_5[(cse_var_2 + 142)] = 0f32
- compute_5[(cse_var_2 + 143)] = 0f32
- compute_5[(cse_var_2 + 160)] = 0f32
- compute_5[(cse_var_2 + 161)] = 0f32
- compute_5[(cse_var_2 + 162)] = 0f32
- compute_5[(cse_var_2 + 163)] = 0f32
- compute_5[(cse_var_2 + 164)] = 0f32
- compute_5[(cse_var_2 + 165)] = 0f32
- compute_5[(cse_var_2 + 166)] = 0f32
- compute_5[(cse_var_2 + 167)] = 0f32
- compute_5[(cse_var_2 + 168)] = 0f32
- compute_5[(cse_var_2 + 169)] = 0f32
- compute_5[(cse_var_2 + 170)] = 0f32
- compute_5[(cse_var_2 + 171)] = 0f32
- compute_5[(cse_var_2 + 172)] = 0f32
- compute_5[(cse_var_2 + 173)] = 0f32
- compute_5[(cse_var_2 + 174)] = 0f32
- compute_5[(cse_var_2 + 175)] = 0f32
- compute_5[(cse_var_2 + 192)] = 0f32
- compute_5[(cse_var_2 + 193)] = 0f32
- compute_5[(cse_var_2 + 194)] = 0f32
- compute_5[(cse_var_2 + 195)] = 0f32
- compute_5[(cse_var_2 + 196)] = 0f32
- compute_5[(cse_var_2 + 197)] = 0f32
- compute_5[(cse_var_2 + 198)] = 0f32
- compute_5[(cse_var_2 + 199)] = 0f32
- compute_5[(cse_var_2 + 200)] = 0f32
- compute_5[(cse_var_2 + 201)] = 0f32
- compute_5[(cse_var_2 + 202)] = 0f32
- compute_5[(cse_var_2 + 203)] = 0f32
- compute_5[(cse_var_2 + 204)] = 0f32
- compute_5[(cse_var_2 + 205)] = 0f32
- compute_5[(cse_var_2 + 206)] = 0f32
- compute_5[(cse_var_2 + 207)] = 0f32
- compute_5[(cse_var_2 + 224)] = 0f32
- compute_5[(cse_var_2 + 225)] = 0f32
- compute_5[(cse_var_2 + 226)] = 0f32
- compute_5[(cse_var_2 + 227)] = 0f32
- compute_5[(cse_var_2 + 228)] = 0f32
- compute_5[(cse_var_2 + 229)] = 0f32
- compute_5[(cse_var_2 + 230)] = 0f32
- compute_5[(cse_var_2 + 231)] = 0f32
- compute_5[(cse_var_2 + 232)] = 0f32
- compute_5[(cse_var_2 + 233)] = 0f32
- compute_5[(cse_var_2 + 234)] = 0f32
- compute_5[(cse_var_2 + 235)] = 0f32
- compute_5[(cse_var_2 + 236)] = 0f32
- compute_5[(cse_var_2 + 237)] = 0f32
- compute_5[(cse_var_2 + 238)] = 0f32
- compute_5[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_131: int32 = (cse_var_2 + 143)
- let cse_var_130: int32 = (cse_var_2 + 15)
- let cse_var_129: int32 = (cse_var_2 + 160)
- let cse_var_128: int32 = (cse_var_2 + 161)
- let cse_var_127: int32 = (cse_var_2 + 162)
- let cse_var_126: int32 = (cse_var_2 + 163)
- let cse_var_125: int32 = (cse_var_2 + 164)
- let cse_var_124: int32 = (cse_var_2 + 165)
- let cse_var_123: int32 = (cse_var_2 + 166)
- let cse_var_122: int32 = (cse_var_2 + 167)
- let cse_var_121: int32 = (cse_var_2 + 168)
- let cse_var_120: int32 = (cse_var_2 + 169)
- let cse_var_119: int32 = (cse_var_2 + 170)
- let cse_var_118: int32 = (cse_var_2 + 171)
- let cse_var_117: int32 = (cse_var_2 + 172)
- let cse_var_116: int32 = (cse_var_2 + 1)
- let cse_var_115: int32 = (cse_var_2 + 174)
- let cse_var_114: int32 = (cse_var_2 + 175)
- let cse_var_113: int32 = (cse_var_2 + 192)
- let cse_var_112: int32 = (cse_var_2 + 193)
- let cse_var_111: int32 = (cse_var_2 + 194)
- let cse_var_110: int32 = (cse_var_2 + 195)
- let cse_var_109: int32 = (cse_var_2 + 196)
- let cse_var_108: int32 = (cse_var_2 + 197)
- let cse_var_107: int32 = (cse_var_2 + 198)
- let cse_var_106: int32 = (cse_var_2 + 199)
- let cse_var_105: int32 = (cse_var_2 + 2)
- let cse_var_104: int32 = (cse_var_2 + 200)
- let cse_var_103: int32 = (cse_var_2 + 201)
- let cse_var_102: int32 = (cse_var_2 + 202)
- let cse_var_101: int32 = (cse_var_2 + 203)
- let cse_var_100: int32 = (cse_var_2 + 173)
- let cse_var_99: int32 = (cse_var_2 + 10)
- let cse_var_98: int32 = (cse_var_2 + 100)
- let cse_var_97: int32 = (cse_var_2 + 101)
- let cse_var_96: int32 = (cse_var_2 + 102)
- let cse_var_95: int32 = (cse_var_2 + 103)
- let cse_var_94: int32 = (cse_var_2 + 104)
- let cse_var_93: int32 = (cse_var_2 + 105)
- let cse_var_92: int32 = (cse_var_2 + 106)
- let cse_var_91: int32 = (cse_var_2 + 107)
- let cse_var_90: int32 = (cse_var_2 + 108)
- let cse_var_89: int32 = (cse_var_2 + 109)
- let cse_var_88: int32 = (cse_var_2 + 11)
- let cse_var_87: int32 = (cse_var_2 + 110)
- let cse_var_86: int32 = (cse_var_2 + 111)
- let cse_var_85: int32 = (cse_var_2 + 12)
- let cse_var_84: int32 = (cse_var_2 + 142)
- let cse_var_83: int32 = (cse_var_2 + 129)
- let cse_var_82: int32 = (cse_var_2 + 13)
- let cse_var_81: int32 = (cse_var_2 + 130)
- let cse_var_80: int32 = (cse_var_2 + 131)
- let cse_var_79: int32 = (cse_var_2 + 132)
- let cse_var_78: int32 = (cse_var_2 + 133)
- let cse_var_77: int32 = (cse_var_2 + 134)
- let cse_var_76: int32 = (cse_var_2 + 135)
- let cse_var_75: int32 = (cse_var_2 + 136)
- let cse_var_74: int32 = (cse_var_2 + 137)
- let cse_var_73: int32 = (cse_var_2 + 138)
- let cse_var_72: int32 = (cse_var_2 + 139)
- let cse_var_71: int32 = (cse_var_2 + 14)
- let cse_var_70: int32 = (cse_var_2 + 140)
- let cse_var_69: int32 = (cse_var_2 + 141)
- let cse_var_68: int32 = (cse_var_2 + 128)
- let cse_var_67: int32 = (cse_var_2 + 43)
- let cse_var_66: int32 = (cse_var_2 + 44)
- let cse_var_65: int32 = (cse_var_2 + 45)
- let cse_var_64: int32 = (cse_var_2 + 46)
- let cse_var_63: int32 = (cse_var_2 + 47)
- let cse_var_62: int32 = (cse_var_2 + 5)
- let cse_var_61: int32 = (cse_var_2 + 6)
- let cse_var_60: int32 = (cse_var_2 + 64)
- let cse_var_59: int32 = (cse_var_2 + 65)
- let cse_var_58: int32 = (cse_var_2 + 66)
- let cse_var_57: int32 = (cse_var_2 + 67)
- let cse_var_56: int32 = (cse_var_2 + 68)
- let cse_var_55: int32 = (cse_var_2 + 69)
- let cse_var_54: int32 = (cse_var_2 + 7)
- let cse_var_53: int32 = (cse_var_2 + 70)
- let cse_var_52: int32 = (cse_var_2 + 42)
- let cse_var_51: int32 = (cse_var_2 + 72)
- let cse_var_50: int32 = (cse_var_2 + 73)
- let cse_var_49: int32 = (cse_var_2 + 74)
- let cse_var_48: int32 = (cse_var_2 + 75)
- let cse_var_47: int32 = (cse_var_2 + 76)
- let cse_var_46: int32 = (cse_var_2 + 77)
- let cse_var_45: int32 = (cse_var_2 + 78)
- let cse_var_44: int32 = (cse_var_2 + 79)
- let cse_var_43: int32 = (cse_var_2 + 8)
- let cse_var_42: int32 = (cse_var_2 + 9)
- let cse_var_41: int32 = (cse_var_2 + 96)
- let cse_var_40: int32 = (cse_var_2 + 97)
- let cse_var_39: int32 = (cse_var_2 + 98)
- let cse_var_38: int32 = (cse_var_2 + 99)
- let cse_var_37: int32 = (elem_idx*16)
- let cse_var_36: int32 = (cse_var_2 + 71)
- let cse_var_35: int32 = (cse_var_2 + 204)
- let cse_var_34: int32 = (cse_var_2 + 206)
- let cse_var_33: int32 = (cse_var_2 + 207)
- let cse_var_32: int32 = (cse_var_2 + 224)
- let cse_var_31: int32 = (cse_var_2 + 225)
- let cse_var_30: int32 = (cse_var_2 + 226)
- let cse_var_29: int32 = (cse_var_2 + 227)
- let cse_var_28: int32 = (cse_var_2 + 228)
- let cse_var_27: int32 = (cse_var_2 + 229)
- let cse_var_26: int32 = (cse_var_2 + 230)
- let cse_var_25: int32 = (cse_var_2 + 231)
- let cse_var_24: int32 = (cse_var_2 + 232)
- let cse_var_23: int32 = (cse_var_2 + 233)
- let cse_var_22: int32 = (cse_var_2 + 234)
- let cse_var_21: int32 = (cse_var_2 + 235)
- let cse_var_20: int32 = (cse_var_2 + 236)
- let cse_var_19: int32 = (cse_var_2 + 205)
- let cse_var_18: int32 = (cse_var_2 + 40)
- let cse_var_17: int32 = (cse_var_2 + 4)
- let cse_var_16: int32 = (cse_var_2 + 39)
- let cse_var_15: int32 = (cse_var_2 + 38)
- let cse_var_14: int32 = (cse_var_2 + 37)
- let cse_var_13: int32 = (cse_var_2 + 36)
- let cse_var_12: int32 = (cse_var_2 + 35)
- let cse_var_11: int32 = (cse_var_2 + 34)
- let cse_var_10: int32 = (cse_var_2 + 33)
- let cse_var_9: int32 = (cse_var_2 + 32)
- let cse_var_8: int32 = (cse_var_2 + 3)
- let cse_var_7: int32 = (cse_var_2 + 239)
- let cse_var_6: int32 = (cse_var_2 + 238)
- let cse_var_5: int32 = (cse_var_2 + 41)
- let cse_var_4: int32 = (cse_var_2 + 237)
- let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ 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, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_132, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -816,7 +441,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.721 ms
+ Execution time of this operator: 1.511 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 464f14fc4..ac5e396ed 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
=================
-**00:44.648** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.040** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.755**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.235**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.218**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:44.112**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.242**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.234**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.225**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.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 53bc35489..2b3ed27c1 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 43.38/43.38 result: MeasureResult(costs=(0.005336062894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.565807819366455, timestamp=1651281447.9343586) [('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: 0.00/43.38 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.32/42.32 result: MeasureResult(costs=(0.005470518157894737,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5970234870910645, timestamp=1651292876.677573) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.32 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: 0.00/43.38 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.32 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: 0x00007f2abf079fa2
+ 12: 0x00007f49a9b12fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.39/144.39 result: MeasureResult(costs=(0.00160325892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4100971221923828, timestamp=1651281474.2659922) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 144.33/144.33 result: MeasureResult(costs=(0.0016039419599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4381542205810547, timestamp=1651292902.5259576) [('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: 0.001989
+ Time cost of this operator: 0.002008
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 012e35094..974f7833f 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.716 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.138 0.989 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
- Total_time - 317.174 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.8 98.739 (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 0.943 0.296 (1, 1, 10, 10, 3) 1 1
+ Total_time - 318.819 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.05 96.807 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.104 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.089 (1, 1, 10, 10, 3) 1 1
- Total_time - 82.691 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 154.9 98.331 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.71 1.086 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.584 (1, 1, 10, 10, 3) 1 1
+ Total_time - 157.529 - - - -
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 0c49b87cf..f95858f72 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:43.818** total execution time for **how_to_work_with_microtvm** files:
+**00:45.802** total execution time for **how_to_work_with_microtvm** files:
-- **00:39.780**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.439**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.198**: :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``)
+- **00:41.483**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.668**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.219**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.218**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.214**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.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 943036aca..e8e980776 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
=================
-**00:08.903** total execution time for **how_to_work_with_relay** files:
+**00:09.886** total execution time for **how_to_work_with_relay** files:
-- **00:07.037**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.660**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.207**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.644**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:02.009**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.233**: :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 dcd84b0aa..37792dbb6 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
=================
-**00:05.706** total execution time for **how_to_work_with_schedules** files:
+**00:06.206** total execution time for **how_to_work_with_schedules** files:
-- **00:02.112**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.121**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.735**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.725**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.310**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.244**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.236**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.259**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.296**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.782**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.772**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.340**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.260**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.254**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.244**: :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 f9820a4d4..1c5c214b1 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/tmpw_oz188a/input0.cc'\nsource_filename = \"/tmp/tmpw_oz188a/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/tmpqfxjyvxy/input0.cc'\nsource_filename = \"/tmp/tmpqfxjyvxy/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 2046f2442..c5955c613 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
=================
-**00:20.204** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.867** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.004**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.200**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.652**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.215**: :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 1251a2a41..2bef02f98 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 21.30s!
+ resnet18_v1 inference graph built in 22.35s!
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 ec9b2bfab..0ffe60909 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 14.86s!
+ yolov3-tiny inference graph built in 15.38s!
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 de46ebe74..02b1085c9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:28.154** total execution time for **topic_vta_tutorials_frontend** files:
+**01:30.278** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.825**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.329**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:47.563**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:42.715**: :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 cf818bed7..39096b194 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
=================
-**00:03.583** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.635** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.047**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.536**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.035**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.600**: :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 9883c0c63..00a56ca57 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
=================
-**00:01.014** total execution time for **topic_vta_tutorials** files:
+**00:01.102** total execution time for **topic_vta_tutorials** files:
-- **00:00.514**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.500**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.559**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.543**: :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 81535aa68..36f372dd6 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.593 ms
+ Execution time of this operator: 93.570 ms
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 659351a89..d82b1af03 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
+ {'mean': 497.9875562000234, 'median': 497.66918380005336, 'std': 1.4269151475583237}
@@ -482,31 +482,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 3.28/ 14.68 GFLOPS | Progress: (4/10) | 6.66 s
[Task 1/25] Current/Best: 8.72/ 14.68 GFLOPS | Progress: (8/10) | 10.73 s
[Task 1/25] Current/Best: 13.92/ 16.88 GFLOPS | Progress: (10/10) | 11.74 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 10.15/ 16.52 GFLOPS | Progress: (4/10) | 2.15 s
[Task 2/25] Current/Best: 12.32/ 16.52 GFLOPS | Progress: (8/10) | 4.11 s
[Task 2/25] Current/Best: 11.26/ 16.52 GFLOPS | Progress: (10/10) | 4.80 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 13.26/ 13.26 GFLOPS | Progress: (4/10) | 4.88 s
[Task 3/25] Current/Best: 7.25/ 17.89 GFLOPS | Progress: (8/10) | 7.45 s
[Task 3/25] Current/Best: 17.52/ 20.39 GFLOPS | Progress: (10/10) | 8.30 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 10.97/ 17.60 GFLOPS | Progress: (4/10) | 9.18 s
[Task 4/25] Current/Best: 15.10/ 17.60 GFLOPS | Progress: (8/10) | 13.24 s
[Task 4/25] Current/Best: 13.77/ 17.60 GFLOPS | Progress: (10/10) | 14.75 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 20.76/ 20.76 GFLOPS | Progress: (4/10) | 2.92 s
[Task 5/25] Current/Best: 5.81/ 20.76 GFLOPS | Progress: (8/10) | 4.94 s
[Task 5/25] Current/Best: 4.17/ 20.76 GFLOPS | Progress: (10/10) | 6.28 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 13.50/ 19.06 GFLOPS | Progress: (4/10) | 3.47 s
[Task 6/25] Current/Best: 13.53/ 20.44 GFLOPS | Progress: (8/10) | 5.17 s
[Task 6/25] Current/Best: 14.25/ 20.44 GFLOPS | Progress: (10/10) | 6.55 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 23.25/ 23.26 GFLOPS | Progress: (4/10) | 3.26 s
[Task 7/25] Current/Best: 17.09/ 23.26 GFLOPS | Progress: (8/10) | 6.06 s
[Task 7/25] Current/Best: 16.00/ 23.26 GFLOPS | Progress: (10/10) | 7.01 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 10.83/ 10.83 GFLOPS | Progress: (4/10) | 4.29 s
[Task 8/25] Current/Best: 13.19/ 13.19 GFLOPS | Progress: (8/10) | 26.17 s
[Task 8/25] Current/Best: 11.15/ 13.19 GFLOPS | Progress: (10/10) | 28.21 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 15.30/ 15.78 GFLOPS | Progress: (4/10) | 4.48 s
[Task 9/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (8/10) | 9.13 s
[Task 9/25] Current/Best: 3.53/ 22.23 GFLOPS | Progress: (10/10) | 14.42 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.32/ 20.37 GFLOPS | Progress: (4/10) | 2.28 s
[Task 10/25] Current/Best: 14.14/ 20.37 GFLOPS | Progress: (8/10) | 3.89 s
[Task 10/25] Current/Best: 8.75/ 20.37 GFLOPS | Progress: (10/10) | 4.67 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (4/10) | 3.19 s
[Task 11/25] Current/Best: 12.71/ 24.09 GFLOPS | Progress: (8/10) | 5.37 s
[Task 11/25] Current/Best: 12.90/ 24.09 GFLOPS | Progress: (10/10) | 6.21 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 16.55/ 17.92 GFLOPS | Progress: (4/10) | 3.06 s
[Task 12/25] Current/Best: 19.06/ 19.06 GFLOPS | Progress: (8/10) | 5.96 s
[Task 12/25] Current/Best: 10.07/ 19.06 GFLOPS | Progress: (10/10) | 7.36 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 6.32/ 20.45 GFLOPS | Progress: (4/10) | 3.13 s
[Task 13/25] Current/Best: 22.25/ 22.25 GFLOPS | Progress: (8/10) | 5.15 s
[Task 13/25] Current/Best: 1.56/ 22.25 GFLOPS | Progress: (10/10) | 7.86 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 19.79/ 19.79 GFLOPS | Progress: (4/10) | 4.77 s
[Task 14/25] Current/Best: 10.15/ 19.79 GFLOPS | Progress: (8/10) | 7.62 s
[Task 14/25] Current/Best: 6.64/ 19.79 GFLOPS | Progress: (10/10) | 8.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 12.24/ 22.97 GFLOPS | Progress: (4/10) | 6.01 s
[Task 1/25] Current/Best: 8.68/ 22.97 GFLOPS | Progress: (8/10) | 8.40 s
[Task 1/25] Current/Best: 13.84/ 22.97 GFLOPS | Progress: (10/10) | 9.75 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 16.97/ 20.86 GFLOPS | Progress: (4/10) | 2.13 s
[Task 2/25] Current/Best: 5.26/ 20.86 GFLOPS | Progress: (8/10) | 3.52 s
[Task 2/25] Current/Best: 6.63/ 20.86 GFLOPS | Progress: (10/10) | 4.08 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 8.49/ 23.30 GFLOPS | Progress: (4/10) | 3.47 s
[Task 3/25] Current/Best: 11.48/ 23.30 GFLOPS | Progress: (8/10) | 6.23 s
[Task 3/25] Current/Best: 16.87/ 23.30 GFLOPS | Progress: (10/10) | 7.05 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 13.67/ 13.67 GFLOPS | Progress: (4/10) | 2.60 s
[Task 4/25] Current/Best: 8.68/ 18.49 GFLOPS | Progress: (8/10) | 4.60 s
[Task 4/25] Current/Best: 13.42/ 18.49 GFLOPS | Progress: (10/10) | 5.68 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/10) | 2.89 s
[Task 5/25] Current/Best: 18.20/ 18.26 GFLOPS | Progress: (8/10) | 4.67 s
[Task 5/25] Current/Best: 10.81/ 18.26 GFLOPS | Progress: (10/10) | 5.41 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 5.72/ 16.17 GFLOPS | Progress: (4/10) | 3.44 s
[Task 6/25] Current/Best: 17.72/ 20.62 GFLOPS | Progress: (8/10) | 5.43 s
[Task 6/25] Current/Best: 12.82/ 20.62 GFLOPS | Progress: (10/10) | 6.67 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 3.14/ 23.61 GFLOPS | Progress: (4/10) | 3.41 s
[Task 7/25] Current/Best: 6.59/ 23.61 GFLOPS | Progress: (8/10) | 6.13 s
[Task 7/25] Current/Best: 16.01/ 23.61 GFLOPS | Progress: (10/10) | 6.93 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 3.02/ 19.45 GFLOPS | Progress: (4/10) | 3.38 s
[Task 8/25] Current/Best: 4.59/ 19.45 GFLOPS | Progress: (8/10) | 16.84 s
[Task 8/25] Current/Best: 11.01/ 19.45 GFLOPS | Progress: (10/10) | 21.46 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 12.61/ 21.14 GFLOPS | Progress: (4/10) | 7.42 s
[Task 9/25] Current/Best: 20.18/ 21.14 GFLOPS | Progress: (8/10) | 8.86 s
[Task 9/25] Current/Best: 11.78/ 21.14 GFLOPS | Progress: (10/10) | 16.53 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 17.94/ 17.94 GFLOPS | Progress: (4/10) | 2.43 s
[Task 10/25] Current/Best: 3.28/ 17.94 GFLOPS | Progress: (8/10) | 4.22 s
[Task 10/25] Current/Best: 11.52/ 17.94 GFLOPS | Progress: (10/10) | 7.36 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 20.00/ 20.00 GFLOPS | Progress: (4/10) | 2.91 s
[Task 11/25] Current/Best: 12.51/ 20.00 GFLOPS | Progress: (8/10) | 6.79 s
[Task 11/25] Current/Best: 7.05/ 20.00 GFLOPS | Progress: (10/10) | 7.81 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 12.74/ 14.95 GFLOPS | Progress: (4/10) | 7.02 s
[Task 12/25] Current/Best: 21.89/ 21.89 GFLOPS | Progress: (8/10) | 9.76 s
[Task 12/25] Current/Best: 14.02/ 21.89 GFLOPS | Progress: (10/10) | 10.63 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 3.10/ 17.21 GFLOPS | Progress: (4/10) | 4.49 s
[Task 13/25] Current/Best: 9.14/ 17.21 GFLOPS | Progress: (8/10) | 7.46 s
[Task 13/25] Current/Best: 9.72/ 17.21 GFLOPS | Progress: (10/10) | 9.83 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 8.11/ 11.46 GFLOPS | Progress: (4/10) | 3.87 s
[Task 14/25] Current/Best: 17.96/ 19.61 GFLOPS | Progress: (8/10) | 6.74 s
[Task 14/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (10/10) | 7.56 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 14.37/ 23.79 GFLOPS | Progress: (4/10) | 2.13 s
[Task 15/25] Current/Best: 6.71/ 23.79 GFLOPS | Progress: (8/10) | 4.35 s
[Task 15/25] Current/Best: 9.23/ 23.79 GFLOPS | Progress: (10/10) | 9.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 3.00/ 19.25 GFLOPS | Progress: (4/10) | 3.21 s
[Task 16/25] Current/Best: 17.82/ 21.96 GFLOPS | Progress: (8/10) | 4.31 s
[Task 16/25] Current/Best: 17.75/ 21.96 GFLOPS | Progress: (10/10) | 4.92 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 12.31/ 23.47 GFLOPS | Progress: (4/10) | 2.78 s
[Task 17/25] Current/Best: 17.16/ 23.47 GFLOPS | Progress: (8/10) | 4.84 s
[Task 17/25] Current/Best: 13.47/ 23.47 GFLOPS | Progress: (10/10) | 5.99 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/10) | 4.12 s
[Task 18/25] Current/Best: 8.05/ 18.14 GFLOPS | Progress: (8/10) | 9.30 s
[Task 18/25] Current/Best: 10.33/ 18.14 GFLOPS | Progress: (10/10) | 11.24 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 18.26/ 21.92 GFLOPS | Progress: (4/10) | 3.92 s
[Task 19/25] Current/Best: 18.20/ 21.92 GFLOPS | Progress: (8/10) | 8.41 s
[Task 19/25] Current/Best: 12.77/ 21.92 GFLOPS | Progress: (10/10) | 10.57 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 8.45/ 17.90 GFLOPS | Progress: (4/10) | 3.27 s
[Task 20/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (8/10) | 5.34 s
[Task 20/25] Current/Best: 14.25/ 19.01 GFLOPS | Progress: (10/10) | 5.96 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 5.12/ 17.70 GFLOPS | Progress: (4/10) | 2.87 s
[Task 21/25] Current/Best: 10.30/ 17.70 GFLOPS | Progress: (8/10) | 4.69 s
[Task 21/25] Current/Best: 6.99/ 17.70 GFLOPS | Progress: (10/10) | 5.80 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 12.97/ 15.39 GFLOPS | Progress: (4/10) | 3.45 s
[Task 22/25] Current/Best: 9.93/ 22.09 GFLOPS | Progress: (8/10) | 5.50 s
[Task 22/25] Current/Best: 5.34/ 22.09 GFLOPS | Progress: (10/10) | 6.39
s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 14.43/ 17.53 GFLOPS | Progress: (4/10) | 4.35 s
[Task 23/25] Current/Best: 12.97/ 19.37 GFLOPS | Progress: (8/10) | 6.99 s
[Task 23/25] Current/Best: 8.89/ 23.59 GFLOPS | Progress: (10/10) | 7.96 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 4.30/ 4.30 GFLOPS | Progress: (4/10) | 34.63 s Done.
+
[Task 15/25] Current/Best: 13.98/ 17.24 GFLOPS | Progress: (4/10) | 3.42 s
[Task 15/25] Current/Best: 1.73/ 18.36 GFLOPS | Progress: (8/10) | 7.15 s
[Task 15/25] Current/Best: 21.41/ 21.41 GFLOPS | Progress: (10/10) | 7.79 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (4/10) | 2.28 s
[Task 16/25] Current/Best: 10.54/ 21.55 GFLOPS | Progress: (8/10) | 3.59 s
[Task 16/25] Current/Best: 21.87/ 21.87 GFLOPS | Progress: (10/10) | 5.38 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 9.66/ 12.58 GFLOPS | Progress: (4/10) | 3.99 s
[Task 17/25] Current/Best: 12.45/ 12.58 GFLOPS | Progress: (8/10) | 7.23 s
[Task 17/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (10/10) | 8.51 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 6.76/ 17.51 GFLOPS | Progress: (4/10) | 3.48 s
[Task 18/25] Current/Best: 6.07/ 17.51 GFLOPS | Progress: (8/10) | 10.39 s
[Task 18/25] Current/Best: 7.39/ 20.58 GFLOPS | Progress: (10/10) | 12.47 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 6.14/ 22.39 GFLOPS | Progress: (4/10) | 4.38 s
[Task 19/25] Current/Best: 8.03/ 22.39 GFLOPS | Progress: (8/10) | 9.99 s
[Task 19/25] Current/Best: 18.67/ 22.39 GFLOPS | Progress: (10/10) | 10.86 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 10.35/ 11.95 GFLOPS | Progress: (4/10) | 3.74 s
[Task 20/25] Current/Best: 13.78/ 13.78 GFLOPS | Progress: (8/10) | 5.59 s
[Task 20/25] Current/Best: 0.00/ 13.78 GFLOPS | Progress: (10/10) | 5.97 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 9.85/ 21.04 GFLOPS | Progress: (4/10) | 3.25 s
[Task 21/25] Current/Best: 6.68/ 21.93 GFLOPS | Progress: (8/10) | 7.26 s
[Task 21/25] Current/Best: 3.16/ 21.93 GFLOPS | Progress: (10/10) | 8.25 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 16.31/ 19.56 GFLOPS | Progress: (4/10) | 2.70 s
[Task 22/25] Current/Best: 16.91/ 19.67 GFLOPS | Progress: (8/10) | 4.05 s
[Task 22/25] Current/Best: 7.83/ 19.67 GFLOPS | Progress: (10/10) | 5.72
s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 8.60/ 22.30 GFLOPS | Progress: (4/10) | 4.83 s
[Task 23/25] Current/Best: 16.07/ 22.30 GFLOPS | Progress: (8/10) | 7.31 s
[Task 23/25] Current/Best: 11.16/ 22.30 GFLOPS | Progress: (10/10) | 9.01 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
- Done.
-
[Task 24/25] Current/Best: 3.60/ 8.70 GFLOPS | Progress: (8/10) | 56.50 s
[Task 24/25] Current/Best: 5.20/ 8.70 GFLOPS | Progress: (10/10) | 66.90 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
-
[Task 25/25] Current/Best: 5.68/ 9.05 GFLOPS | Progress: (4/10) | 3.54 s
[Task 25/25] Current/Best: 5.81/ 9.05 GFLOPS | Progress: (8/10) | 6.19 s
[Task 25/25] Current/Best: 7.64/ 9.05 GFLOPS | Progress: (10/10) | 6.96 s Done.
+
[Task 24/25] Current/Best: 2.63/ 2.63 GFLOPS | Progress: (4/10) | 58.23 s
[Task 24/25] Current/Best: 9.59/ 9.59 GFLOPS | Progress: (8/10) | 281.83 s
[Task 24/25] Current/Best: 3.41/ 9.59 GFLOPS | Progress: (10/10) | 293.99 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 3.61/ 7.60 GFLOPS | Progress: (4/10) | 5.83 s
[Task 25/25] Current/Best: 7.89/ 7.89 GFLOPS | Progress: (8/10) | 11.16 s
[Task 25/25] Current/Best: 3.51/ 7.89 GFLOPS | Progress: (10/10) | 15.97 s Done.
@@ -565,6 +564,14 @@ model using optimized operators to speed up our computations.
+.. rst-class:: sphx-glr-script-out
+
+ Out:
+
+ .. code-block:: none
+
+ Done.
+
Verify that the optimized model runs and produces the same results:
@@ -595,8 +602,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -649,8 +656,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 428.3857485400017, 'median': 428.4126755999978, 'std': 0.6424460229291523}
- unoptimized: {'mean': 491.7812707299992, 'median': 491.7406261499991, 'std': 0.606950351019823}
+ optimized: {'mean': 444.93712196999695, 'median': 444.79594105000615, 'std': 1.0579891845993745}
+ unoptimized: {'mean': 497.9875562000234, 'median': 497.66918380005336, 'std': 1.4269151475583237}
@@ -670,7 +677,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 7 minutes 49.457 seconds)
+ **Total running time of the script:** ( 11 minutes 48.780 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 4cd3194d8..e371d73c5 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
- 1.276e-07 secs/op
+ 1.279e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 49150f98f..3b668d901 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xe7ae3a0)), stage(b, placeholder(b, 0xe0554d0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0x54fb300)), stage(b, placeholder(b, 0x566c590)), 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 271a9bdd0..3058b0ef6 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
=================
-**10:41.220** total execution time for **tutorial** files:
+**14:23.025** total execution time for **tutorial** files:
-- **07:49.457**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **00:58.813**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:58.451**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.207**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:26.040**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:01.211**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.713**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.199**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.037**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.031**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.030**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.030**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **11:48.780**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:01.531**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:44.528**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:26.540**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:19.856**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.726**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.614**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.232**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.056**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.055**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.054**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.054**: :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 7491581c8..5bef6061a 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -243,7 +243,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000006
@@ -388,7 +388,7 @@ 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"),
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.180989998687437e-06 1.0
- naive 6.1019e-06 0.8497296335345577
- parallel 6.112399999999999e-06 0.8511918274663023
- vector 2.4469599999999997e-05 3.4075524411637703
+ numpy 7.583030001114821e-06 1.0
+ naive 5.8504e-06 0.7715121790550613
+ parallel 6.0865e-06 0.8026474903970038
+ vector 2.46347e-05 3.2486618141268493
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018402
+ Numpy running time: 0.018741
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.253881
+ none: 3.451376
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.301795
+ blocking: 0.304061
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.336453
+ vectorization: 0.335071
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.114948
+ loop permutation: 0.118027
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107904
+ array packing: 0.110283
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110984
+ block caching: 0.110907
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144506
+ parallelization: 0.144727
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2538812269 1.0
- blocking 0.30179535830000004 0.09274934678163499
- vectorization 0.3364530468 0.10340053103921733
- loop permutation 0.11494751169999999 0.03532627766180373
- array packing 0.1079040546 0.03316164514793955
- block caching 0.11098448289999999 0.03410833867643529
- parallelization 0.1445058061 0.044410289135744484
+ none 3.4513759629 1.0
+ blocking 0.3040608368 0.08809843959871429
+ vectorization 0.33507104239999996 0.09708332155111214
+ loop permutation 0.1180269743 0.034197078373585384
+ array packing 0.110282971 0.0319533346078401
+ block caching 0.11090670459999999 0.03213405487903185
+ parallelization 0.14472713739999998 0.04193317069937342
@@ -1541,6 +1541,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.531 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 3ddb7233f..c3157ff09 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-552f06ed450d59816eb3a85f7e810d9726dcce26
+17b687e400e39d82f9ff92dadd66076cf429f91f
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 2bd696a21..c270f7f9f 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.zipeccbf69f-00ae-4432-87a2-b99dccae5fad 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.zip0aba8440-1535-4da1-85fb-146681a0a832 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 716fac026..d1bbe6642 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,48 +406,71 @@ 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<08:33, 84.6kB/s]
- 0%| | 48.0k/41.5M [00:00<05:34, 130kB/s]
- 0%| | 96.0k/41.5M [00:00<04:10, 174kB/s]
- 0%| | 160k/41.5M [00:00<03:09, 229kB/s]
- 1%| | 328k/41.5M [00:01<01:36, 447kB/s]
- 1%|1 | 544k/41.5M [00:01<01:04, 666kB/s]
- 3%|2 | 1.06M/41.5M [00:01<00:31, 1.33MB/s]
- 5%|4 | 1.99M/41.5M [00:01<00:16, 2.45MB/s]
- 8%|8 | 3.46M/41.5M [00:01<00:09, 4.11MB/s]
- 12%|#1 | 4.93M/41.5M [00:02<00:07, 5.14MB/s]
- 15%|#5 | 6.41M/41.5M [00:02<00:06, 5.87MB/s]
- 19%|#8 | 7.88M/41.5M [00:02<00:05, 6.31MB/s]
- 23%|##2 | 9.34M/41.5M [00:02<00:05, 6.54MB/s]
- 26%|##6 | 10.8M/41.5M [00:02<00:04, 6.78MB/s]
- 30%|##9 | 12.3M/41.5M [00:03<00:04, 6.93MB/s]
- 33%|###3 | 13.8M/41.5M [00:03<00:04, 7.10MB/s]
- 37%|###6 | 15.2M/41.5M [00:03<00:03, 8.35MB/s]
- 39%|###8 | 16.1M/41.5M [00:03<00:03, 8.38MB/s]
- 41%|#### | 17.0M/41.5M [00:03<00:03, 7.00MB/s]
- 44%|####3 | 18.1M/41.5M [00:03<00:03, 7.99MB/s]
- 46%|####5 | 19.0M/41.5M [00:03<00:02, 8.13MB/s]
- 48%|####7 | 19.8M/41.5M [00:04<00:03, 6.49MB/s]
- 51%|##### | 21.1M/41.5M [00:04<00:03, 6.29MB/s]
- 54%|#####4 | 22.6M/41.5M [00:04<00:03, 6.52MB/s]
- 58%|#####7 | 24.0M/41.5M [00:04<00:02, 6.63MB/s]
- 61%|######1 | 25.5M/41.5M [00:05<00:02, 6.67MB/s]
- 65%|######4 | 26.9M/41.5M [00:05<00:01, 8.04MB/s]
- 67%|######7 | 27.8M/41.5M [00:05<00:01, 8.03MB/s]
- 69%|######9 | 28.6M/41.5M [00:05<00:01, 6.78MB/s]
- 72%|#######1 | 29.9M/41.5M [00:05<00:01, 7.96MB/s]
- 74%|#######4 | 30.7M/41.5M [00:05<00:01, 8.08MB/s]
- 76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.58MB/s]
- 79%|#######9 | 32.8M/41.5M [00:05<00:01, 7.81MB/s]
- 81%|########1 | 33.6M/41.5M [00:06<00:01, 7.76MB/s]
- 83%|########3 | 34.5M/41.5M [00:06<00:01, 6.42MB/s]
- 86%|########6 | 35.8M/41.5M [00:06<00:00, 7.64MB/s]
- 89%|########9 | 36.9M/41.5M [00:06<00:00, 8.74MB/s]
- 91%|#########1| 37.9M/41.5M [00:06<00:00, 7.65MB/s]
- 93%|#########3| 38.7M/41.5M [00:06<00:00, 7.37MB/s]
- 96%|#########6| 39.9M/41.5M [00:06<00:00, 8.41MB/s]
- 98%|#########8| 40.7M/41.5M [00:07<00:00, 7.30MB/s]
-100%|##########| 41.5M/41.5M [00:07<00:00, 6.10MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:03, 90.0kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:04, 143kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:38, 198kB/s]
+ 0%| | 168k/41.5M [00:00<02:34, 280kB/s]
+ 1%| | 304k/41.5M [00:00<01:37, 444kB/s]
+ 1%|1 | 496k/41.5M [00:01<01:07, 637kB/s]
+ 2%|1 | 728k/41.5M [00:01<00:53, 804kB/s]
+ 2%|2 | 968k/41.5M [00:01<00:45, 935kB/s]
+ 3%|2 | 1.20M/41.5M [00:01<00:39, 1.06MB/s]
+ 4%|3 | 1.45M/41.5M [00:01<00:35, 1.19MB/s]
+ 4%|4 | 1.72M/41.5M [00:02<00:32, 1.30MB/s]
+ 5%|4 | 2.01M/41.5M [00:02<00:29, 1.40MB/s]
+ 6%|5 | 2.30M/41.5M [00:02<00:28, 1.46MB/s]
+ 6%|6 | 2.61M/41.5M [00:02<00:26, 1.54MB/s]
+ 7%|7 | 2.93M/41.5M [00:02<00:25, 1.60MB/s]
+ 8%|7 | 3.27M/41.5M [00:03<00:24, 1.67MB/s]
+ 9%|8 | 3.62M/41.5M [00:03<00:22, 1.76MB/s]
+ 10%|9 | 3.98M/41.5M [00:03<00:21, 1.86MB/s]
+ 11%|# | 4.37M/41.5M [00:03<00:19, 1.96MB/s]
+ 12%|#1 | 4.77M/41.5M [00:03<00:18, 2.07MB/s]
+ 13%|#2 | 5.20M/41.5M [00:03<00:17, 2.18MB/s]
+ 14%|#3 | 5.65M/41.5M [00:04<00:16, 2.27MB/s]
+ 15%|#4 | 6.12M/41.5M [00:04<00:15, 2.36MB/s]
+ 16%|#5 | 6.62M/41.5M [00:04<00:14, 2.46MB/s]
+ 17%|#7 | 7.13M/41.5M [00:04<00:13, 2.57MB/s]
+ 18%|#8 | 7.67M/41.5M [00:04<00:11, 3.14MB/s]
+ 20%|#9 | 8.23M/41.5M [00:04<00:09, 3.51MB/s]
+ 21%|## | 8.60M/41.5M [00:05<00:10, 3.22MB/s]
+ 22%|##1 | 8.93M/41.5M [00:05<00:12, 2.77MB/s]
+ 23%|##2 | 9.48M/41.5M [00:05<00:11, 2.88MB/s]
+ 24%|##4 | 10.1M/41.5M [00:05<00:08, 3.66MB/s]
+ 26%|##6 | 10.8M/41.5M [00:05<00:07, 4.39MB/s]
+ 27%|##7 | 11.3M/41.5M [00:05<00:07, 4.01MB/s]
+ 28%|##8 | 11.7M/41.5M [00:06<00:09, 3.39MB/s]
+ 30%|##9 | 12.3M/41.5M [00:06<00:07, 4.02MB/s]
+ 32%|###1 | 13.1M/41.5M [00:06<00:06, 4.84MB/s]
+ 33%|###2 | 13.6M/41.5M [00:06<00:06, 4.26MB/s]
+ 34%|###3 | 14.1M/41.5M [00:06<00:07, 3.61MB/s]
+ 36%|###5 | 14.8M/41.5M [00:06<00:06, 4.53MB/s]
+ 38%|###7 | 15.7M/41.5M [00:06<00:04, 5.43MB/s]
+ 39%|###9 | 16.3M/41.5M [00:06<00:05, 4.81MB/s]
+ 41%|#### | 16.8M/41.5M [00:07<00:06, 4.07MB/s]
+ 43%|####2 | 17.8M/41.5M [00:07<00:05, 4.65MB/s]
+ 45%|####5 | 18.8M/41.5M [00:07<00:04, 5.82MB/s]
+ 47%|####6 | 19.4M/41.5M [00:07<00:04, 5.54MB/s]
+ 48%|####8 | 20.0M/41.5M [00:07<00:04, 4.76MB/s]
+ 50%|##### | 20.9M/41.5M [00:07<00:04, 5.03MB/s]
+ 53%|#####3 | 22.1M/41.5M [00:08<00:03, 5.55MB/s]
+ 56%|#####6 | 23.3M/41.5M [00:08<00:03, 5.99MB/s]
+ 59%|#####9 | 24.6M/41.5M [00:08<00:02, 6.33MB/s]
+ 62%|######2 | 25.9M/41.5M [00:08<00:02, 6.74MB/s]
+ 66%|######5 | 27.3M/41.5M [00:08<00:02, 7.23MB/s]
+ 69%|######9 | 28.7M/41.5M [00:08<00:01, 8.52MB/s]
+ 73%|#######2 | 30.2M/41.5M [00:09<00:01, 9.78MB/s]
+ 75%|#######5 | 31.2M/41.5M [00:09<00:01, 8.89MB/s]
+ 77%|#######7 | 32.1M/41.5M [00:09<00:01, 7.66MB/s]
+ 80%|#######9 | 33.1M/41.5M [00:09<00:01, 8.32MB/s]
+ 83%|########3 | 34.5M/41.5M [00:09<00:00, 9.73MB/s]
+ 86%|########5 | 35.6M/41.5M [00:09<00:00, 8.78MB/s]
+ 88%|########7 | 36.5M/41.5M [00:09<00:00, 7.45MB/s]
+ 90%|######### | 37.5M/41.5M [00:10<00:00, 8.14MB/s]
+ 94%|#########3| 38.9M/41.5M [00:10<00:00, 9.58MB/s]
+ 96%|#########6| 39.9M/41.5M [00:10<00:00, 8.48MB/s]
+ 98%|#########8| 40.8M/41.5M [00:10<00:00, 7.23MB/s]
+100%|##########| 41.5M/41.5M [00:10<00:00, 4.13MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 5cbd5128a..936b5503e 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -420,7 +420,7 @@ provides a static definition of the input size.</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>/workspace/python/tvm/relay/frontend/onnx.py:5595: UserWarning: Mismatched attribute type in ' : kernel_shape'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/frontend/onnx.py:5596: UserWarning: Mismatched attribute type in ' : kernel_shape'
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 9052807bf..9d1333ed3 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.918 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 21 minutes 58.059 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 6be070511..8a735ab5a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,9 +387,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
- 83%|########3 | 37.2M/44.7M [00:00<00:00, 198MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 186MB/s]
+ 30%|##9 | 13.2M/44.7M [00:00<00:00, 138MB/s]
+ 77%|#######6 | 34.2M/44.7M [00:00<00:00, 186MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 184MB/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 5dd595095..2de6010bf 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,6 +607,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.010 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 d32e74444..60e42bceb 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>05:15.477</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>26:18.836</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:06.918</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>00:59.815</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>00:55.491</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:31.087</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>00:25.177</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:21.531</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>00:20.848</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:18.629</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:13.297</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>00:02.684</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>21:58.059</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>01:04.010</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:56.771</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>00:35.024</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>00:25.485</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:21.711</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>00:21.707</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:19.580</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:13.739</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>00:02.749</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 b3df563e1..d607e675f 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9735 15.9725 16.1387 15.8400 0.0920
+ 16.1572 16.1322 16.3299 16.0403 0.0952
</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 0d30c82e2..10e3e1712 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,24 +409,95 @@ 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]
- 6%|5 | 9.83M/170M [00:00<00:01, 103MB/s]
- 12%|#1 | 19.7M/170M [00:00<00:01, 92.6MB/s]
- 17%|#7 | 28.9M/170M [00:00<00:01, 94.6MB/s]
- 23%|##2 | 38.8M/170M [00:00<00:01, 97.8MB/s]
- 28%|##8 | 48.1M/170M [00:00<00:01, 86.4MB/s]
- 33%|###3 | 56.6M/170M [00:00<00:01, 84.6MB/s]
- 39%|###8 | 65.8M/170M [00:00<00:01, 88.1MB/s]
- 44%|####4 | 74.8M/170M [00:00<00:01, 90.0MB/s]
- 49%|####9 | 83.5M/170M [00:00<00:01, 83.4MB/s]
- 55%|#####5 | 93.8M/170M [00:01<00:00, 89.8MB/s]
- 60%|###### | 103M/170M [00:01<00:00, 90.1MB/s]
- 65%|######5 | 111M/170M [00:01<00:00, 84.9MB/s]
- 71%|#######1 | 121M/170M [00:01<00:00, 90.6MB/s]
- 77%|#######6 | 131M/170M [00:01<00:00, 93.1MB/s]
- 83%|########3 | 142M/170M [00:01<00:00, 99.3MB/s]
- 89%|########9 | 152M/170M [00:01<00:00, 101MB/s]
- 95%|#########5| 162M/170M [00:01<00:00, 90.9MB/s]
-100%|##########| 170M/170M [00:01<00:00, 89.6MB/s]
+ 1%| | 1.25M/170M [00:00<00:13, 12.7MB/s]
+ 1%|1 | 2.46M/170M [00:00<00:15, 11.4MB/s]
+ 2%|2 | 3.88M/170M [00:00<00:13, 12.5MB/s]
+ 4%|3 | 6.38M/170M [00:00<00:11, 15.0MB/s]
+ 5%|4 | 8.01M/170M [00:00<00:10, 15.5MB/s]
+ 6%|5 | 9.77M/170M [00:00<00:10, 16.4MB/s]
+ 7%|7 | 12.6M/170M [00:00<00:08, 20.3MB/s]
+ 9%|8 | 14.6M/170M [00:00<00:09, 17.4MB/s]
+ 10%|9 | 16.3M/170M [00:01<00:10, 14.6MB/s]
+ 11%|# | 18.0M/170M [00:01<00:11, 14.1MB/s]
+ 11%|#1 | 19.5M/170M [00:01<00:11, 13.8MB/s]
+ 12%|#2 | 20.8M/170M [00:01<00:12, 13.0MB/s]
+ 13%|#3 | 22.1M/170M [00:01<00:11, 12.9MB/s]
+ 14%|#3 | 23.4M/170M [00:01<00:11, 12.9MB/s]
+ 15%|#5 | 25.7M/170M [00:01<00:09, 15.8MB/s]
+ 16%|#6 | 27.8M/170M [00:01<00:09, 16.5MB/s]
+ 17%|#7 | 29.4M/170M [00:02<00:09, 15.3MB/s]
+ 18%|#8 | 31.1M/170M [00:02<00:09, 15.8MB/s]
+ 19%|#9 | 32.6M/170M [00:02<00:10, 14.0MB/s]
+ 20%|## | 34.4M/170M [00:02<00:09, 14.8MB/s]
+ 22%|##2 | 37.4M/170M [00:02<00:07, 19.4MB/s]
+ 23%|##3 | 39.7M/170M [00:02<00:06, 20.5MB/s]
+ 25%|##4 | 41.9M/170M [00:02<00:06, 20.4MB/s]
+ 26%|##5 | 43.9M/170M [00:02<00:06, 20.1MB/s]
+ 27%|##7 | 45.9M/170M [00:02<00:06, 20.3MB/s]
+ 28%|##8 | 47.9M/170M [00:03<00:07, 17.3MB/s]
+ 29%|##9 | 49.6M/170M [00:03<00:07, 17.4MB/s]
+ 30%|### | 51.3M/170M [00:03<00:07, 16.1MB/s]
+ 31%|###1 | 52.9M/170M [00:03<00:07, 15.4MB/s]
+ 32%|###2 | 54.4M/170M [00:03<00:07, 15.3MB/s]
+ 33%|###3 | 56.4M/170M [00:03<00:07, 16.5MB/s]
+ 34%|###4 | 58.0M/170M [00:03<00:07, 16.0MB/s]
+ 35%|###5 | 59.5M/170M [00:03<00:08, 13.0MB/s]
+ 36%|###6 | 61.8M/170M [00:04<00:07, 15.6MB/s]
+ 37%|###7 | 63.4M/170M [00:04<00:07, 15.4MB/s]
+ 38%|###8 | 65.0M/170M [00:04<00:07, 14.8MB/s]
+ 40%|###9 | 67.5M/170M [00:04<00:06, 17.7MB/s]
+ 42%|####1 | 70.7M/170M [00:04<00:04, 22.0MB/s]
+ 43%|####2 | 72.9M/170M [00:04<00:04, 20.9MB/s]
+ 44%|####4 | 75.0M/170M [00:04<00:04, 20.5MB/s]
+ 46%|####6 | 78.3M/170M [00:04<00:03, 24.0MB/s]
+ 47%|####7 | 80.6M/170M [00:05<00:04, 20.3MB/s]
+ 49%|####8 | 82.7M/170M [00:05<00:06, 15.1MB/s]
+ 50%|####9 | 84.4M/170M [00:05<00:06, 14.5MB/s]
+ 51%|#####1 | 86.9M/170M [00:05<00:05, 16.8MB/s]
+ 52%|#####2 | 88.7M/170M [00:05<00:05, 15.9MB/s]
+ 53%|#####3 | 90.5M/170M [00:05<00:05, 16.6MB/s]
+ 54%|#####4 | 92.2M/170M [00:05<00:04, 16.9MB/s]
+ 55%|#####5 | 93.9M/170M [00:05<00:05, 15.8MB/s]
+ 56%|#####6 | 95.7M/170M [00:06<00:04, 16.3MB/s]
+ 57%|#####7 | 97.3M/170M [00:06<00:04, 15.4MB/s]
+ 58%|#####8 | 98.8M/170M [00:06<00:04, 15.4MB/s]
+ 59%|#####9 | 100M/170M [00:06<00:04, 14.9MB/s]
+ 60%|###### | 103M/170M [00:06<00:03, 17.8MB/s]
+ 62%|######1 | 104M/170M [00:06<00:04, 13.9MB/s]
+ 62%|######2 | 106M/170M [00:06<00:04, 13.8MB/s]
+ 64%|######3 | 108M/170M [00:06<00:04, 14.7MB/s]
+ 64%|######4 | 109M/170M [00:07<00:04, 14.0MB/s]
+ 65%|######5 | 111M/170M [00:07<00:04, 14.1MB/s]
+ 66%|######6 | 112M/170M [00:07<00:04, 14.3MB/s]
+ 67%|######7 | 114M/170M [00:07<00:03, 16.5MB/s]
+ 69%|######8 | 117M/170M [00:07<00:02, 19.7MB/s]
+ 71%|####### | 120M/170M [00:07<00:02, 21.8MB/s]
+ 72%|#######2 | 123M/170M [00:07<00:01, 25.1MB/s]
+ 74%|#######3 | 126M/170M [00:07<00:02, 22.1MB/s]
+ 75%|#######5 | 128M/170M [00:08<00:02, 19.8MB/s]
+ 76%|#######6 | 130M/170M [00:08<00:02, 18.7MB/s]
+ 77%|#######7 | 132M/170M [00:08<00:02, 18.7MB/s]
+ 79%|#######8 | 134M/170M [00:08<00:01, 19.1MB/s]
+ 80%|######## | 136M/170M [00:08<00:01, 20.5MB/s]
+ 81%|########1 | 138M/170M [00:08<00:01, 18.1MB/s]
+ 82%|########2 | 140M/170M [00:08<00:02, 14.4MB/s]
+ 83%|########3 | 141M/170M [00:08<00:01, 15.3MB/s]
+ 84%|########4 | 143M/170M [00:09<00:02, 14.0MB/s]
+ 85%|########5 | 144M/170M [00:09<00:01, 14.2MB/s]
+ 86%|########6 | 146M/170M [00:09<00:01, 15.6MB/s]
+ 87%|########7 | 148M/170M [00:09<00:01, 15.5MB/s]
+ 88%|########8 | 150M/170M [00:09<00:01, 14.9MB/s]
+ 89%|########9 | 151M/170M [00:09<00:01, 16.3MB/s]
+ 90%|######### | 153M/170M [00:09<00:01, 17.0MB/s]
+ 91%|#########1| 155M/170M [00:09<00:00, 16.9MB/s]
+ 93%|#########2| 157M/170M [00:09<00:00, 18.1MB/s]
+ 94%|#########3| 159M/170M [00:10<00:00, 16.8MB/s]
+ 95%|#########4| 161M/170M [00:10<00:00, 16.6MB/s]
+ 96%|#########5| 163M/170M [00:10<00:00, 18.6MB/s]
+ 97%|#########7| 165M/170M [00:10<00:00, 19.0MB/s]
+ 98%|#########8| 167M/170M [00:10<00:00, 17.2MB/s]
+ 99%|#########9| 168M/170M [00:10<00:00, 16.4MB/s]
+100%|##########| 170M/170M [00:10<00:00, 16.7MB/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').
@@ -519,7 +590,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.101 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.108 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 3405f2e93..adb0e9a7f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,15 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
+ 12%|#2 | 1.69M/13.6M [00:00<00:00, 17.2MB/s]
+ 25%|##4 | 3.33M/13.6M [00:00<00:00, 11.5MB/s]
+ 39%|###8 | 5.27M/13.6M [00:00<00:00, 14.1MB/s]
+ 52%|#####1 | 6.99M/13.6M [00:00<00:00, 15.1MB/s]
+ 63%|######2 | 8.52M/13.6M [00:00<00:00, 15.4MB/s]
+ 74%|#######4 | 10.0M/13.6M [00:00<00:00, 15.3MB/s]
+ 85%|########5 | 11.5M/13.6M [00:01<00:00, 9.41MB/s]
+ 94%|#########3| 12.7M/13.6M [00:01<00:00, 9.57MB/s]
+100%|##########| 13.6M/13.6M [00:01<00:00, 11.8MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +547,7 @@ 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)
- 90.3897 90.2330 92.7423 89.9795 0.3807
+ 90.7954 90.6947 100.4582 90.1987 1.0365
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +586,7 @@ 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 4.622 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.781 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 1a55a4527..46afb51d3 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.5120 119.4274 121.5809 118.4995 0.4991
+ 120.0622 119.9243 126.6465 119.0002 0.9385
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 56.016 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.709 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 a9d60cea9..dd2cca9a0 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.968 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.520 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 3ab8f53c4..a0c57911a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,24 +415,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|2 | 3469/132723 [00:00<00:03, 34420.94KB/s]
- 7%|6 | 8811/132723 [00:00<00:02, 45556.38KB/s]
- 13%|#2 | 16679/132723 [00:00<00:01, 60652.65KB/s]
- 19%|#8 | 24681/132723 [00:00<00:01, 68288.44KB/s]
- 25%|##4 | 32729/132723 [00:00<00:01, 72675.72KB/s]
- 31%|### | 40742/132723 [00:00<00:01, 75206.24KB/s]
- 37%|###6 | 48808/132723 [00:00<00:01, 76987.35KB/s]
- 43%|####2 | 56841/132723 [00:00<00:00, 78048.74KB/s]
- 49%|####8 | 64647/132723 [00:00<00:00, 77763.41KB/s]
- 55%|#####4 | 72448/132723 [00:01<00:00, 77835.59KB/s]
- 60%|###### | 80248/132723 [00:01<00:00, 77876.25KB/s]
- 66%|######6 | 88037/132723 [00:01<00:00, 77740.81KB/s]
- 72%|#######2 | 95812/132723 [00:01<00:00, 77595.04KB/s]
- 78%|#######8 | 103608/132723 [00:01<00:00, 77701.18KB/s]
- 84%|########3 | 111379/132723 [00:01<00:00, 77457.54KB/s]
- 90%|########9 | 119126/132723 [00:01<00:00, 77329.54KB/s]
- 96%|#########5| 126864/132723 [00:01<00:00, 77340.81KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74499.40KB/s]
+ 3%|2 | 3930/132723 [00:00<00:03, 39296.38KB/s]
+ 8%|7 | 10091/132723 [00:00<00:02, 52419.00KB/s]
+ 14%|#3 | 18506/132723 [00:00<00:01, 66905.93KB/s]
+ 20%|## | 26876/132723 [00:00<00:01, 73533.10KB/s]
+ 27%|##6 | 35391/132723 [00:00<00:01, 77719.85KB/s]
+ 33%|###3 | 43988/132723 [00:00<00:01, 80518.98KB/s]
+ 39%|###9 | 52377/132723 [00:00<00:00, 81619.58KB/s]
+ 46%|####5 | 60864/132723 [00:00<00:00, 82646.66KB/s]
+ 52%|#####2 | 69289/132723 [00:00<00:00, 83144.51KB/s]
+ 59%|#####8 | 77776/132723 [00:01<00:00, 83670.53KB/s]
+ 65%|######5 | 86293/132723 [00:01<00:00, 84126.95KB/s]
+ 71%|#######1 | 94827/132723 [00:01<00:00, 84492.65KB/s]
+ 78%|#######7 | 103302/132723 [00:01<00:00, 84568.55KB/s]
+ 84%|########4 | 111759/132723 [00:01<00:00, 84558.54KB/s]
+ 91%|######### | 120215/132723 [00:01<00:00, 79103.22KB/s]
+ 97%|#########7| 128749/132723 [00:01<00:00, 80890.78KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 79396.11KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -472,7 +471,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.450 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 25.953 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 18b20ebaa..50eca5ca9 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:27.704</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:59.591</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:04.101</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>02:22.450</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>01:56.016</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>01:10.968</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>01:04.622</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>00:27.896</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>00:21.451</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>00:00.202</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>03:20.108</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:25.953</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>02:00.709</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>01:12.520</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>01:07.781</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>00:29.552</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>00:22.757</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>00:00.211</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 de9aff35a..d05fe1694 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb1c37f6d-754c-4b34-aca9-d8ed44396371 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.zip754d81c8-ba1a-4c89-a8dd-418c23c8656b 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>
@@ -650,7 +650,7 @@ 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>Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registerd for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 54e462b90..04357d6b8 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>00:37.957</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.848</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.493</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>00:02.229</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>00:01.040</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>00:00.194</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>00:35.221</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>00:02.297</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>00:01.107</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>00:00.222</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 86e012a8c..bd9fd339d 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: 5847us [5847us] (44.94%; 44.94%)
-FoldScaleAxis: 7163us [2us] (55.06%; 55.06%)
- FoldConstant: 7161us [1488us] (55.04%; 99.97%)
- InferType: 5673us [5673us] (43.61%; 79.22%)
+InferType: 6268us [6268us] (45.79%; 45.79%)
+FoldScaleAxis: 7421us [2us] (54.21%; 54.21%)
+ FoldConstant: 7418us [1525us] (54.19%; 99.97%)
+ InferType: 5893us [5893us] (43.05%; 79.44%)
</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: 5683us [5683us] (44.20%; 44.20%)
-FoldScaleAxis: 7173us [2us] (55.80%; 55.80%)
- FoldConstant: 7171us [1510us] (55.78%; 99.98%)
- InferType: 5661us [5661us] (44.04%; 78.94%)
+InferType: 6026us [6026us] (44.82%; 44.82%)
+FoldScaleAxis: 7419us [2us] (55.18%; 55.18%)
+ FoldConstant: 7417us [1540us] (55.17%; 99.98%)
+ InferType: 5877us [5877us] (43.71%; 79.23%)
</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 ddf254870..911dffd3e 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: 54.134968 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.018735 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 cce10f835..7e94a54b3 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: 7.091136 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.421299 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 f6e7fb3b7..4ce630532 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: 0.018117
-Baseline: 3.197863
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018893
+Baseline: 3.444817
</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: 0.302272
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.297772
</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: 0.341488
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333955
</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: 0.120279
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117961
</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: 0.111055
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110713
</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: 0.111010
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111482
</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: 0.144610
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145078
</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 dcbf77a03..88148847f 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>00:34.438</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.304</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:31.826</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>00:01.414</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>00:01.197</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>00:32.535</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.493</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.276</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 330b8364f..3b2756942 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>04:55.482</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:04.820</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:20.906</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>01:19.998</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:40.306</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>00:17.326</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>00:08.590</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>00:08.355</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>02:28.498</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>01:21.539</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>00:41.053</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>00:16.092</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>00:09.124</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>00:08.513</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 99079d1e9..1830ed675 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -470,689 +470,70 @@ 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" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [324]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_1: int32 = (rc.outer.outer*196)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (fl [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + ( [...]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [324], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 100), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[(threadIdx.x_2*6)] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6))]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 1)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 2)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 3)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 4)]
+ }
+ if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*6) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 6)*6)) + 5)]
+ }
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ for (xx.outer.inner: int32, 0, 7) {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*36) + (ry.outer.inner*3)) + 29)]))
+ }
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 71)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- compute[(((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
- compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*64) + threadIdx.x)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
</pre></div>
@@ -1189,7 +570,7 @@ 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: 0.260 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.268 ms
</pre></div>
</div>
</div>
@@ -1221,35 +602,35 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=64)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_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=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_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=7)
+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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1266,16 +647,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
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=64)
+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)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+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)
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", 1024)
+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, "unroll_explicit", True)
CUDA source code:
@@ -1293,10 +674,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[576];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1304,599 +685,52 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int) [...]
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int [...]
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 100) {
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[(((int)threadIdx.x) * 6)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6))];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 1)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 2)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 3)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 4)];
+ }
+ if (((int)threadIdx.x) < 96) {
+ kernel_shared[((((int)threadIdx.x) * 6) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 6) * 6)) + 5)];
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
- kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3))]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 36) + (ry_outer_inner * 3)) + 29)]));
+ }
+ }
+ }
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
- compute[((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1933,7 +767,7 @@ 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 20.906 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.498 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 04b137a53..f8d39d4a2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7771 9.7825 9.8053 9.7436 0.0255
+ 9.8268 9.8703 9.8707 9.7394 0.0618
</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 5a7954e52..52ecb951e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 765.3085 765.3539 767.8644 762.7072 2.1057
+ 769.2630 769.7279 772.1471 765.9140 2.5658
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.998 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.539 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 ec2d2557e..29076aaf3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,407 +600,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = (nb_j.inner*16)
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_2] = 0f32
- compute_5[(cse_var_2 + 1)] = 0f32
- compute_5[(cse_var_2 + 2)] = 0f32
- compute_5[(cse_var_2 + 3)] = 0f32
- compute_5[(cse_var_2 + 4)] = 0f32
- compute_5[(cse_var_2 + 5)] = 0f32
- compute_5[(cse_var_2 + 6)] = 0f32
- compute_5[(cse_var_2 + 7)] = 0f32
- compute_5[(cse_var_2 + 8)] = 0f32
- compute_5[(cse_var_2 + 9)] = 0f32
- compute_5[(cse_var_2 + 10)] = 0f32
- compute_5[(cse_var_2 + 11)] = 0f32
- compute_5[(cse_var_2 + 12)] = 0f32
- compute_5[(cse_var_2 + 13)] = 0f32
- compute_5[(cse_var_2 + 14)] = 0f32
- compute_5[(cse_var_2 + 15)] = 0f32
- compute_5[(cse_var_2 + 32)] = 0f32
- compute_5[(cse_var_2 + 33)] = 0f32
- compute_5[(cse_var_2 + 34)] = 0f32
- compute_5[(cse_var_2 + 35)] = 0f32
- compute_5[(cse_var_2 + 36)] = 0f32
- compute_5[(cse_var_2 + 37)] = 0f32
- compute_5[(cse_var_2 + 38)] = 0f32
- compute_5[(cse_var_2 + 39)] = 0f32
- compute_5[(cse_var_2 + 40)] = 0f32
- compute_5[(cse_var_2 + 41)] = 0f32
- compute_5[(cse_var_2 + 42)] = 0f32
- compute_5[(cse_var_2 + 43)] = 0f32
- compute_5[(cse_var_2 + 44)] = 0f32
- compute_5[(cse_var_2 + 45)] = 0f32
- compute_5[(cse_var_2 + 46)] = 0f32
- compute_5[(cse_var_2 + 47)] = 0f32
- compute_5[(cse_var_2 + 64)] = 0f32
- compute_5[(cse_var_2 + 65)] = 0f32
- compute_5[(cse_var_2 + 66)] = 0f32
- compute_5[(cse_var_2 + 67)] = 0f32
- compute_5[(cse_var_2 + 68)] = 0f32
- compute_5[(cse_var_2 + 69)] = 0f32
- compute_5[(cse_var_2 + 70)] = 0f32
- compute_5[(cse_var_2 + 71)] = 0f32
- compute_5[(cse_var_2 + 72)] = 0f32
- compute_5[(cse_var_2 + 73)] = 0f32
- compute_5[(cse_var_2 + 74)] = 0f32
- compute_5[(cse_var_2 + 75)] = 0f32
- compute_5[(cse_var_2 + 76)] = 0f32
- compute_5[(cse_var_2 + 77)] = 0f32
- compute_5[(cse_var_2 + 78)] = 0f32
- compute_5[(cse_var_2 + 79)] = 0f32
- compute_5[(cse_var_2 + 96)] = 0f32
- compute_5[(cse_var_2 + 97)] = 0f32
- compute_5[(cse_var_2 + 98)] = 0f32
- compute_5[(cse_var_2 + 99)] = 0f32
- compute_5[(cse_var_2 + 100)] = 0f32
- compute_5[(cse_var_2 + 101)] = 0f32
- compute_5[(cse_var_2 + 102)] = 0f32
- compute_5[(cse_var_2 + 103)] = 0f32
- compute_5[(cse_var_2 + 104)] = 0f32
- compute_5[(cse_var_2 + 105)] = 0f32
- compute_5[(cse_var_2 + 106)] = 0f32
- compute_5[(cse_var_2 + 107)] = 0f32
- compute_5[(cse_var_2 + 108)] = 0f32
- compute_5[(cse_var_2 + 109)] = 0f32
- compute_5[(cse_var_2 + 110)] = 0f32
- compute_5[(cse_var_2 + 111)] = 0f32
- compute_5[(cse_var_2 + 128)] = 0f32
- compute_5[(cse_var_2 + 129)] = 0f32
- compute_5[(cse_var_2 + 130)] = 0f32
- compute_5[(cse_var_2 + 131)] = 0f32
- compute_5[(cse_var_2 + 132)] = 0f32
- compute_5[(cse_var_2 + 133)] = 0f32
- compute_5[(cse_var_2 + 134)] = 0f32
- compute_5[(cse_var_2 + 135)] = 0f32
- compute_5[(cse_var_2 + 136)] = 0f32
- compute_5[(cse_var_2 + 137)] = 0f32
- compute_5[(cse_var_2 + 138)] = 0f32
- compute_5[(cse_var_2 + 139)] = 0f32
- compute_5[(cse_var_2 + 140)] = 0f32
- compute_5[(cse_var_2 + 141)] = 0f32
- compute_5[(cse_var_2 + 142)] = 0f32
- compute_5[(cse_var_2 + 143)] = 0f32
- compute_5[(cse_var_2 + 160)] = 0f32
- compute_5[(cse_var_2 + 161)] = 0f32
- compute_5[(cse_var_2 + 162)] = 0f32
- compute_5[(cse_var_2 + 163)] = 0f32
- compute_5[(cse_var_2 + 164)] = 0f32
- compute_5[(cse_var_2 + 165)] = 0f32
- compute_5[(cse_var_2 + 166)] = 0f32
- compute_5[(cse_var_2 + 167)] = 0f32
- compute_5[(cse_var_2 + 168)] = 0f32
- compute_5[(cse_var_2 + 169)] = 0f32
- compute_5[(cse_var_2 + 170)] = 0f32
- compute_5[(cse_var_2 + 171)] = 0f32
- compute_5[(cse_var_2 + 172)] = 0f32
- compute_5[(cse_var_2 + 173)] = 0f32
- compute_5[(cse_var_2 + 174)] = 0f32
- compute_5[(cse_var_2 + 175)] = 0f32
- compute_5[(cse_var_2 + 192)] = 0f32
- compute_5[(cse_var_2 + 193)] = 0f32
- compute_5[(cse_var_2 + 194)] = 0f32
- compute_5[(cse_var_2 + 195)] = 0f32
- compute_5[(cse_var_2 + 196)] = 0f32
- compute_5[(cse_var_2 + 197)] = 0f32
- compute_5[(cse_var_2 + 198)] = 0f32
- compute_5[(cse_var_2 + 199)] = 0f32
- compute_5[(cse_var_2 + 200)] = 0f32
- compute_5[(cse_var_2 + 201)] = 0f32
- compute_5[(cse_var_2 + 202)] = 0f32
- compute_5[(cse_var_2 + 203)] = 0f32
- compute_5[(cse_var_2 + 204)] = 0f32
- compute_5[(cse_var_2 + 205)] = 0f32
- compute_5[(cse_var_2 + 206)] = 0f32
- compute_5[(cse_var_2 + 207)] = 0f32
- compute_5[(cse_var_2 + 224)] = 0f32
- compute_5[(cse_var_2 + 225)] = 0f32
- compute_5[(cse_var_2 + 226)] = 0f32
- compute_5[(cse_var_2 + 227)] = 0f32
- compute_5[(cse_var_2 + 228)] = 0f32
- compute_5[(cse_var_2 + 229)] = 0f32
- compute_5[(cse_var_2 + 230)] = 0f32
- compute_5[(cse_var_2 + 231)] = 0f32
- compute_5[(cse_var_2 + 232)] = 0f32
- compute_5[(cse_var_2 + 233)] = 0f32
- compute_5[(cse_var_2 + 234)] = 0f32
- compute_5[(cse_var_2 + 235)] = 0f32
- compute_5[(cse_var_2 + 236)] = 0f32
- compute_5[(cse_var_2 + 237)] = 0f32
- compute_5[(cse_var_2 + 238)] = 0f32
- compute_5[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- let cse_var_131: int32 = (cse_var_2 + 143)
- let cse_var_130: int32 = (cse_var_2 + 15)
- let cse_var_129: int32 = (cse_var_2 + 160)
- let cse_var_128: int32 = (cse_var_2 + 161)
- let cse_var_127: int32 = (cse_var_2 + 162)
- let cse_var_126: int32 = (cse_var_2 + 163)
- let cse_var_125: int32 = (cse_var_2 + 164)
- let cse_var_124: int32 = (cse_var_2 + 165)
- let cse_var_123: int32 = (cse_var_2 + 166)
- let cse_var_122: int32 = (cse_var_2 + 167)
- let cse_var_121: int32 = (cse_var_2 + 168)
- let cse_var_120: int32 = (cse_var_2 + 169)
- let cse_var_119: int32 = (cse_var_2 + 170)
- let cse_var_118: int32 = (cse_var_2 + 171)
- let cse_var_117: int32 = (cse_var_2 + 172)
- let cse_var_116: int32 = (cse_var_2 + 1)
- let cse_var_115: int32 = (cse_var_2 + 174)
- let cse_var_114: int32 = (cse_var_2 + 175)
- let cse_var_113: int32 = (cse_var_2 + 192)
- let cse_var_112: int32 = (cse_var_2 + 193)
- let cse_var_111: int32 = (cse_var_2 + 194)
- let cse_var_110: int32 = (cse_var_2 + 195)
- let cse_var_109: int32 = (cse_var_2 + 196)
- let cse_var_108: int32 = (cse_var_2 + 197)
- let cse_var_107: int32 = (cse_var_2 + 198)
- let cse_var_106: int32 = (cse_var_2 + 199)
- let cse_var_105: int32 = (cse_var_2 + 2)
- let cse_var_104: int32 = (cse_var_2 + 200)
- let cse_var_103: int32 = (cse_var_2 + 201)
- let cse_var_102: int32 = (cse_var_2 + 202)
- let cse_var_101: int32 = (cse_var_2 + 203)
- let cse_var_100: int32 = (cse_var_2 + 173)
- let cse_var_99: int32 = (cse_var_2 + 10)
- let cse_var_98: int32 = (cse_var_2 + 100)
- let cse_var_97: int32 = (cse_var_2 + 101)
- let cse_var_96: int32 = (cse_var_2 + 102)
- let cse_var_95: int32 = (cse_var_2 + 103)
- let cse_var_94: int32 = (cse_var_2 + 104)
- let cse_var_93: int32 = (cse_var_2 + 105)
- let cse_var_92: int32 = (cse_var_2 + 106)
- let cse_var_91: int32 = (cse_var_2 + 107)
- let cse_var_90: int32 = (cse_var_2 + 108)
- let cse_var_89: int32 = (cse_var_2 + 109)
- let cse_var_88: int32 = (cse_var_2 + 11)
- let cse_var_87: int32 = (cse_var_2 + 110)
- let cse_var_86: int32 = (cse_var_2 + 111)
- let cse_var_85: int32 = (cse_var_2 + 12)
- let cse_var_84: int32 = (cse_var_2 + 142)
- let cse_var_83: int32 = (cse_var_2 + 129)
- let cse_var_82: int32 = (cse_var_2 + 13)
- let cse_var_81: int32 = (cse_var_2 + 130)
- let cse_var_80: int32 = (cse_var_2 + 131)
- let cse_var_79: int32 = (cse_var_2 + 132)
- let cse_var_78: int32 = (cse_var_2 + 133)
- let cse_var_77: int32 = (cse_var_2 + 134)
- let cse_var_76: int32 = (cse_var_2 + 135)
- let cse_var_75: int32 = (cse_var_2 + 136)
- let cse_var_74: int32 = (cse_var_2 + 137)
- let cse_var_73: int32 = (cse_var_2 + 138)
- let cse_var_72: int32 = (cse_var_2 + 139)
- let cse_var_71: int32 = (cse_var_2 + 14)
- let cse_var_70: int32 = (cse_var_2 + 140)
- let cse_var_69: int32 = (cse_var_2 + 141)
- let cse_var_68: int32 = (cse_var_2 + 128)
- let cse_var_67: int32 = (cse_var_2 + 43)
- let cse_var_66: int32 = (cse_var_2 + 44)
- let cse_var_65: int32 = (cse_var_2 + 45)
- let cse_var_64: int32 = (cse_var_2 + 46)
- let cse_var_63: int32 = (cse_var_2 + 47)
- let cse_var_62: int32 = (cse_var_2 + 5)
- let cse_var_61: int32 = (cse_var_2 + 6)
- let cse_var_60: int32 = (cse_var_2 + 64)
- let cse_var_59: int32 = (cse_var_2 + 65)
- let cse_var_58: int32 = (cse_var_2 + 66)
- let cse_var_57: int32 = (cse_var_2 + 67)
- let cse_var_56: int32 = (cse_var_2 + 68)
- let cse_var_55: int32 = (cse_var_2 + 69)
- let cse_var_54: int32 = (cse_var_2 + 7)
- let cse_var_53: int32 = (cse_var_2 + 70)
- let cse_var_52: int32 = (cse_var_2 + 42)
- let cse_var_51: int32 = (cse_var_2 + 72)
- let cse_var_50: int32 = (cse_var_2 + 73)
- let cse_var_49: int32 = (cse_var_2 + 74)
- let cse_var_48: int32 = (cse_var_2 + 75)
- let cse_var_47: int32 = (cse_var_2 + 76)
- let cse_var_46: int32 = (cse_var_2 + 77)
- let cse_var_45: int32 = (cse_var_2 + 78)
- let cse_var_44: int32 = (cse_var_2 + 79)
- let cse_var_43: int32 = (cse_var_2 + 8)
- let cse_var_42: int32 = (cse_var_2 + 9)
- let cse_var_41: int32 = (cse_var_2 + 96)
- let cse_var_40: int32 = (cse_var_2 + 97)
- let cse_var_39: int32 = (cse_var_2 + 98)
- let cse_var_38: int32 = (cse_var_2 + 99)
- let cse_var_37: int32 = (elem_idx*16)
- let cse_var_36: int32 = (cse_var_2 + 71)
- let cse_var_35: int32 = (cse_var_2 + 204)
- let cse_var_34: int32 = (cse_var_2 + 206)
- let cse_var_33: int32 = (cse_var_2 + 207)
- let cse_var_32: int32 = (cse_var_2 + 224)
- let cse_var_31: int32 = (cse_var_2 + 225)
- let cse_var_30: int32 = (cse_var_2 + 226)
- let cse_var_29: int32 = (cse_var_2 + 227)
- let cse_var_28: int32 = (cse_var_2 + 228)
- let cse_var_27: int32 = (cse_var_2 + 229)
- let cse_var_26: int32 = (cse_var_2 + 230)
- let cse_var_25: int32 = (cse_var_2 + 231)
- let cse_var_24: int32 = (cse_var_2 + 232)
- let cse_var_23: int32 = (cse_var_2 + 233)
- let cse_var_22: int32 = (cse_var_2 + 234)
- let cse_var_21: int32 = (cse_var_2 + 235)
- let cse_var_20: int32 = (cse_var_2 + 236)
- let cse_var_19: int32 = (cse_var_2 + 205)
- let cse_var_18: int32 = (cse_var_2 + 40)
- let cse_var_17: int32 = (cse_var_2 + 4)
- let cse_var_16: int32 = (cse_var_2 + 39)
- let cse_var_15: int32 = (cse_var_2 + 38)
- let cse_var_14: int32 = (cse_var_2 + 37)
- let cse_var_13: int32 = (cse_var_2 + 36)
- let cse_var_12: int32 = (cse_var_2 + 35)
- let cse_var_11: int32 = (cse_var_2 + 34)
- let cse_var_10: int32 = (cse_var_2 + 33)
- let cse_var_9: int32 = (cse_var_2 + 32)
- let cse_var_8: int32 = (cse_var_2 + 3)
- let cse_var_7: int32 = (cse_var_2 + 239)
- let cse_var_6: int32 = (cse_var_2 + 238)
- let cse_var_5: int32 = (cse_var_2 + 41)
- let cse_var_4: int32 = (cse_var_2 + 237)
- let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*2048)
- {
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ 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, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_132, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -1039,7 +664,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.721 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.511 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 f93abf7cb..49b9191b0 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>00:44.648</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.040</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.755</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.235</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.223</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>00:00.218</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.216</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>00:44.112</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>00:00.242</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>00:00.234</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:00.227</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>00:00.225</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>
</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 031e7acfb..f523ec394 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 43.38/43.38 result: MeasureResult(costs=(0.005336062894736842,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.565807819366455, timestamp=1651281447.9343586) [('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: 0.00/43.38 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.32/42.32 result: MeasureResult(costs=(0.005470518157894737,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5970234870910645, timestamp=1651292876.677573) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.32 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: 0.00/43.38 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: 0.00/43.38 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/43.38 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.32 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: 0x00007f2abf079fa2
+ 12: 0x00007f49a9b12fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.39/144.39 result: MeasureResult(costs=(0.00160325892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4100971221923828, timestamp=1651281474.2659922) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 144.33/144.33 result: MeasureResult(costs=(0.0016039419599999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4381542205810547, timestamp=1651292902.5259576) [('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: 0.001989
+Time cost of this operator: 0.002008
</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 651a32e36..4963d8b6b 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.1 98.716 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.138 0.989 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
-Total_time - 317.174 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.8 98.739 (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 0.943 0.296 (1, 1, 10, 10, 3) 1 1
+Total_time - 318.819 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.05 96.807 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.104 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.089 (1, 1, 10, 10, 3) 1 1
-Total_time - 82.691 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 154.9 98.331 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.71 1.086 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.584 (1, 1, 10, 10, 3) 1 1
+Total_time - 157.529 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 24cf3628e..6de7a3c89 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.818</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:45.802</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:39.780</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>00:03.439</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>00:00.204</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.198</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</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>00:41.483</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>00:03.668</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>00:00.219</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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.218</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:00.214</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
</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 ff9772a52..b2cd5e68e 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>00:08.903</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.886</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:07.037</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>00:01.660</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>00:00.207</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:07.644</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>00:02.009</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>00:00.233</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 804cc40d4..bc27f4b40 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>00:05.706</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.206</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.112</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>00:01.121</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>00:00.735</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>00:00.725</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.310</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.244</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>00:00.236</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>00:00.224</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>00:02.259</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>00:01.296</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>00:00.782</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>00:00.772</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>00:00.340</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>00:00.260</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>00:00.254</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>00:00.244</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 6766b9b77..97f5a2956 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/tmpw_oz188a/input0.cc'\nsource_filename = \"/tmp/tmpw_oz188a/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/tmpqfxjyvxy/input0.cc'\nsource_filename = \"/tmp/tmpqfxjyvxy/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/arg__info_8h_source.html b/docs/reference/api/doxygen/arg__info_8h_source.html
index 6e5146171..4440c35c6 100644
--- a/docs/reference/api/doxygen/arg__info_8h_source.html
+++ b/docs/reference/api/doxygen/arg__info_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfo_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfo.html">tvm::meta_schedule::TensorInfo</a></div><div class="ttdoc">Managed reference to TensorInfoNode. </div><div class="ttdef"><b>Definition:</b> arg_info.h:91</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfoNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html">tvm::meta_schedule::TensorInfoNode</a></div><div class="ttdoc">The tensor argument information. </div><div class="ttdef"><b>Definition:</b> arg_info.h:68</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfoNode_html_ab54cd62d85a051b78c9605ac0d2d3cb7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html#ab54cd62d85a051b78c9605ac0d2d3cb7">tvm::meta_schedule::TensorInfoNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> arg_info.h:75</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</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="classtvm_1_1meta__schedule_1_1TensorInfoNode_html_a703cc684f922c4c7dddb20a503a78eb9"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html#a703cc684f922c4c7dddb20a503a78eb9">tvm::meta_schedule::TensorInfoNode::dtype</a></div><div class="ttdeci">runtime::DataType dtype</div><div class="ttdoc">The data type of the tensor. </div><div class="ttdef"><b>Definition:</b> arg_info.h:71</div></div>
<div class="ttc" id="shape__tuple_8h_html"><div class="ttname"><a href="shape__tuple_8h.html">shape_tuple.h</a></div><div class="ttdoc">Runtime ShapeTuple container types. </div></div>
diff --git a/docs/reference/api/doxygen/bytecode_8h_source.html b/docs/reference/api/doxygen/bytecode_8h_source.html
index 629bae7bf..66ef787e8 100644
--- a/docs/reference/api/doxygen/bytecode_8h_source.html
+++ b/docs/reference/api/doxygen/bytecode_8h_source.html
@@ -111,7 +111,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a46879dbe84105fb621a6167f8d73b223"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a46879dbe84105fb621a6167f8d73b223">tvm::runtime::vm::Instruction::target</a></div><div class="ttdeci">RegName target</div><div class="ttdoc">The register containing the target value. </div><div class="ttdef"><b>Definition:</b> bytecode.h:143</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a360b264ed892e620935b648e5a91a5ea"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a360b264ed892e620935b648e5a91a5ea">tvm::runtime::vm::Instruction::arity</a></div><div class="ttdeci">Index arity</div><div class="ttdoc">The arity of the packed function. </div><div class="ttdef"><b>Definition:</b> bytecode.h:133</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a3a175836bc0893d99935f32911e45bfd"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3a175836bc0893d99935f32911e45bfd">tvm::runtime::vm::Instruction::closure</a></div><div class="ttdeci">RegName closure</div><div class="ttdoc">The register containing the closure. </div><div class="ttdef"><b>Definition:</b> bytecode.h:115</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a3412cabd3b4f42f106f56fc22257f6ca"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3412cabd3b4f42f106f56fc22257f6ca">tvm::runtime::vm::Instruction::storage</a></div><div class="ttdeci">RegName storage</div><div class="ttdoc">The storage to allocate from. </div><div class="ttdef"><b>Definition:</b> bytecode.h:93</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1vm_html_a3597867d2db714bf760876a23d6b7d3d"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">tvm::runtime::vm::Index</a></div><div class="ttdeci">int64_t Index</div><div class="ttdoc">An alias for the integer type used ubiquitously in the VM. </div><div class="ttdef"><b>Definition:</b> bytecode.h:43</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a5d98a3b5b50e6fa9029d05f741c0bce9"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a5d98a3b5b50e6fa9029d05f741c0bce9">tvm::runtime::vm::Instruction::num_args</a></div><div class="ttdeci">Index num_args</div><div class="ttdoc">The number of arguments to the function. </div><div class="ttdef"><b>Definition:</b> bytecode.h:153</div></div>
diff --git a/docs/reference/api/doxygen/c__runtime__api_8h_source.html b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
index 59dcfc50a..19d6daabc 100644
--- a/docs/reference/api/doxygen/c__runtime__api_8h_source.html
+++ b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
@@ -126,7 +126,7 @@ $(function() {
<div class="ttc" id="c__runtime__api_8h_html_ae690840d1af9c7b0fe5b9b457456f60d"><div class="ttname"><a href="c__runtime__api_8h.html#ae690840d1af9c7b0fe5b9b457456f60d">TVMArrayToDLPack</a></div><div class="ttdeci">int TVMArrayToDLPack(TVMArrayHandle from, DLManagedTensor **out)</div><div class="ttdoc">Produce a DLMangedTensor from the array that shares data memory with the array. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a6cd1076476117e74454f67931c2da1d4"><div class="ttname"><a href="c__runtime__api_8h.html#a6cd1076476117e74454f67931c2da1d4">TVMRetValueHandle</a></div><div class="ttdeci">void * TVMRetValueHandle</div><div class="ttdoc">Handle to hold return value. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:167</div></div>
<div class="ttc" id="c__runtime__api_8h_html_acf57d257a6e0841d84ebbd2a339d183e"><div class="ttname"><a href="c__runtime__api_8h.html#acf57d257a6e0841d84ebbd2a339d183e">TVMFunctionHandle</a></div><div class="ttdeci">void * TVMFunctionHandle</div><div class="ttdoc">Handle to packed function handle. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:165</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ace8007daffd9f2c6d954c24d870bfcc4"><div class="ttname"><a href="c__runtime__api_8h.html#ace8007daffd9f2c6d954c24d870bfcc4">tvm_index_t</a></div><div class="ttdeci">int64_t tvm_index_t</div><div class="ttdoc">type of array index. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:81</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a190e81769e805cca153514137a66e793a9387f774bc8453afe4aa4cd17789a405"><div class="ttname"><a href="c__runtime__api_8h.html#a190e81769e805cca153514137a66e793a9387f774bc8453afe4aa4cd17789a405">kTVMOpaqueHandle</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:113</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ae899a6a211b7913e92420a01b804db64"><div class="ttname"><a href="c__runtime__api_8h.html#ae899a6a211b7913e92420a01b804db64">TVMObjectRetain</a></div><div class="ttdeci">int TVMObjectRetain(TVMObjectHandle obj)</div><div class="ttdoc">Increase the reference count of an object. </div></div>
diff --git a/docs/reference/api/doxygen/data__layout_8h_source.html b/docs/reference/api/doxygen/data__layout_8h_source.html
index 9f31861c5..16c30d28d 100644
--- a/docs/reference/api/doxygen/data__layout_8h_source.html
+++ b/docs/reference/api/doxygen/data__layout_8h_source.html
@@ -94,7 +94,7 @@ $(function() {
<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="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="classtvm_1_1tir_1_1Layout_html_a7fd4348d39ad4249daf89d54195fa65a"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a7fd4348d39ad4249daf89d54195fa65a">tvm::tir::Layout::ndim</a></div><div class="ttdeci">size_t ndim() const</div><div class="ttdef"><b>Definition:</b> data_layout.h:178</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BijectiveLayoutNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BijectiveLayoutNode.html">tvm::tir::BijectiveLayoutNode</a></div><div class="ttdef"><b>Definition:</b> data_layout.h:293</div></div>
<div class="ttc" id="namespacetvm_1_1te_html_ae0c71f84710b436cbe0b32289d0838f4"><div class="ttname"><a href="namespacetvm_1_1te.html#ae0c71f84710b436cbe0b32289d0838f4">tvm::te::var</a></div><div class="ttdeci">Var var(std::string name_hint, DataType t=DataType::Int(32))</div><div class="ttdoc">Construct a new Var expression. </div></div>
diff --git a/docs/reference/api/doxygen/dataflow__pattern_8h_source.html b/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
index 0bc591273..c52622c09 100644
--- a/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
+++ b/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
@@ -128,7 +128,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1relay_html_a3834130d66634d032f8e9bffafbe09ad"><div class="ttname"><a href="namespacetvm_1_1relay.html#a3834130d66634d032f8e9bffafbe09ad">tvm::relay::IsTuple</a></div><div class="ttdeci">DFPattern IsTuple(const Array< DFPattern > &fields)</div><div class="ttdoc">Syntatic Sugar for creating a TuplePattern. </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="classtvm_1_1relay_1_1FunctionPatternNode_html_a5e831242707df5d59474816c416abe97"><div class="ttname"><a href="classtvm_1_1relay_1_1FunctionPatternNode.html#a5e831242707df5d59474816c416abe97">tvm::relay::FunctionPatternNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> dataflow_pattern.h:201</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1RelayExpr_html"><div class="ttname"><a href="classtvm_1_1RelayExpr.html">tvm::RelayExpr</a></div><div class="ttdoc">Managed reference to RelayExprNode. </div><div class="ttdef"><b>Definition:</b> expr.h:217</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1ConstantPatternNode_html"><div class="ttname"><a href="classtvm_1_1relay_1_1ConstantPatternNode.html">tvm::relay::ConstantPatternNode</a></div><div class="ttdoc">Container for Constant. </div><div class="ttdef"><b>Definition:</b> dataflow_pattern.h:138</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
diff --git a/docs/reference/api/doxygen/detail_2broadcast_8h_source.html b/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
index 651236ee6..9df6252b5 100644
--- a/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
@@ -77,7 +77,7 @@ $(function() {
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_ae8c7db788e840dc1c2ed1f365d5ea829"><div class="ttname"><a href="namespacetvm_1_1tir.html#ae8c7db788e840dc1c2ed1f365d5ea829">tvm::tir::IntImmNode</a></div><div class="ttdeci">tvm::IntImmNode IntImmNode</div><div class="ttdef"><b>Definition:</b> expr.h:49</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_aed3f57cf8d1c3546f075701898c5b70f"><div class="ttname"><a href="namespacetvm_1_1tir.html#aed3f57cf8d1c3546f075701898c5b70f">tvm::tir::make_zero</a></div><div class="ttdeci">PrimExpr make_zero(DataType t, Span span=Span())</div><div class="ttdoc">Make a const zero expr. </div><div class="ttdef"><b>Definition:</b> op.h:1152</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html">tvm::te::Tensor</a></div><div class="ttdoc">Tensor structure representing a possible input, or intermediate computation result. </div><div class="ttdef"><b>Definition:</b> tensor.h:102</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_ae9734c8e6324f9be27fce8d45d0aa6f4"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#ae9734c8e6324f9be27fce8d45d0aa6f4">tvm::runtime::Array::begin</a></div><div class="ttdeci">iterator begin() const</div><div class="ttdef"><b>Definition:</b> array.h:366</div></div>
diff --git a/docs/reference/api/doxygen/detail_2extern_8h_source.html b/docs/reference/api/doxygen/detail_2extern_8h_source.html
index cb2848ef1..754f18115 100644
--- a/docs/reference/api/doxygen/detail_2extern_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2extern_8h_source.html
@@ -74,7 +74,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_aebad9f7235dd20af649fb5c2113797b8"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#aebad9f7235dd20af649fb5c2113797b8">tvm::runtime::DataType::Handle</a></div><div class="ttdeci">static DataType Handle(int bits=64, int lanes=1)</div><div class="ttdoc">Construct a handle type. </div><div class="ttdef"><b>Definition:</b> data_type.h:188</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a28f99e6dd767482765b854ee9fc71f2c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a28f99e6dd767482765b854ee9fc71f2c">tvm::tir::builtin::tvm_stack_make_array</a></div><div class="ttdeci">const Op & tvm_stack_make_array()</div><div class="ttdoc">Allocate a NDArray(DLTensor) on stack, return the handle. </div></div>
<div class="ttc" id="classtvm_1_1te_1_1ExternOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ExternOp.html">tvm::te::ExternOp</a></div><div class="ttdoc">Managed reference to ExternOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:460</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_abd540cb73407771ecfb4f78722ce5a1b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#abd540cb73407771ecfb4f78722ce5a1b">tvm::tir::builtin::tvm_stack_make_shape</a></div><div class="ttdeci">const Op & tvm_stack_make_shape()</div><div class="ttdoc">Allocate a shape tuple on stack, return the handle. </div></div>
<div class="ttc" id="namespacetvm_1_1te_html_ae0c71f84710b436cbe0b32289d0838f4"><div class="ttname"><a href="namespacetvm_1_1te.html#ae0c71f84710b436cbe0b32289d0838f4">tvm::te::var</a></div><div class="ttdeci">Var var(std::string name_hint, DataType t=DataType::Int(32))</div><div class="ttdoc">Construct a new Var expression. </div></div>
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
diff --git a/docs/reference/api/doxygen/device__api_8h_source.html b/docs/reference/api/doxygen/device__api_8h_source.html
index 58c01f2fc..ad51f8fdb 100644
--- a/docs/reference/api/doxygen/device__api_8h_source.html
+++ b/docs/reference/api/doxygen/device__api_8h_source.html
@@ -94,7 +94,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619adff7742765a9f6f50973675bf34ad264"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619adff7742765a9f6f50973675bf34ad264">tvm::runtime::kMaxSharedMemoryPerBlock</a></div><div class="ttdef"><b>Definition:</b> device_api.h:42</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619a90ebfaf325917db841553c65ce2ae630"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619a90ebfaf325917db841553c65ce2ae630">tvm::runtime::kMaxClockRate</a></div><div class="ttdef"><b>Definition:</b> device_api.h:45</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619a100cda550bad77fbaf993566c022bdf9"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619a100cda550bad77fbaf993566c022bdf9">tvm::runtime::kDriverVersion</a></div><div class="ttdef"><b>Definition:</b> device_api.h:51</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619aa707ea3fd97e625364ad60daa89be2da"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619aa707ea3fd97e625364ad60daa89be2da">tvm::runtime::kWarpSize</a></div><div class="ttdef"><b>Definition:</b> device_api.h:41</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619ad7ca96c2095b4670de00ee1d0ca79201"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619ad7ca96c2095b4670de00ee1d0ca79201">tvm::runtime::kGcnArch</a></div><div class="ttdef"><b>Definition:</b> device_api.h:49</div></div>
diff --git a/docs/reference/api/doxygen/einsum_8h_source.html b/docs/reference/api/doxygen/einsum_8h_source.html
index b39d89c28..d64da9e5a 100644
--- a/docs/reference/api/doxygen/einsum_8h_source.html
+++ b/docs/reference/api/doxygen/einsum_8h_source.html
@@ -88,7 +88,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a830eee18b651d35c1b5fc972f611fcec"><div class="ttname"><a href="namespacetvm_1_1topi.html#a830eee18b651d35c1b5fc972f611fcec">tvm::topi::GetCombinedDimsView</a></div><div class="ttdeci">void GetCombinedDimsView(const Tensor &op, int iop, char *labels, Array< PrimExpr > *newshape, Array< PrimExpr > *newstride)</div><div class="ttdoc">If any dimensions are combined, create a view that combines them. Shows in newshape and newstri [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a9a9498e3d8d11a6f68faa9c43f055646"><div class="ttname"><a href="namespacetvm_1_1topi.html#a9a9498e3d8d11a6f68faa9c43f055646">tvm::topi::ParseOperandSubscripts</a></div><div class="ttdeci">int ParseOperandSubscripts(const char *subscripts, int length, int ndim, int iop, char *op_labels, char *label_counts, int *min_label, int *max_label)</div><div class="ttdoc">Parse the subscripts for one operand into an output of &#39;ndim&#39; labe [...]
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_afb771a1ebb231df6e61e22ce933ba40d"><div class="ttname"><a href="namespacetvm_1_1topi.html#afb771a1ebb231df6e61e22ce933ba40d">tvm::topi::ParseEinsumInput</a></div><div class="ttdeci">std::tuple< std::string, std::string > ParseEinsumInput(std::string subscripts, const std::vector< Array< PrimExpr >> &operands)</div><div class="ttdoc">Parse the input subscripts into a vector of strings. </div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html">tvm::te::Tensor</a></div><div class="ttdoc">Tensor structure representing a possible input, or intermediate computation result. </div><div class="ttdef"><b>Definition:</b> tensor.h:102</div></div>
diff --git a/docs/reference/api/doxygen/elemwise_8h_source.html b/docs/reference/api/doxygen/elemwise_8h_source.html
index 8b98260e2..2391c05e1 100644
--- a/docs/reference/api/doxygen/elemwise_8h_source.html
+++ b/docs/reference/api/doxygen/elemwise_8h_source.html
@@ -110,7 +110,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a99f3fd2edfd74113c83bc9fb98e8aca1"><div class="ttname"><a href="namespacetvm_1_1topi.html#a99f3fd2edfd74113c83bc9fb98e8aca1">tvm::topi::bitwise_not</a></div><div class="ttdeci">Tensor bitwise_not(const Tensor &x, std::string name="T_bitwise_not", std::string tag=kElementWise)</div><div class="ttdoc">Creates an operation that returns the bitwise NOT of a given tensor. </div><div class="ttdef"><b>Definition:</b> elemwise.h:196</d [...]
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_aec153e599d33c78a7592007cde1c02cb"><div class="ttname"><a href="namespacetvm_1_1topi.html#aec153e599d33c78a7592007cde1c02cb">tvm::topi::tanh</a></div><div class="ttdeci">Tensor tanh(const Tensor &x, std::string name="T_" "tanh", std::string tag=kElementWise)</div><div class="ttdef"><b>Definition:</b> elemwise.h:73</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a188f69f0e65e2efb4914e458db50b3d8"><div class="ttname"><a href="namespacetvm_1_1topi.html#a188f69f0e65e2efb4914e458db50b3d8">tvm::topi::fast_erf_float32</a></div><div class="ttdeci">Tensor fast_erf_float32(const Tensor &data, std::string name, std::string tag)</div><div class="ttdoc">Fast_erf_float expression from Eigen. </div><div class="ttdef"><b>Definition:</b> elemwise.h:509</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a472208fa01448c0ed649bec218eed7f9"><div class="ttname"><a href="namespacetvm_1_1topi.html#a472208fa01448c0ed649bec218eed7f9">tvm::topi::acos</a></div><div class="ttdeci">Tensor acos(const Tensor &x, std::string name="T_" "acos", std::string tag=kElementWise)</div><div class="ttdef"><b>Definition:</b> elemwise.h:66</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a25239505894bdae140e53f4abc146f92"><div class="ttname"><a href="namespacetvm_1_1topi.html#a25239505894bdae140e53f4abc146f92">tvm::topi::reinterpret</a></div><div class="ttdeci">Tensor reinterpret(const Tensor &x, DataType type, std::string name="tensor", std::string tag=kElementWise)</div><div class="ttdoc">Reinterpret each element of x to the given type. </div><div class="ttdef"><b>Definition:</b> elemwise.h:309</div></div>
diff --git a/docs/reference/api/doxygen/functions_a.html b/docs/reference/api/doxygen/functions_a.html
index 1bd79f081..f4c59ea88 100644
--- a/docs/reference/api/doxygen/functions_a.html
+++ b/docs/reference/api/doxygen/functions_a.html
@@ -221,6 +221,9 @@ $(function() {
<li>allow_copy_on_write_
: <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">tvm::tir::StmtMutator</a>
</li>
+<li>allowzero
+: <a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930">tvm::relay::ReshapeAttrs</a>
+</li>
<li>alpha
: <a class="el" href="structtvm_1_1relay_1_1LeakyReluAttrs.html#a78576f4cbcc1139b98c4fc00b99d0e07">tvm::relay::LeakyReluAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1LRNAttrs.html#a76f869f2e2c27773e73744ac05bd3d1e">tvm::relay::LRNAttrs</a>
@@ -354,7 +357,7 @@ $(function() {
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a360b264ed892e620935b648e5a91a5ea">tvm::runtime::vm::Instruction</a>
</li>
<li>Array()
-: <a class="el" href="classtvm_1_1runtime_1_1Array.html#a478af2e3338db97bf9dd3411de6d9a8a">tvm::runtime::Array< T, typename ></a>
+: <a class="el" href="classtvm_1_1runtime_1_1Array.html#aacdeb14d66a7f85e94ee843c459f7959">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ArrayNode.html#a23070656da6784a7e4c33c4b0ea9de35">tvm::runtime::ArrayNode</a>
</li>
<li>array
@@ -419,7 +422,7 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a7fbfe0e01b0fa54e151bd481956dcfec">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1MapNode.html#a49edd4ddc34a4e0b097c34560b9b3b4e">tvm::runtime::MapNode</a>
, <a class="el" href="classtvm_1_1runtime_1_1ShapeTuple.html#a07d50937020663f46ce9b1f31f066a7a">tvm::runtime::ShapeTuple</a>
-, <a class="el" href="classtvm_1_1runtime_1_1SmallMapNode.html#a0593c84ceb05afb1a3f87045a3dc3a59">tvm::runtime::SmallMapNode</a>
+, <a class="el" href="classtvm_1_1runtime_1_1SmallMapNode.html#a866679f23f724edc2d165f530f058b09">tvm::runtime::SmallMapNode</a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#aaeda6a88310d41a22ce884fb1570b0d2">tvm::runtime::String</a>
</li>
<li>attach_ivar
@@ -444,7 +447,7 @@ $(function() {
: <a class="el" href="structtvm_1_1AttrError.html#a3285db0171872bc2fdde8243f6e801d9">tvm::AttrError</a>
</li>
<li>AttrInitEntry()
-: <a class="el" href="structtvm_1_1detail_1_1AttrInitEntry.html#af07c4a3a8f4663ac03ae238ab7b9d791">tvm::detail::AttrInitEntry< T ></a>
+: <a class="el" href="structtvm_1_1detail_1_1AttrInitEntry.html#ad68ac350b0d49e97caab8443cc8fb08b">tvm::detail::AttrInitEntry< T ></a>
</li>
<li>AttrInitVisitor()
: <a class="el" href="classtvm_1_1detail_1_1AttrInitVisitor.html#ac3c800c9249fee195db2a5fa473fe960">tvm::detail::AttrInitVisitor< FFind ></a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index 5fde19631..07b41b291 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -981,7 +981,7 @@ $(function() {
: <a class="el" href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a5882f7eda112e825eb5a87e45aeb85b0">tvm::runtime::TVMArgsSetter</a>
</li>
<li>TVMArgValue()
-: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a5fbd71750e5bbba6edc9094178af9276">tvm::runtime::TVMArgValue</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TVMArgValue.html#a987b2fb283cea5484d4655e3f711c046">tvm::runtime::TVMArgValue</a>
</li>
<li>TVMMovableArgValue_()
: <a class="el" href="classtvm_1_1runtime_1_1TVMMovableArgValue__.html#a8eca9048535541f374a5806f9648131b">tvm::runtime::TVMMovableArgValue_</a>
@@ -1022,7 +1022,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#afd8ee9dd9648c19b468bb4b0b00e8e4e">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a36ca0d1876544463ee848766e70e5e96">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
diff --git a/docs/reference/api/doxygen/functions_i.html b/docs/reference/api/doxygen/functions_i.html
index 867bfdf0d..9915eb3f1 100644
--- a/docs/reference/api/doxygen/functions_i.html
+++ b/docs/reference/api/doxygen/functions_i.html
@@ -554,7 +554,7 @@ $(function() {
<li>iterator
: <a class="el" href="classtvm_1_1runtime_1_1Array.html#a98e5ad633b8195d954c98067213ae29f">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#ad8b40ddeffccb6f221601eda70202f9a">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a75e3f2657cdb7cc613bf922429983165">tvm::runtime::MapNode::iterator</a>
+, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#ad605c9f9aaed23e669c2a3c595d08ba4">tvm::runtime::MapNode::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor.html#a79703afd52032715cc2d9d4c6830147f">tvm::runtime::metadata::ArrayAccessor< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor_3_01const_01char_01_5_00_01_1_1tvm_1_1runtime_1_1String_01_4.html#a3216d91ef7fb0771463e76c9a0afcd1c">tvm::runtime::metadata::ArrayAccessor< const char *, ::tvm::runtime::String ></a>
, <a class="el" href="classtvm_1_1support_1_1Span.html#af6fbb6a54a3ecf8673146acae0c8228b">tvm::support::Span< T, W ></a>
@@ -584,7 +584,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1IterVar.html#a1c0d6998203092c953b7da00f16c5c31">tvm::tir::IterVar</a>
</li>
<li>IterVarAttr()
-: <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#aa20680587a1c880b659063cd37ba4763">tvm::te::IterVarAttr</a>
+: <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#a5549479b7e3ce243d89b219b0dd7ef71">tvm::te::IterVarAttr</a>
</li>
<li>IterVarRelation()
: <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#a3e611ee0870d9a542b8deb79575dbf66">tvm::te::IterVarRelation</a>
diff --git a/docs/reference/api/doxygen/functions_m.html b/docs/reference/api/doxygen/functions_m.html
index f56ff9eb7..9e89a8991 100644
--- a/docs/reference/api/doxygen/functions_m.html
+++ b/docs/reference/api/doxygen/functions_m.html
@@ -296,7 +296,7 @@ $(function() {
: <a class="el" href="classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536">tvm::DiagnosticContextNode</a>
</li>
<li>Module()
-: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9">tvm::runtime::Module</a>
+: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4">tvm::runtime::Module</a>
, <a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d">tvm::runtime::ModuleNode</a>
</li>
<li>ModuleInternal
diff --git a/docs/reference/api/doxygen/functions_s.html b/docs/reference/api/doxygen/functions_s.html
index 67fe6e2f6..d725fc15f 100644
--- a/docs/reference/api/doxygen/functions_s.html
+++ b/docs/reference/api/doxygen/functions_s.html
@@ -1046,7 +1046,7 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1BufferNode.html#ac18ddd10b79a30ae57d3a8283686259d">tvm::tir::BufferNode</a>
</li>
<li>String()
-: <a class="el" href="classtvm_1_1runtime_1_1String.html#a02fca36e3ff55cc1e83635b02a11fca3">tvm::runtime::String</a>
+: <a class="el" href="classtvm_1_1runtime_1_1String.html#ac5d930b522e9fef9c07e51819d96d2f3">tvm::runtime::String</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj_1_1FromStd.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj::FromStd</a>
, <a class="el" href="classtvm_1_1runtime_1_1StringObj.html#a7fb804f7dc96dd9f705c84095f37f1ca">tvm::runtime::StringObj</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_t.html b/docs/reference/api/doxygen/functions_t.html
index acdd0e341..ec9a2f4cc 100644
--- a/docs/reference/api/doxygen/functions_t.html
+++ b/docs/reference/api/doxygen/functions_t.html
@@ -78,7 +78,7 @@ $(function() {
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a46879dbe84105fb621a6167f8d73b223">tvm::runtime::vm::Instruction</a>
</li>
<li>Target()
-: <a class="el" href="classtvm_1_1Target.html#ab825b350cf478bf948d807b6fdf636a0">tvm::Target</a>
+: <a class="el" href="classtvm_1_1Target.html#a77f3d7cc97d8cfd7172af58b4e784d89">tvm::Target</a>
</li>
<li>target
: <a class="el" href="classtvm_1_1VirtualDeviceNode.html#a8b2d427d9e21886ccaeaae5e9cc55aaf">tvm::VirtualDeviceNode</a>
@@ -1263,7 +1263,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8941c80982a1b2a289440f3c79bb0ac8">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0161d426f9ca366c860ad48c384f7192">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
diff --git a/docs/reference/api/doxygen/functions_vars_a.html b/docs/reference/api/doxygen/functions_vars_a.html
index bb73a9776..5d037d3bc 100644
--- a/docs/reference/api/doxygen/functions_vars_a.html
+++ b/docs/reference/api/doxygen/functions_vars_a.html
@@ -127,6 +127,9 @@ $(function() {
<li>allow_copy_on_write_
: <a class="el" href="classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f">tvm::tir::StmtMutator</a>
</li>
+<li>allowzero
+: <a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930">tvm::relay::ReshapeAttrs</a>
+</li>
<li>alpha
: <a class="el" href="structtvm_1_1relay_1_1LeakyReluAttrs.html#a78576f4cbcc1139b98c4fc00b99d0e07">tvm::relay::LeakyReluAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1LRNAttrs.html#a76f869f2e2c27773e73744ac05bd3d1e">tvm::relay::LRNAttrs</a>
diff --git a/docs/reference/api/doxygen/index__map_8h_source.html b/docs/reference/api/doxygen/index__map_8h_source.html
index 6eb60d198..68f34c02a 100644
--- a/docs/reference/api/doxygen/index__map_8h_source.html
+++ b/docs/reference/api/doxygen/index__map_8h_source.html
@@ -84,7 +84,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1IndexMapNode_html_aa3c9eafa0939e2f944ad55d2b27510b2"><div class="ttname"><a href="classtvm_1_1tir_1_1IndexMapNode.html#aa3c9eafa0939e2f944ad55d2b27510b2">tvm::tir::IndexMapNode::TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_FINAL_OBJECT_INFO(IndexMapNode, Object)</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="classtvm_1_1runtime_1_1TypedPackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TypedPackedFunc.html">tvm::runtime::TypedPackedFunc</a></div><div class="ttdoc">Please refer to TypedPackedFunc<R(Args..)>. </div><div class="ttdef"><b>Definition:</b> packed_func.h:60</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1IndexMapNode_html_a2b0b7e7ec70ab1264162e3550db1cf29"><div class="ttname"><a href="classtvm_1_1tir_1_1IndexMapNode.html#a2b0b7e7ec70ab1264162e3550db1cf29">tvm::tir::IndexMapNode::MapRanges</a></div><div class="ttdeci">Array< Range > MapRanges(const Array< Range > &ranges) const</div><div class="ttdoc">Map a memory range to the output space. </div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</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>
diff --git a/docs/reference/api/doxygen/loop__state_8h_source.html b/docs/reference/api/doxygen/loop__state_8h_source.html
index 0d298195f..2c8ae0327 100644
--- a/docs/reference/api/doxygen/loop__state_8h_source.html
+++ b/docs/reference/api/doxygen/loop__state_8h_source.html
@@ -83,7 +83,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1auto__scheduler_1_1AttachMapNode_1_1IterKeyHash_html_a3754605e2a818ecbf7ef3ec891b7b6ce"><div class="ttname"><a href="structtvm_1_1auto__scheduler_1_1AttachMapNode_1_1IterKeyHash.html#a3754605e2a818ecbf7ef3ec891b7b6ce">tvm::auto_scheduler::AttachMapNode::IterKeyHash::operator()</a></div><div class="ttdeci">std::size_t operator()(const IterKey &k) const</div><div class="ttdef"><b>Definition:</b> loop_state.h:162</div></div>
<div class="ttc" id="namespacestd_html"><div class="ttname"><a href="namespacestd.html">std</a></div><div class="ttdef"><b>Definition:</b> loop_state.h:456</div></div>
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1State_html"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1State.html">tvm::auto_scheduler::State</a></div><div class="ttdoc">Managed reference to StateNode. </div><div class="ttdef"><b>Definition:</b> loop_state.h:272</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af4e59b01a5842baf6b47ad3f83731f53"><div class="ttname"><a href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi::split</a></div><div class="ttdeci">Array< Tensor > split(const Tensor &x, Array< PrimExpr > split_indices, int axis, std::string name="T_split", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into multiple sub-tensors. </div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af4e59b01a5842baf6b47ad3f83731f53"><div class="ttname"><a href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi::split</a></div><div class="ttdeci">Array< Tensor > split(const Tensor &x, Array< PrimExpr > split_indices, int axis, std::string name="T_split", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into multiple sub-tensors. </div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="namespacetvm_1_1auto__scheduler_html_af6533a065c0157391331e89a0e95f35aad8f4940d9b6d718087e3e6306ea80d4b"><div class="ttname"><a href="namespacetvm_1_1auto__scheduler.html#af6533a065c0157391331e89a0e95f35aad8f4940d9b6d718087e3e6306ea80d4b">tvm::auto_scheduler::StageKind::kPlaceholder</a></div><div class="ttdoc">A placeholder stage. </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="classtvm_1_1auto__scheduler_1_1StateNode_html_a881e14990bf228ee3fddb3721c451b9e"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1StateNode.html#a881e14990bf228ee3fddb3721c451b9e">tvm::auto_scheduler::StateNode::stages</a></div><div class="ttdeci">Array< Stage > stages</div><div class="ttdoc">Current stages and loop structures. </div><div class="ttdef"><b>Definition:</b> loop_state.h:238</div></div>
diff --git a/docs/reference/api/doxygen/measure_8h_source.html b/docs/reference/api/doxygen/measure_8h_source.html
index 0927eefad..8de882e12 100644
--- a/docs/reference/api/doxygen/measure_8h_source.html
+++ b/docs/reference/api/doxygen/measure_8h_source.html
@@ -148,7 +148,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1LocalBuilderNode_html"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1LocalBuilderNode.html">tvm::auto_scheduler::LocalBuilderNode</a></div><div class="ttdoc">LocalBuilder use local CPU cores to build programs in parallel. </div><div class="ttdef"><b>Definition:</b> measure.h:341</div></div>
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1MeasureCallbackNode_html"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1MeasureCallbackNode.html">tvm::auto_scheduler::MeasureCallbackNode</a></div><div class="ttdoc">Bass class of measurement callbacks. </div><div class="ttdef"><b>Definition:</b> measure.h:211</div></div>
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1SearchTask_html"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1SearchTask.html">tvm::auto_scheduler::SearchTask</a></div><div class="ttdoc">Managed reference to SearchTaskNode. </div><div class="ttdef"><b>Definition:</b> search_task.h:148</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1170</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1171</div></div>
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1MeasureResultNode_html_a841db8124b175450ab8c2a2e67e14902"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1MeasureResultNode.html#a841db8124b175450ab8c2a2e67e14902">tvm::auto_scheduler::MeasureResultNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> measure.h:175</div></div>
<div class="ttc" id="search__task_8h_html"><div class="ttname"><a href="search__task_8h.html">search_task.h</a></div><div class="ttdoc">Meta information and hardware parameters for a search task. </div></div>
<div class="ttc" id="classtvm_1_1auto__scheduler_1_1RPCRunnerNode_html_ad249e4a70344d09e0eb513e92e690619"><div class="ttname"><a href="classtvm_1_1auto__scheduler_1_1RPCRunnerNode.html#ad249e4a70344d09e0eb513e92e690619">tvm::auto_scheduler::RPCRunnerNode::key</a></div><div class="ttdeci">String key</div><div class="ttdoc">The key of the device registered in the RPC tracker. </div><div class="ttdef"><b>Definition:</b> measure.h:412</div></div>
diff --git a/docs/reference/api/doxygen/memory__manager_8h_source.html b/docs/reference/api/doxygen/memory__manager_8h_source.html
index af8c243ae..215147598 100644
--- a/docs/reference/api/doxygen/memory__manager_8h_source.html
+++ b/docs/reference/api/doxygen/memory__manager_8h_source.html
@@ -81,7 +81,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1StorageObj_html_ae787a0a25d67ff1952ac5e9eeb0d1a61"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1StorageObj.html#ae787a0a25d67ff1952ac5e9eeb0d1a61">tvm::runtime::vm::StorageObj::buffer</a></div><div class="ttdeci">Buffer buffer</div><div class="ttdoc">The index into the VM function table. </div><div class="ttdef"><b>Definition:</b> memory_manager.h:117</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1MemoryManager_html_aeaa1e35590fd9bcbceea389d3dc1c3c3"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1MemoryManager.html#aeaa1e35590fd9bcbceea389d3dc1c3c3">tvm::runtime::vm::MemoryManager::GetAllocator</a></div><div class="ttdeci">static Allocator * GetAllocator(Device dev)</div><div class="ttdoc">Get an allocator given the context. </div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Buffer_html_a99624b7e535aba1bf5131a5afc08c1c4"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Buffer.html#a99624b7e535aba1bf5131a5afc08c1c4">tvm::runtime::vm::Buffer::data</a></div><div class="ttdeci">void * data</div><div class="ttdoc">The pointer to the allocated block of memory. </div><div class="ttdef"><b>Definition:</b> memory_manager.h:43</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</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"><div class="ttname"><a href="object_8h.html">object.h</a></div><div class="ttdoc">A managed object in the TVM runtime. </div></div>
diff --git a/docs/reference/api/doxygen/metadata_8h_source.html b/docs/reference/api/doxygen/metadata_8h_source.html
index 0c810ce62..d502629e7 100644
--- a/docs/reference/api/doxygen/metadata_8h_source.html
+++ b/docs/reference/api/doxygen/metadata_8h_source.html
@@ -73,7 +73,7 @@ $(function() {
<div class="ttc" id="structTVMTensorInfo_html_a06914e1f39997fd01fec5c6b8103b9ac"><div class="ttname"><a href="structTVMTensorInfo.html#a06914e1f39997fd01fec5c6b8103b9ac">TVMTensorInfo::num_shape</a></div><div class="ttdeci">int64_t num_shape</div><div class="ttdoc">Rank of this tensor. </div><div class="ttdef"><b>Definition:</b> metadata.h:101</div></div>
<div class="ttc" id="structTVMTensorInfo_html"><div class="ttname"><a href="structTVMTensorInfo.html">TVMTensorInfo</a></div><div class="ttdoc">Describes one tensor argument to run_model. NOTE: while TIR allows for other types of arguments...</div><div class="ttdef"><b>Definition:</b> metadata.h:95</div></div>
<div class="ttc" id="structTVMMetadata_html_a2b75989a3e2ed401b97fa825b056f6ed"><div class="ttname"><a href="structTVMMetadata.html#a2b75989a3e2ed401b97fa825b056f6ed">TVMMetadata::num_outputs</a></div><div class="ttdeci">int64_t num_outputs</div><div class="ttdoc">Number of elements in outputs array. </div><div class="ttdef"><b>Definition:</b> metadata.h:77</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="metadata__base_8h_html"><div class="ttname"><a href="metadata__base_8h.html">metadata_base.h</a></div><div class="ttdoc">Defines types which can be used in Metadata. </div></div>
<div class="ttc" id="structTVMMetadata_html_abda76f88609ebbf7f1acbc6509594e78"><div class="ttname"><a href="structTVMMetadata.html#abda76f88609ebbf7f1acbc6509594e78">TVMMetadata::inputs</a></div><div class="ttdeci">const struct TVMTensorInfo * inputs</div><div class="ttdoc">Inputs to the AOT run_model function. The order of the elements is the same as in the arguments to ru...</div><div class="ttdef"><b>Definition:</b> metadata.h:68</div></div>
<div class="ttc" id="structTVMMetadata_html_aec02adf93a75cd6cd89864c01bad43a7"><div class="ttname"><a href="structTVMMetadata.html#aec02adf93a75cd6cd89864c01bad43a7">TVMMetadata::num_inputs</a></div><div class="ttdeci">int64_t num_inputs</div><div class="ttdoc">Number of elements in inputs array. </div><div class="ttdef"><b>Definition:</b> metadata.h:70</div></div>
diff --git a/docs/reference/api/doxygen/ndarray_8h_source.html b/docs/reference/api/doxygen/ndarray_8h_source.html
index 856057d40..dc54462c9 100644
--- a/docs/reference/api/doxygen/ndarray_8h_source.html
+++ b/docs/reference/api/doxygen/ndarray_8h_source.html
@@ -111,7 +111,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase_html_a1063a9d01075d5b7b0e8fa31d4d72e0b"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase.html#a1063a9d01075d5b7b0e8fa31d4d72e0b">tvm::runtime::NDArray::ContainerBase::dl_tensor</a></div><div class="ttdeci">DLTensor dl_tensor</div><div class="ttdoc">The corresponding dl_tensor field. </div><div class="ttdef"><b>Definition:</b> ndarray.h:257</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_1_1Container_html_a56109cfc826b26172f084c3790144351"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray_1_1Container.html#a56109cfc826b26172f084c3790144351">tvm::runtime::NDArray::Container::SetDeleter</a></div><div class="ttdeci">void SetDeleter(FDeleter deleter)</div><div class="ttdoc">Set the deleter field. </div><div class="ttdef"><b>Definition:</b> ndarray.h:308</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_html_afb6060bb96dad082c1deca26e6b58ae2"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray.html#afb6060bb96dad082c1deca26e6b58ae2">tvm::runtime::NDArray::NewFromDLTensor</a></div><div class="ttdeci">static NDArray NewFromDLTensor(DLTensor *dl_tensor, Device dev)</div><div class="ttdoc">Create new NDArray, data is copied from DLTensor. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ace8007daffd9f2c6d954c24d870bfcc4"><div class="ttname"><a href="c__runtime__api_8h.html#ace8007daffd9f2c6d954c24d870bfcc4">tvm_index_t</a></div><div class="ttdeci">int64_t tvm_index_t</div><div class="ttdoc">type of array index. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:81</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_aadbc0886ffa80162ff31eefd0431ba09"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#aadbc0886ffa80162ff31eefd0431ba09">tvm::runtime::ObjectRef::get</a></div><div class="ttdeci">const Object * get() const</div><div class="ttdef"><b>Definition:</b> object.h:546</div></div>
diff --git a/docs/reference/api/doxygen/nn_2bnn_8h_source.html b/docs/reference/api/doxygen/nn_2bnn_8h_source.html
index b81fb8538..7e75687c2 100644
--- a/docs/reference/api/doxygen/nn_2bnn_8h_source.html
+++ b/docs/reference/api/doxygen/nn_2bnn_8h_source.html
@@ -91,7 +91,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html">tvm::arith::Analyzer</a></div><div class="ttdoc">Analyzer that contains bunch of sub-analyzers. </div><div class="ttdef"><b>Definition:</b> analyzer.h:387</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_ad1cf4571ee1a22c188c66ee2e6e6c042"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#ad1cf4571ee1a22c188c66ee2e6e6c042">tvm::runtime::DataType::UInt</a></div><div class="ttdeci">static DataType UInt(int bits, int lanes=1)</div><div class="ttdoc">Construct an uint type. </div><div class="ttdef"><b>Definition:</b> data_type.h:161</div></div>
<div class="ttc" id="namespacetvm_1_1topi_1_1nn_html_a08aaeadaa767fa996d2f2e0a7d12c7cd"><div class="ttname"><a href="namespacetvm_1_1topi_1_1nn.html#a08aaeadaa767fa996d2f2e0a7d12c7cd">tvm::topi::nn::binary_dense</a></div><div class="ttdeci">tvm::te::Tensor binary_dense(const tvm::te::Tensor &data, const tvm::te::Tensor &weight)</div><div class="ttdoc">Binary matrix multiplication using xor and bit-count. </div><div class="ttdef"><b>Definition:</b> bnn.h:101</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/nn_2dense_8h_source.html b/docs/reference/api/doxygen/nn_2dense_8h_source.html
index c63d85e7f..5ff32ce2d 100644
--- a/docs/reference/api/doxygen/nn_2dense_8h_source.html
+++ b/docs/reference/api/doxygen/nn_2dense_8h_source.html
@@ -81,7 +81,7 @@ $(function() {
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
<div class="ttc" id="tags_8h_html"><div class="ttname"><a href="tags_8h.html">tags.h</a></div><div class="ttdoc">External function interface to rocBLAS libraries. </div></div>
<div class="ttc" id="namespacetvm_1_1te_html_afe4f57aeb3dd5ae9c0b58135e14d67ca"><div class="ttname"><a href="namespacetvm_1_1te.html#afe4f57aeb3dd5ae9c0b58135e14d67ca">tvm::te::compute</a></div><div class="ttdeci">Tensor compute(Array< PrimExpr > shape, FCompute fcompute, std::string name="tensor", std::string tag="", Map< String, ObjectRef > attrs={})</div><div class="ttdoc">Construct a new tensor by computing over shape, using the computation rule: resul [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/operation_8h_source.html b/docs/reference/api/doxygen/operation_8h_source.html
index 591a7c3da..a5b633308 100644
--- a/docs/reference/api/doxygen/operation_8h_source.html
+++ b/docs/reference/api/doxygen/operation_8h_source.html
@@ -122,7 +122,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1te_1_1ExternOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ExternOp.html">tvm::te::ExternOp</a></div><div class="ttdoc">Managed reference to ExternOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:460</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="classtvm_1_1te_1_1TensorComputeOpNode_html_a81533c6957c82df59ef8d810ace1bed2"><div class="ttname"><a href="classtvm_1_1te_1_1TensorComputeOpNode.html#a81533c6957c82df59ef8d810ace1bed2">tvm::te::TensorComputeOpNode::inputs</a></div><div class="ttdeci">Array< Tensor > inputs</div><div class="ttdoc">input tensors of intrin </div><div class="ttdef"><b>Definition:</b> operation.h:281</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1te_1_1ScanOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ScanOp.html">tvm::te::ScanOp</a></div><div class="ttdoc">Managed reference to ScanOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:399</div></div>
<div class="ttc" id="classtvm_1_1te_1_1ScanOpNode_html_a1b681295f74cb94732ef167a15a8488f"><div class="ttname"><a href="classtvm_1_1te_1_1ScanOpNode.html#a1b681295f74cb94732ef167a15a8488f">tvm::te::ScanOpNode::ScanOpNode</a></div><div class="ttdeci">ScanOpNode()</div><div class="ttdoc">constructor </div><div class="ttdef"><b>Definition:</b> operation.h:360</div></div>
diff --git a/docs/reference/api/doxygen/profiling_8h_source.html b/docs/reference/api/doxygen/profiling_8h_source.html
index e9b8da0d0..3d0d751f8 100644
--- a/docs/reference/api/doxygen/profiling_8h_source.html
+++ b/docs/reference/api/doxygen/profiling_8h_source.html
@@ -99,7 +99,7 @@ $(function() {
<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="classtvm_1_1runtime_1_1profiling_1_1ReportNode_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1ReportNode.html">tvm::runtime::profiling::ReportNode</a></div><div class="ttdoc">Data collected from a profiling run. Includes per-call metrics and per-device metrics. </div><div class="ttdef"><b>Definition:</b> profiling.h:177</div></div>
<div class="ttc" id="device__api_8h_html"><div class="ttname"><a href="device__api_8h.html">device_api.h</a></div><div class="ttdoc">Abstract device memory management API. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1profiling_1_1Report_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1Report.html">tvm::runtime::profiling::Report</a></div><div class="ttdef"><b>Definition:</b> profiling.h:253</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1profiling_html_a213f5d3fec6828976d6eaf847a9018e4"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1profiling.html#a213f5d3fec6828976d6eaf847a9018e4">tvm::runtime::profiling::ProfileFunction</a></div><div class="ttdeci">PackedFunc ProfileFunction(Module mod, std::string func_name, int device_type, int device_id, int warmup_iters, Array< MetricCollector > collectors)</div><div class="ttdoc">Collect performance information of a fu [...]
@@ -116,7 +116,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1runtime_1_1profiling_1_1DeviceWrapperNode_html"><div class="ttname"><a href="structtvm_1_1runtime_1_1profiling_1_1DeviceWrapperNode.html">tvm::runtime::profiling::DeviceWrapperNode</a></div><div class="ttdoc">Wrapper for Device because Device is not passable across the PackedFunc interface. </div><div class="ttdef"><b>Definition:</b> profiling.h:157</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1PackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1PackedFunc.html">tvm::runtime::PackedFunc</a></div><div class="ttdoc">Packed function is a type-erased function. The arguments are passed by packed format. </div><div class="ttdef"><b>Definition:</b> packed_func.h:138</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TimerNode_html_ad16fba1e2e166b90af3f374cad678244"><div class="ttname"><a href="classtvm_1_1runtime_1_1TimerNode.html#ad16fba1e2e166b90af3f374cad678244">tvm::runtime::TimerNode::~TimerNode</a></div><div class="ttdeci">virtual ~TimerNode()</div><div class="ttdef"><b>Definition:</b> profiling.h:73</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1170</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1171</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode_html_aeb383df9354bf396426a17857a1bb84a"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#aeb383df9354bf396426a17857a1bb84a">tvm::runtime::profiling::MetricCollectorNode::~MetricCollectorNode</a></div><div class="ttdeci">virtual ~MetricCollectorNode()</div><div class="ttdef"><b>Definition:</b> profiling.h:309</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_aaa95d3ad68932ab206efbe0a326db6a2"><div class="ttname"><a href="namespacetvm_1_1topi.html#aaa95d3ad68932ab206efbe0a326db6a2">tvm::topi::mod</a></div><div class="ttdeci">tvm::PrimExpr mod(const tvm::PrimExpr &a, const tvm::PrimExpr &b)</div><div class="ttdef"><b>Definition:</b> broadcast.h:290</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1profiling_1_1DeviceWrapper_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1DeviceWrapper.html">tvm::runtime::profiling::DeviceWrapper</a></div><div class="ttdoc">Wrapper for Device. </div><div class="ttdef"><b>Definition:</b> profiling.h:169</div></div>
diff --git a/docs/reference/api/doxygen/ravel__unravel_8h_source.html b/docs/reference/api/doxygen/ravel__unravel_8h_source.html
index 741bc3459..8ef073964 100644
--- a/docs/reference/api/doxygen/ravel__unravel_8h_source.html
+++ b/docs/reference/api/doxygen/ravel__unravel_8h_source.html
@@ -70,7 +70,7 @@ $(function() {
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> autodiff.h:35</div></div>
<div class="ttc" id="namespacetvm_html_a8f30aa0685ca52f846843e76a1ad1dc7"><div class="ttname"><a href="namespacetvm.html#a8f30aa0685ca52f846843e76a1ad1dc7">tvm::indexdiv</a></div><div class="ttdeci">PrimExpr indexdiv(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute floor(a / b) where a and b are non-negative. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
diff --git a/docs/reference/api/doxygen/relay_2attrs_2transform_8h_source.html b/docs/reference/api/doxygen/relay_2attrs_2transform_8h_source.html
index 19dbdef9f..28304921b 100644
--- a/docs/reference/api/doxygen/relay_2attrs_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/relay_2attrs_2transform_8h_source.html
@@ -66,171 +66,172 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="relay_2attrs_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 [...]
-<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a12e1ac049238f8b036e20411e4ee5ad5"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a12e1ac049238f8b036e20411e4ee5ad5">tvm::relay::AutoSchedulerLayoutTransformAttrs::dst_layout</a></div><div class="ttdeci">std::string dst_layout</div><div class="ttdef"><b>Definition:</b> transform.h:419</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a8f25936511569c3ea754e9d065ccff81"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a8f25936511569c3ea754e9d065ccff81">tvm::relay::ReshapeLikeAttrs::rhs_begin</a></div><div class="ttdeci">int rhs_begin</div><div class="ttdef"><b>Definition:</b> transform.h:131</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_af469a6f2f29cca8b0780e3feb7ed0502"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#af469a6f2f29cca8b0780e3feb7ed0502">tvm::relay::ClipAttrs::a_max</a></div><div class="ttdeci">double a_max</div><div class="ttdef"><b>Definition:</b> transform.h:383</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a9159fd9be82ddd5e9b6a5d135efa91dd"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a9159fd9be82ddd5e9b6a5d135efa91dd">tvm::relay::ReshapeLikeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReshapeLikeAttrs, "relay.attrs.ReshapeLikeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:133</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseAttrs_html_a0fe0a352985941489400e211799f1b8a"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html#a0fe0a352985941489400e211799f1b8a">tvm::relay::ReverseAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:288</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ae48ab03ec982a572227f9d5dc66f88c7"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ae48ab03ec982a572227f9d5dc66f88c7">tvm::relay::StridedSliceAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(StridedSliceAttrs, "relay.attrs.StridedSliceAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:350</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html_a51c18ba5f84813d9d48f3c09a61a58d1"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html#a51c18ba5f84813d9d48f3c09a61a58d1">tvm::relay::SliceLikeAttrs::axes</a></div><div class="ttdeci">Array< Integer > axes</div><div class="ttdef"><b>Definition:</b> transform.h:370</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_ab858f0ecef7ac56b1f9d69b57eb6f3c8"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#ab858f0ecef7ac56b1f9d69b57eb6f3c8">tvm::relay::ReshapeLikeAttrs::lhs_begin</a></div><div class="ttdeci">int lhs_begin</div><div class="ttdef"><b>Definition:</b> transform.h:129</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a4ff9895cebf85396e817f40d9209cff1"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a4ff9895cebf85396e817f40d9209cff1">tvm::relay::MatrixSetDiagAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(MatrixSetDiagAttrs, "relay.attrs.MatrixSetDiagAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:487</div></div>
+<a href="relay_2attrs_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 [...]
+<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a12e1ac049238f8b036e20411e4ee5ad5"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a12e1ac049238f8b036e20411e4ee5ad5">tvm::relay::AutoSchedulerLayoutTransformAttrs::dst_layout</a></div><div class="ttdeci">std::string dst_layout</div><div class="ttdef"><b>Definition:</b> transform.h:422</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a8f25936511569c3ea754e9d065ccff81"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a8f25936511569c3ea754e9d065ccff81">tvm::relay::ReshapeLikeAttrs::rhs_begin</a></div><div class="ttdeci">int rhs_begin</div><div class="ttdef"><b>Definition:</b> transform.h:134</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_af469a6f2f29cca8b0780e3feb7ed0502"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#af469a6f2f29cca8b0780e3feb7ed0502">tvm::relay::ClipAttrs::a_max</a></div><div class="ttdeci">double a_max</div><div class="ttdef"><b>Definition:</b> transform.h:386</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a9159fd9be82ddd5e9b6a5d135efa91dd"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a9159fd9be82ddd5e9b6a5d135efa91dd">tvm::relay::ReshapeLikeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReshapeLikeAttrs, "relay.attrs.ReshapeLikeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:136</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseAttrs_html_a0fe0a352985941489400e211799f1b8a"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html#a0fe0a352985941489400e211799f1b8a">tvm::relay::ReverseAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:291</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ae48ab03ec982a572227f9d5dc66f88c7"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ae48ab03ec982a572227f9d5dc66f88c7">tvm::relay::StridedSliceAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(StridedSliceAttrs, "relay.attrs.StridedSliceAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:353</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html_a51c18ba5f84813d9d48f3c09a61a58d1"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html#a51c18ba5f84813d9d48f3c09a61a58d1">tvm::relay::SliceLikeAttrs::axes</a></div><div class="ttdeci">Array< Integer > axes</div><div class="ttdef"><b>Definition:</b> transform.h:373</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_ab858f0ecef7ac56b1f9d69b57eb6f3c8"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#ab858f0ecef7ac56b1f9d69b57eb6f3c8">tvm::relay::ReshapeLikeAttrs::lhs_begin</a></div><div class="ttdeci">int lhs_begin</div><div class="ttdef"><b>Definition:</b> transform.h:132</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a4ff9895cebf85396e817f40d9209cff1"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a4ff9895cebf85396e817f40d9209cff1">tvm::relay::MatrixSetDiagAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(MatrixSetDiagAttrs, "relay.attrs.MatrixSetDiagAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:490</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1CastAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1CastAttrs.html">tvm::relay::CastAttrs</a></div><div class="ttdoc">data type cast </div><div class="ttdef"><b>Definition:</b> transform.h:60</div></div>
<div class="ttc" id="classtvm_1_1Bool_html"><div class="ttname"><a href="classtvm_1_1Bool.html">tvm::Bool</a></div><div class="ttdoc">Boolean constant. </div><div class="ttdef"><b>Definition:</b> expr.h:368</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html">tvm::relay::FixedPointMultiplyAttrs</a></div><div class="ttdoc">Attributes for FixedPointMultiply operator. </div><div class="ttdef"><b>Definition:</b> transform.h:392</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html">tvm::relay::FixedPointMultiplyAttrs</a></div><div class="ttdoc">Attributes for FixedPointMultiply operator. </div><div class="ttdef"><b>Definition:</b> transform.h:395</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ExpandDimsAttrs_html_a289f19d5f47a1242a04a909c73ca34ac"><div class="ttname"><a href="structtvm_1_1relay_1_1ExpandDimsAttrs.html#a289f19d5f47a1242a04a909c73ca34ac">tvm::relay::ExpandDimsAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:70</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html_aaa7de649c2e9a4e5fc4de4a44f909e34"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html#aaa7de649c2e9a4e5fc4de4a44f909e34">tvm::relay::NdarraySizeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(NdarraySizeAttrs, "relay.attrs.NdarraySizeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:462</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeAttrs_html_adb72dc00148149948a282e4fdbd1cd28"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeAttrs.html#adb72dc00148149948a282e4fdbd1cd28">tvm::relay::ReshapeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReshapeAttrs, "relay.attrs.ReshapeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:121</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeAttrs_html_a53162b9a7f6232a8d599f58ffafce930"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930">tvm::relay::ReshapeAttrs::allowzero</a></div><div class="ttdeci">bool allowzero</div><div class="ttdef"><b>Definition:</b> transform.h:121</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html_aaa7de649c2e9a4e5fc4de4a44f909e34"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html#aaa7de649c2e9a4e5fc4de4a44f909e34">tvm::relay::NdarraySizeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(NdarraySizeAttrs, "relay.attrs.NdarraySizeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:465</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeAttrs_html_adb72dc00148149948a282e4fdbd1cd28"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeAttrs.html#adb72dc00148149948a282e4fdbd1cd28">tvm::relay::ReshapeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReshapeAttrs, "relay.attrs.ReshapeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:122</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ExpandDimsAttrs_html_a97098294de301209eda70719568f1dc9"><div class="ttname"><a href="structtvm_1_1relay_1_1ExpandDimsAttrs.html#a97098294de301209eda70719568f1dc9">tvm::relay::ExpandDimsAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ExpandDimsAttrs, "relay.attrs.ExpandDimsAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:73</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_a97756a96fa3b8190f8fcdd0ebe328166"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#a97756a96fa3b8190f8fcdd0ebe328166">tvm::relay::LayoutTransformAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(LayoutTransformAttrs, "relay.attrs.LayoutTransformAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:409</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_ad0f658bf9e6ac538840fc71b1d312f3b"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#ad0f658bf9e6ac538840fc71b1d312f3b">tvm::relay::LayoutTransformAttrs::src_layout</a></div><div class="ttdeci">std::string src_layout</div><div class="ttdef"><b>Definition:</b> transform.h:406</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_a8287fc14b2ad6671f6ab51ba77134aa1"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#a8287fc14b2ad6671f6ab51ba77134aa1">tvm::relay::OneHotAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:470</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_a97756a96fa3b8190f8fcdd0ebe328166"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#a97756a96fa3b8190f8fcdd0ebe328166">tvm::relay::LayoutTransformAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(LayoutTransformAttrs, "relay.attrs.LayoutTransformAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:412</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_ad0f658bf9e6ac538840fc71b1d312f3b"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#ad0f658bf9e6ac538840fc71b1d312f3b">tvm::relay::LayoutTransformAttrs::src_layout</a></div><div class="ttdeci">std::string src_layout</div><div class="ttdef"><b>Definition:</b> transform.h:409</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_a8287fc14b2ad6671f6ab51ba77134aa1"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#a8287fc14b2ad6671f6ab51ba77134aa1">tvm::relay::OneHotAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:473</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ExpandDimsAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ExpandDimsAttrs.html">tvm::relay::ExpandDimsAttrs</a></div><div class="ttdoc">Attributes used in expand_dims operators. </div><div class="ttdef"><b>Definition:</b> transform.h:69</div></div>
<div class="ttc" id="relay_2expr_8h_html"><div class="ttname"><a href="relay_2expr_8h.html">expr.h</a></div><div class="ttdoc">Relay expression language. </div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html">tvm::relay::MatrixSetDiagAttrs</a></div><div class="ttdoc">Attributes used in matrix_set_diag operator. </div><div class="ttdef"><b>Definition:</b> transform.h:481</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html">tvm::relay::MatrixSetDiagAttrs</a></div><div class="ttdoc">Attributes used in matrix_set_diag operator. </div><div class="ttdef"><b>Definition:</b> transform.h:484</div></div>
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1TransposeAttrs_html_a69ccef64142afaab9a5fc6015714ab55"><div class="ttname"><a href="structtvm_1_1relay_1_1TransposeAttrs.html#a69ccef64142afaab9a5fc6015714ab55">tvm::relay::TransposeAttrs::axes</a></div><div class="ttdeci">Array< Integer > axes</div><div class="ttdef"><b>Definition:</b> transform.h:112</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1DynExpandDimsAttrs_html_adbba8b09c3486a42abfb2248f5993035"><div class="ttname"><a href="structtvm_1_1relay_1_1DynExpandDimsAttrs.html#adbba8b09c3486a42abfb2248f5993035">tvm::relay::DynExpandDimsAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(DynExpandDimsAttrs, "relay.attrs.DynExpandDimsAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:90</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html">tvm::relay::UniqueAttrs</a></div><div class="ttdoc">Attributes used in unique operator. </div><div class="ttdef"><b>Definition:</b> transform.h:516</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_ae77cd5a12123839e40c9ff43cfe26d12"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#ae77cd5a12123839e40c9ff43cfe26d12">tvm::relay::OneHotAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:471</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_aa7f0e8e2bab7a0726918fa9ea5d3258f"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#aa7f0e8e2bab7a0726918fa9ea5d3258f">tvm::relay::SplitAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:328</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html">tvm::relay::UniqueAttrs</a></div><div class="ttdoc">Attributes used in unique operator. </div><div class="ttdef"><b>Definition:</b> transform.h:519</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_ae77cd5a12123839e40c9ff43cfe26d12"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#ae77cd5a12123839e40c9ff43cfe26d12">tvm::relay::OneHotAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:474</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_aa7f0e8e2bab7a0726918fa9ea5d3258f"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#aa7f0e8e2bab7a0726918fa9ea5d3258f">tvm::relay::SplitAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:331</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1CastAttrs_html_a0ba181c2c6c542448a841f3a87e360c7"><div class="ttname"><a href="structtvm_1_1relay_1_1CastAttrs.html#a0ba181c2c6c542448a841f3a87e360c7">tvm::relay::CastAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:61</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html_a51905623ae6dd3c47faba6f42b66d864"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html#a51905623ae6dd3c47faba6f42b66d864">tvm::relay::ShapeOfAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ShapeOfAttrs, "relay.attrs.ShapeOfAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:433</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html">tvm::relay::InitOpAttrs</a></div><div class="ttdoc">Attributes that specify a tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:217</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a7273f14f80b4dbaf455b47d7a2f6ad46"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a7273f14f80b4dbaf455b47d7a2f6ad46">tvm::relay::SequenceMaskAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:440</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_ade3005a90c1ff77a1f583c4a7ba898e0"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#ade3005a90c1ff77a1f583c4a7ba898e0">tvm::relay::RepeatAttrs::repeats</a></div><div class="ttdeci">Integer repeats</div><div class="ttdef"><b>Definition:</b> transform.h:266</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html">tvm::relay::ScatterAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:147</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html_ab7475a4936b4cea3cdbdffb32b45da57"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html#ab7475a4936b4cea3cdbdffb32b45da57">tvm::relay::StackAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(StackAttrs, "relay.attrs.StackAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:258</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html_a51905623ae6dd3c47faba6f42b66d864"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html#a51905623ae6dd3c47faba6f42b66d864">tvm::relay::ShapeOfAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ShapeOfAttrs, "relay.attrs.ShapeOfAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:436</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html">tvm::relay::InitOpAttrs</a></div><div class="ttdoc">Attributes that specify a tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:220</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a7273f14f80b4dbaf455b47d7a2f6ad46"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a7273f14f80b4dbaf455b47d7a2f6ad46">tvm::relay::SequenceMaskAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:443</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_ade3005a90c1ff77a1f583c4a7ba898e0"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#ade3005a90c1ff77a1f583c4a7ba898e0">tvm::relay::RepeatAttrs::repeats</a></div><div class="ttdeci">Integer repeats</div><div class="ttdef"><b>Definition:</b> transform.h:269</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html">tvm::relay::ScatterAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:150</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html_ab7475a4936b4cea3cdbdffb32b45da57"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html#ab7475a4936b4cea3cdbdffb32b45da57">tvm::relay::StackAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(StackAttrs, "relay.attrs.StackAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:261</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ReshapeAttrs_html_a9bca32c3acff2ed8fd6bc63a50f82051"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeAttrs.html#a9bca32c3acff2ed8fd6bc63a50f82051">tvm::relay::ReshapeAttrs::newshape</a></div><div class="ttdeci">Array< Integer > newshape</div><div class="ttdef"><b>Definition:</b> transform.h:120</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html">tvm::relay::GatherNDAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:182</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html">tvm::relay::GatherNDAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:185</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1TransposeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1TransposeAttrs.html">tvm::relay::TransposeAttrs</a></div><div class="ttdoc">Attributes used in transpose operators. </div><div class="ttdef"><b>Definition:</b> transform.h:111</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html">tvm::relay::OneHotAttrs</a></div><div class="ttdoc">Attributes used in one-hot operator. </div><div class="ttdef"><b>Definition:</b> transform.h:468</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_a317374d804a576b50d9a51e4a8ee3ff2"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#a317374d804a576b50d9a51e4a8ee3ff2">tvm::relay::FixedPointMultiplyAttrs::multiplier</a></div><div class="ttdeci">int32_t multiplier</div><div class="ttdef"><b>Definition:</b> transform.h:393</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html">tvm::relay::OneHotAttrs</a></div><div class="ttdoc">Attributes used in one-hot operator. </div><div class="ttdef"><b>Definition:</b> transform.h:471</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_a317374d804a576b50d9a51e4a8ee3ff2"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#a317374d804a576b50d9a51e4a8ee3ff2">tvm::relay::FixedPointMultiplyAttrs::multiplier</a></div><div class="ttdeci">int32_t multiplier</div><div class="ttdef"><b>Definition:</b> transform.h:396</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ConcatenateAttrs_html_a4eb9569b302dd8613b74625456f1e97c"><div class="ttname"><a href="structtvm_1_1relay_1_1ConcatenateAttrs.html#a4eb9569b302dd8613b74625456f1e97c">tvm::relay::ConcatenateAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ConcatenateAttrs, "relay.attrs.ConcatenateAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:101</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html">tvm::relay::GatherAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:172</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html">tvm::relay::ClipAttrs</a></div><div class="ttdoc">Attributes for Clip operator. </div><div class="ttdef"><b>Definition:</b> transform.h:381</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html">tvm::relay::ScatterAddAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:155</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html">tvm::relay::GatherAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:175</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html">tvm::relay::ClipAttrs</a></div><div class="ttdoc">Attributes for Clip operator. </div><div class="ttdef"><b>Definition:</b> transform.h:384</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html">tvm::relay::ScatterAddAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:158</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ExpandDimsAttrs_html_af2885538e2f74029ecad343a9844fc8a"><div class="ttname"><a href="structtvm_1_1relay_1_1ExpandDimsAttrs.html#af2885538e2f74029ecad343a9844fc8a">tvm::relay::ExpandDimsAttrs::num_newaxis</a></div><div class="ttdeci">int num_newaxis</div><div class="ttdef"><b>Definition:</b> transform.h:71</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html_ada5d11bde3fdd7c2e23191d01573ea3f"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html#ada5d11bde3fdd7c2e23191d01573ea3f">tvm::relay::TileAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(TileAttrs, "relay.attrs.TileAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:279</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html">tvm::relay::StridedSliceAttrs</a></div><div class="ttdoc">Attributes for StridedSlice operator. </div><div class="ttdef"><b>Definition:</b> transform.h:343</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ade582278d58f236cccf69167cdd961f1"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ade582278d58f236cccf69167cdd961f1">tvm::relay::StridedSliceAttrs::begin</a></div><div class="ttdeci">Optional< Array< Integer > > begin</div><div class="ttdef"><b>Definition:</b> transform.h:344</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_af0ed09ec12a589b85fa813c810f4cb2f"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#af0ed09ec12a589b85fa813c810f4cb2f">tvm::relay::ClipAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ClipAttrs, "relay.attrs.ClipAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:385</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_a163b5ad31df0638663ea18d781defcae"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#a163b5ad31df0638663ea18d781defcae">tvm::relay::UniqueAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(UniqueAttrs, "relay.attrs.UniqueAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:519</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html_ada5d11bde3fdd7c2e23191d01573ea3f"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html#ada5d11bde3fdd7c2e23191d01573ea3f">tvm::relay::TileAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(TileAttrs, "relay.attrs.TileAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:282</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html">tvm::relay::StridedSliceAttrs</a></div><div class="ttdoc">Attributes for StridedSlice operator. </div><div class="ttdef"><b>Definition:</b> transform.h:346</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ade582278d58f236cccf69167cdd961f1"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ade582278d58f236cccf69167cdd961f1">tvm::relay::StridedSliceAttrs::begin</a></div><div class="ttdeci">Optional< Array< Integer > > begin</div><div class="ttdef"><b>Definition:</b> transform.h:347</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_af0ed09ec12a589b85fa813c810f4cb2f"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#af0ed09ec12a589b85fa813c810f4cb2f">tvm::relay::ClipAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ClipAttrs, "relay.attrs.ClipAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:388</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_a163b5ad31df0638663ea18d781defcae"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#a163b5ad31df0638663ea18d781defcae">tvm::relay::UniqueAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(UniqueAttrs, "relay.attrs.UniqueAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:522</div></div>
<div class="ttc" id="ir_2attrs_8h_html"><div class="ttname"><a href="ir_2attrs_8h.html">attrs.h</a></div><div class="ttdoc">Helpers for attribute objects. </div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_a285b0073659f6403fb5ef3808347f3c9"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#a285b0073659f6403fb5ef3808347f3c9">tvm::relay::SplitAttrs::indices_or_sections</a></div><div class="ttdeci">ObjectRef indices_or_sections</div><div class="ttdef"><b>Definition:</b> transform.h:327</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_ac363fad76b1bd8dae81fd57d26461b71"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#ac363fad76b1bd8dae81fd57d26461b71">tvm::relay::GatherNDAttrs::batch_dims</a></div><div class="ttdeci">Integer batch_dims</div><div class="ttdef"><b>Definition:</b> transform.h:183</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html">tvm::relay::SliceLikeAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:369</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ab3a282ef18dc4fa3a69917bfbcddce55"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ab3a282ef18dc4fa3a69917bfbcddce55">tvm::relay::StridedSliceAttrs::slice_mode</a></div><div class="ttdeci">tvm::String slice_mode</div><div class="ttdef"><b>Definition:</b> transform.h:347</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html_aaaec76cc5ea9a543c4ea174a6b38bf5e"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html#aaaec76cc5ea9a543c4ea174a6b38bf5e">tvm::relay::InitOpAttrs::shape</a></div><div class="ttdeci">Optional< Array< Integer > > shape</div><div class="ttdef"><b>Definition:</b> transform.h:218</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html">tvm::relay::ReshapeLikeAttrs</a></div><div class="ttdoc">Attributes used in MXNet-style reshape_like operators. </div><div class="ttdef"><b>Definition:</b> transform.h:128</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_a285b0073659f6403fb5ef3808347f3c9"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#a285b0073659f6403fb5ef3808347f3c9">tvm::relay::SplitAttrs::indices_or_sections</a></div><div class="ttdeci">ObjectRef indices_or_sections</div><div class="ttdef"><b>Definition:</b> transform.h:330</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_ac363fad76b1bd8dae81fd57d26461b71"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#ac363fad76b1bd8dae81fd57d26461b71">tvm::relay::GatherNDAttrs::batch_dims</a></div><div class="ttdeci">Integer batch_dims</div><div class="ttdef"><b>Definition:</b> transform.h:186</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html">tvm::relay::SliceLikeAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:372</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ab3a282ef18dc4fa3a69917bfbcddce55"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ab3a282ef18dc4fa3a69917bfbcddce55">tvm::relay::StridedSliceAttrs::slice_mode</a></div><div class="ttdeci">tvm::String slice_mode</div><div class="ttdef"><b>Definition:</b> transform.h:350</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html_aaaec76cc5ea9a543c4ea174a6b38bf5e"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html#aaaec76cc5ea9a543c4ea174a6b38bf5e">tvm::relay::InitOpAttrs::shape</a></div><div class="ttdeci">Optional< Array< Integer > > shape</div><div class="ttdef"><b>Definition:</b> transform.h:221</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html">tvm::relay::ReshapeLikeAttrs</a></div><div class="ttdoc">Attributes used in MXNet-style reshape_like operators. </div><div class="ttdef"><b>Definition:</b> transform.h:131</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1DynExpandDimsAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1DynExpandDimsAttrs.html">tvm::relay::DynExpandDimsAttrs</a></div><div class="ttdoc">Attributes used in dynamic expand_dims operators. </div><div class="ttdef"><b>Definition:</b> transform.h:87</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a079744827d8dd377fd0d076d93b9cc60"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a079744827d8dd377fd0d076d93b9cc60">tvm::relay::SequenceMaskAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SequenceMaskAttrs, "relay.attrs.SequenceMaskAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:442</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a079744827d8dd377fd0d076d93b9cc60"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a079744827d8dd377fd0d076d93b9cc60">tvm::relay::SequenceMaskAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SequenceMaskAttrs, "relay.attrs.SequenceMaskAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:445</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SlidingWindowAttrs_html_a8e12fafa989faf9bf986ee40626326c2"><div class="ttname"><a href="structtvm_1_1relay_1_1SlidingWindowAttrs.html#a8e12fafa989faf9bf986ee40626326c2">tvm::relay::SlidingWindowAttrs::window_shape</a></div><div class="ttdeci">Array< Integer > window_shape</div><div class="ttdef"><b>Definition:</b> transform.h:39</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_ae8ae5bc1551b406a4f52395af343c2ce"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#ae8ae5bc1551b406a4f52395af343c2ce">tvm::relay::ArangeAttrs::start</a></div><div class="ttdeci">Expr start</div><div class="ttdef"><b>Definition:</b> transform.h:229</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html_a490e2e66c402990983f0407d4ff035b0"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html#a490e2e66c402990983f0407d4ff035b0">tvm::relay::EinsumAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(EinsumAttrs, "relay.attrs.EinsumAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:531</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html">tvm::relay::EinsumAttrs</a></div><div class="ttdoc">Attributes used in einsum operator. </div><div class="ttdef"><b>Definition:</b> transform.h:528</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html_a5e1dab557af22dbf5f635b3f20c42b56"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html#a5e1dab557af22dbf5f635b3f20c42b56">tvm::relay::EinsumAttrs::equation</a></div><div class="ttdeci">String equation</div><div class="ttdef"><b>Definition:</b> transform.h:529</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html">tvm::relay::ScanopAttrs</a></div><div class="ttdoc">Attributes used in cumsum and cumprod operator. </div><div class="ttdef"><b>Definition:</b> transform.h:500</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html_a73812f7280b47ad059b84c1b56243873"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html#a73812f7280b47ad059b84c1b56243873">tvm::relay::SparseToDenseAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SparseToDenseAttrs, "relay.attrs.SparseToDenseAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:453</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_ad8d38a1e0ea91c357a55b141ae21fe68"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#ad8d38a1e0ea91c357a55b141ae21fe68">tvm::relay::TakeAttrs::batch_dims</a></div><div class="ttdeci">Integer batch_dims</div><div class="ttdef"><b>Definition:</b> transform.h:197</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a0bf9d25ced9bfc91e766494e5f641e70"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a0bf9d25ced9bfc91e766494e5f641e70">tvm::relay::TakeAttrs::mode</a></div><div class="ttdeci">tvm::String mode</div><div class="ttdef"><b>Definition:</b> transform.h:199</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_ae8ae5bc1551b406a4f52395af343c2ce"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#ae8ae5bc1551b406a4f52395af343c2ce">tvm::relay::ArangeAttrs::start</a></div><div class="ttdeci">Expr start</div><div class="ttdef"><b>Definition:</b> transform.h:232</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html_a490e2e66c402990983f0407d4ff035b0"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html#a490e2e66c402990983f0407d4ff035b0">tvm::relay::EinsumAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(EinsumAttrs, "relay.attrs.EinsumAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:534</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html">tvm::relay::EinsumAttrs</a></div><div class="ttdoc">Attributes used in einsum operator. </div><div class="ttdef"><b>Definition:</b> transform.h:531</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1EinsumAttrs_html_a5e1dab557af22dbf5f635b3f20c42b56"><div class="ttname"><a href="structtvm_1_1relay_1_1EinsumAttrs.html#a5e1dab557af22dbf5f635b3f20c42b56">tvm::relay::EinsumAttrs::equation</a></div><div class="ttdeci">String equation</div><div class="ttdef"><b>Definition:</b> transform.h:532</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html">tvm::relay::ScanopAttrs</a></div><div class="ttdoc">Attributes used in cumsum and cumprod operator. </div><div class="ttdef"><b>Definition:</b> transform.h:503</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html_a73812f7280b47ad059b84c1b56243873"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html#a73812f7280b47ad059b84c1b56243873">tvm::relay::SparseToDenseAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SparseToDenseAttrs, "relay.attrs.SparseToDenseAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:456</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_ad8d38a1e0ea91c357a55b141ae21fe68"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#ad8d38a1e0ea91c357a55b141ae21fe68">tvm::relay::TakeAttrs::batch_dims</a></div><div class="ttdeci">Integer batch_dims</div><div class="ttdef"><b>Definition:</b> transform.h:200</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a0bf9d25ced9bfc91e766494e5f641e70"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a0bf9d25ced9bfc91e766494e5f641e70">tvm::relay::TakeAttrs::mode</a></div><div class="ttdeci">tvm::String mode</div><div class="ttdef"><b>Definition:</b> transform.h:202</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html">tvm::runtime::DataType</a></div><div class="ttdoc">Runtime primitive data type. </div><div class="ttdef"><b>Definition:</b> data_type.h:41</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html">tvm::relay::LayoutTransformAttrs</a></div><div class="ttdoc">Attributes for LayoutTransform operator. </div><div class="ttdef"><b>Definition:</b> transform.h:405</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html">tvm::relay::ArangeAttrs</a></div><div class="ttdoc">Attributes used in arange operators. </div><div class="ttdef"><b>Definition:</b> transform.h:228</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_a3c89eda41d69f3cc9ec0ca73e3c01bab"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#a3c89eda41d69f3cc9ec0ca73e3c01bab">tvm::relay::GatherNDAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GatherNDAttrs, "relay.attrs.GatherNDAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:186</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html">tvm::relay::LayoutTransformAttrs</a></div><div class="ttdoc">Attributes for LayoutTransform operator. </div><div class="ttdef"><b>Definition:</b> transform.h:408</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html">tvm::relay::ArangeAttrs</a></div><div class="ttdoc">Attributes used in arange operators. </div><div class="ttdef"><b>Definition:</b> transform.h:231</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_a3c89eda41d69f3cc9ec0ca73e3c01bab"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#a3c89eda41d69f3cc9ec0ca73e3c01bab">tvm::relay::GatherNDAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GatherNDAttrs, "relay.attrs.GatherNDAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:189</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="structtvm_1_1relay_1_1ReverseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html">tvm::relay::ReverseAttrs</a></div><div class="ttdoc">Attributes used in reverse operators. </div><div class="ttdef"><b>Definition:</b> transform.h:287</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html_a848f0532864ed09ed9a4e954d4d0b627"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html#a848f0532864ed09ed9a4e954d4d0b627">tvm::relay::ScatterAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterAttrs, "relay.attrs.ScatterAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:150</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html">tvm::relay::SplitAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:326</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html">tvm::relay::ReverseAttrs</a></div><div class="ttdoc">Attributes used in reverse operators. </div><div class="ttdef"><b>Definition:</b> transform.h:290</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html_a848f0532864ed09ed9a4e954d4d0b627"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html#a848f0532864ed09ed9a4e954d4d0b627">tvm::relay::ScatterAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterAttrs, "relay.attrs.ScatterAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:153</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html">tvm::relay::SplitAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:329</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SlidingWindowAttrs_html_aa565b6e06fb72698e900dcb81721a8fa"><div class="ttname"><a href="structtvm_1_1relay_1_1SlidingWindowAttrs.html#aa565b6e06fb72698e900dcb81721a8fa">tvm::relay::SlidingWindowAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:38</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseAttrs_html_a523a327ad70ae6803192abddee26c518"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html#a523a327ad70ae6803192abddee26c518">tvm::relay::ReverseAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReverseAttrs, "relay.attrs.ReverseAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:289</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_a8a9a5b34513d0e9b46cae1ac436c6917"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#a8a9a5b34513d0e9b46cae1ac436c6917">tvm::relay::ClipAttrs::a_min</a></div><div class="ttdeci">double a_min</div><div class="ttdef"><b>Definition:</b> transform.h:382</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_a698ab8a2112fff60a95425155e015a78"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#a698ab8a2112fff60a95425155e015a78">tvm::relay::OneHotAttrs::depth</a></div><div class="ttdeci">int depth</div><div class="ttdef"><b>Definition:</b> transform.h:469</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html">tvm::relay::MeshgridAttrs</a></div><div class="ttdoc">Attributes used in meshgrid operators. </div><div class="ttdef"><b>Definition:</b> transform.h:243</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_ae3c94ca8dff6e3bc5a916286e4710ba3"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#ae3c94ca8dff6e3bc5a916286e4710ba3">tvm::relay::ScanopAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:502</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html_a676e5a94fc15ef0db05a549d3a6c923f"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html#a676e5a94fc15ef0db05a549d3a6c923f">tvm::relay::GatherAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GatherAttrs, "relay.attrs.GatherAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:175</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseAttrs_html_a523a327ad70ae6803192abddee26c518"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseAttrs.html#a523a327ad70ae6803192abddee26c518">tvm::relay::ReverseAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReverseAttrs, "relay.attrs.ReverseAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:292</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ClipAttrs_html_a8a9a5b34513d0e9b46cae1ac436c6917"><div class="ttname"><a href="structtvm_1_1relay_1_1ClipAttrs.html#a8a9a5b34513d0e9b46cae1ac436c6917">tvm::relay::ClipAttrs::a_min</a></div><div class="ttdeci">double a_min</div><div class="ttdef"><b>Definition:</b> transform.h:385</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_a698ab8a2112fff60a95425155e015a78"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#a698ab8a2112fff60a95425155e015a78">tvm::relay::OneHotAttrs::depth</a></div><div class="ttdeci">int depth</div><div class="ttdef"><b>Definition:</b> transform.h:472</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html">tvm::relay::MeshgridAttrs</a></div><div class="ttdoc">Attributes used in meshgrid operators. </div><div class="ttdef"><b>Definition:</b> transform.h:246</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_ae3c94ca8dff6e3bc5a916286e4710ba3"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#ae3c94ca8dff6e3bc5a916286e4710ba3">tvm::relay::ScanopAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:505</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html_a676e5a94fc15ef0db05a549d3a6c923f"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html#a676e5a94fc15ef0db05a549d3a6c923f">tvm::relay::GatherAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GatherAttrs, "relay.attrs.GatherAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:178</div></div>
<div class="ttc" id="ir_2attrs_8h_html_a578da113eb199bad72e26c03ad24832f"><div class="ttname"><a href="ir_2attrs_8h.html#a578da113eb199bad72e26c03ad24832f">TVM_ATTR_FIELD</a></div><div class="ttdeci">#define TVM_ATTR_FIELD(FieldName)</div><div class="ttdoc">Declare an attribute field. </div><div class="ttdef"><b>Definition:</b> attrs.h:76</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_ab4b29f691ffdffb10564af81eec6e1bd"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#ab4b29f691ffdffb10564af81eec6e1bd">tvm::relay::ArangeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ArangeAttrs, "relay.attrs.ArangeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:234</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html">tvm::relay::TileAttrs</a></div><div class="ttdoc">Attributes used in tile operators. </div><div class="ttdef"><b>Definition:</b> transform.h:277</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_a405dbeb1c77da2690c40606c980f388d"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#a405dbeb1c77da2690c40606c980f388d">tvm::relay::ArangeAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:232</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_aef434799646533ec9d796393ba01db44"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#aef434799646533ec9d796393ba01db44">tvm::relay::UniqueAttrs::sorted</a></div><div class="ttdeci">bool sorted</div><div class="ttdef"><b>Definition:</b> transform.h:517</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_ab4b29f691ffdffb10564af81eec6e1bd"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#ab4b29f691ffdffb10564af81eec6e1bd">tvm::relay::ArangeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ArangeAttrs, "relay.attrs.ArangeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:237</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html">tvm::relay::TileAttrs</a></div><div class="ttdoc">Attributes used in tile operators. </div><div class="ttdef"><b>Definition:</b> transform.h:280</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_a405dbeb1c77da2690c40606c980f388d"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#a405dbeb1c77da2690c40606c980f388d">tvm::relay::ArangeAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:235</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_aef434799646533ec9d796393ba01db44"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#aef434799646533ec9d796393ba01db44">tvm::relay::UniqueAttrs::sorted</a></div><div class="ttdeci">bool sorted</div><div class="ttdef"><b>Definition:</b> transform.h:520</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="structtvm_1_1relay_1_1ScatterNDAttrs_html_ab13eeaa700fe7e41666ac04179e0fd62"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html#ab13eeaa700fe7e41666ac04179e0fd62">tvm::relay::ScatterNDAttrs::mode</a></div><div class="ttdeci">String mode</div><div class="ttdef"><b>Definition:</b> transform.h:164</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html_a549d7ca42a8ac4f7db2b96f276de6266"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html#a549d7ca42a8ac4f7db2b96f276de6266">tvm::relay::InitOpAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(InitOpAttrs, "relay.attrs.InitOpAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:221</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html_aa266a70026db0feb88f57a08fb4d3303"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html#aa266a70026db0feb88f57a08fb4d3303">tvm::relay::ScatterAddAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterAddAttrs, "relay.attrs.ScatterAddAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:158</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterNDAttrs_html_ab13eeaa700fe7e41666ac04179e0fd62"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html#ab13eeaa700fe7e41666ac04179e0fd62">tvm::relay::ScatterNDAttrs::mode</a></div><div class="ttdeci">String mode</div><div class="ttdef"><b>Definition:</b> transform.h:167</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1InitOpAttrs_html_a549d7ca42a8ac4f7db2b96f276de6266"><div class="ttname"><a href="structtvm_1_1relay_1_1InitOpAttrs.html#a549d7ca42a8ac4f7db2b96f276de6266">tvm::relay::InitOpAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(InitOpAttrs, "relay.attrs.InitOpAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:224</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html_aa266a70026db0feb88f57a08fb4d3303"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html#aa266a70026db0feb88f57a08fb4d3303">tvm::relay::ScatterAddAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterAddAttrs, "relay.attrs.ScatterAddAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:161</div></div>
<div class="ttc" id="classtvm_1_1RelayExpr_html"><div class="ttname"><a href="classtvm_1_1RelayExpr.html">tvm::RelayExpr</a></div><div class="ttdoc">Managed reference to RelayExprNode. </div><div class="ttdef"><b>Definition:</b> expr.h:217</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_a1eadf1f3964ca83dade8edeae7d6d7cf"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#a1eadf1f3964ca83dade8edeae7d6d7cf">tvm::relay::ArangeAttrs::stop</a></div><div class="ttdeci">Expr stop</div><div class="ttdef"><b>Definition:</b> transform.h:230</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_a1eadf1f3964ca83dade8edeae7d6d7cf"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#a1eadf1f3964ca83dade8edeae7d6d7cf">tvm::relay::ArangeAttrs::stop</a></div><div class="ttdeci">Expr stop</div><div class="ttdef"><b>Definition:</b> transform.h:233</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SlidingWindowAttrs_html_a74e2768c0ff2825a95c17c2a9a034254"><div class="ttname"><a href="structtvm_1_1relay_1_1SlidingWindowAttrs.html#a74e2768c0ff2825a95c17c2a9a034254">tvm::relay::SlidingWindowAttrs::strides</a></div><div class="ttdeci">Array< Integer > strides</div><div class="ttdef"><b>Definition:</b> transform.h:40</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_afc3b30a439e284ebc3182c830f334b80"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#afc3b30a439e284ebc3182c830f334b80">tvm::relay::ReshapeLikeAttrs::lhs_end</a></div><div class="ttdeci">Integer lhs_end</div><div class="ttdef"><b>Definition:</b> transform.h:130</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a9a073f69d510b4f8a15c9e8e3b4c5159"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a9a073f69d510b4f8a15c9e8e3b4c5159">tvm::relay::AutoSchedulerLayoutTransformAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(AutoSchedulerLayoutTransformAttrs, "relay.attrs.AutoSchedulerLayoutTransformAttrs")</div><div class="ttdef"><b>Definition:</b> t [...]
-<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html_a72481a0669da7058965729aa3e161008"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html#a72481a0669da7058965729aa3e161008">tvm::relay::SqueezeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SqueezeAttrs, "relay.attrs.SqueezeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:315</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html_a56c8360378bd1bb56e22f21ee8a0b4be"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html#a56c8360378bd1bb56e22f21ee8a0b4be">tvm::relay::SliceLikeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SliceLikeAttrs, "relay.attrs.SliceLikeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:372</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_afd0a3040ec86dc3d2b6b28ac6170425e"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#afd0a3040ec86dc3d2b6b28ac6170425e">tvm::relay::ScanopAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:501</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html_acac0351f86c23beb264227981424022e"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html#acac0351f86c23beb264227981424022e">tvm::relay::TileAttrs::reps</a></div><div class="ttdeci">Array< Integer > reps</div><div class="ttdef"><b>Definition:</b> transform.h:278</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_ab107432fff56dfd9ef4a0600ee616ade"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#ab107432fff56dfd9ef4a0600ee616ade">tvm::relay::ReverseSequenceAttrs::seq_axis</a></div><div class="ttdeci">Integer seq_axis</div><div class="ttdef"><b>Definition:</b> transform.h:298</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterNDAttrs_html_a8eba0ff6fb3ce4c6e18c7d541f9f428f"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html#a8eba0ff6fb3ce4c6e18c7d541f9f428f">tvm::relay::ScatterNDAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterNDAttrs, "relay.attrs.ScatterNDAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:166</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_adb7c44439db1d842a6c804547df02a31"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#adb7c44439db1d842a6c804547df02a31">tvm::relay::MatrixSetDiagAttrs::super_diag_right_align</a></div><div class="ttdeci">bool super_diag_right_align</div><div class="ttdef"><b>Definition:</b> transform.h:484</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_a5ada31d79efbeb340a0cd7d5ca7c1afb"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#a5ada31d79efbeb340a0cd7d5ca7c1afb">tvm::relay::UniqueAttrs::return_counts</a></div><div class="ttdeci">bool return_counts</div><div class="ttdef"><b>Definition:</b> transform.h:518</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_afc3b30a439e284ebc3182c830f334b80"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#afc3b30a439e284ebc3182c830f334b80">tvm::relay::ReshapeLikeAttrs::lhs_end</a></div><div class="ttdeci">Integer lhs_end</div><div class="ttdef"><b>Definition:</b> transform.h:133</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a9a073f69d510b4f8a15c9e8e3b4c5159"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a9a073f69d510b4f8a15c9e8e3b4c5159">tvm::relay::AutoSchedulerLayoutTransformAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(AutoSchedulerLayoutTransformAttrs, "relay.attrs.AutoSchedulerLayoutTransformAttrs")</div><div class="ttdef"><b>Definition:</b> t [...]
+<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html_a72481a0669da7058965729aa3e161008"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html#a72481a0669da7058965729aa3e161008">tvm::relay::SqueezeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SqueezeAttrs, "relay.attrs.SqueezeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:318</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SliceLikeAttrs_html_a56c8360378bd1bb56e22f21ee8a0b4be"><div class="ttname"><a href="structtvm_1_1relay_1_1SliceLikeAttrs.html#a56c8360378bd1bb56e22f21ee8a0b4be">tvm::relay::SliceLikeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SliceLikeAttrs, "relay.attrs.SliceLikeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:375</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_afd0a3040ec86dc3d2b6b28ac6170425e"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#afd0a3040ec86dc3d2b6b28ac6170425e">tvm::relay::ScanopAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:504</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TileAttrs_html_acac0351f86c23beb264227981424022e"><div class="ttname"><a href="structtvm_1_1relay_1_1TileAttrs.html#acac0351f86c23beb264227981424022e">tvm::relay::TileAttrs::reps</a></div><div class="ttdeci">Array< Integer > reps</div><div class="ttdef"><b>Definition:</b> transform.h:281</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_ab107432fff56dfd9ef4a0600ee616ade"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#ab107432fff56dfd9ef4a0600ee616ade">tvm::relay::ReverseSequenceAttrs::seq_axis</a></div><div class="ttdeci">Integer seq_axis</div><div class="ttdef"><b>Definition:</b> transform.h:301</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterNDAttrs_html_a8eba0ff6fb3ce4c6e18c7d541f9f428f"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html#a8eba0ff6fb3ce4c6e18c7d541f9f428f">tvm::relay::ScatterNDAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScatterNDAttrs, "relay.attrs.ScatterNDAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:169</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_adb7c44439db1d842a6c804547df02a31"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#adb7c44439db1d842a6c804547df02a31">tvm::relay::MatrixSetDiagAttrs::super_diag_right_align</a></div><div class="ttdeci">bool super_diag_right_align</div><div class="ttdef"><b>Definition:</b> transform.h:487</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1UniqueAttrs_html_a5ada31d79efbeb340a0cd7d5ca7c1afb"><div class="ttname"><a href="structtvm_1_1relay_1_1UniqueAttrs.html#a5ada31d79efbeb340a0cd7d5ca7c1afb">tvm::relay::UniqueAttrs::return_counts</a></div><div class="ttdeci">bool return_counts</div><div class="ttdef"><b>Definition:</b> transform.h:521</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="namespacetvm_html_a28c693333c2b15702b1a9a57dec0fbf5"><div class="ttname"><a href="namespacetvm.html#a28c693333c2b15702b1a9a57dec0fbf5">tvm::NullValue< DataType ></a></div><div class="ttdeci">DataType NullValue< DataType >()</div><div class="ttdef"><b>Definition:</b> attrs.h:90</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html_a5ada9836e19157a53637c14f9318fb64"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html#a5ada9836e19157a53637c14f9318fb64">tvm::relay::ScatterAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:148</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAttrs_html_a5ada9836e19157a53637c14f9318fb64"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAttrs.html#a5ada9836e19157a53637c14f9318fb64">tvm::relay::ScatterAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:151</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1CastAttrs_html_a460996bb6ac2eb42602b245721a4b2d3"><div class="ttname"><a href="structtvm_1_1relay_1_1CastAttrs.html#a460996bb6ac2eb42602b245721a4b2d3">tvm::relay::CastAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(CastAttrs, "relay.attrs.CastAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:63</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html">tvm::relay::SparseToDenseAttrs</a></div><div class="ttdoc">Attributes used in sparse_to_dense operator. </div><div class="ttdef"><b>Definition:</b> transform.h:450</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html_ab623ebb33e110ab0eeefbf30528a5be3"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html#ab623ebb33e110ab0eeefbf30528a5be3">tvm::relay::MeshgridAttrs::indexing</a></div><div class="ttdeci">std::string indexing</div><div class="ttdef"><b>Definition:</b> transform.h:244</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html">tvm::relay::SparseToDenseAttrs</a></div><div class="ttdoc">Attributes used in sparse_to_dense operator. </div><div class="ttdef"><b>Definition:</b> transform.h:453</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html_ab623ebb33e110ab0eeefbf30528a5be3"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html#ab623ebb33e110ab0eeefbf30528a5be3">tvm::relay::MeshgridAttrs::indexing</a></div><div class="ttdeci">std::string indexing</div><div class="ttdef"><b>Definition:</b> transform.h:247</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1DynExpandDimsAttrs_html_a5a0dbf8383656b0c5f6181ee5581881b"><div class="ttname"><a href="structtvm_1_1relay_1_1DynExpandDimsAttrs.html#a5a0dbf8383656b0c5f6181ee5581881b">tvm::relay::DynExpandDimsAttrs::num_newaxis</a></div><div class="ttdeci">int num_newaxis</div><div class="ttdef"><b>Definition:</b> transform.h:88</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SlidingWindowAttrs_html_a5ebc3832fc40189627f9f423623a2cdd"><div class="ttname"><a href="structtvm_1_1relay_1_1SlidingWindowAttrs.html#a5ebc3832fc40189627f9f423623a2cdd">tvm::relay::SlidingWindowAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SlidingWindowAttrs, "relay.attrs.SlidingWindowAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:41</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a6c2ed7bdf83375c58a687b7698f4cc05"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a6c2ed7bdf83375c58a687b7698f4cc05">tvm::relay::AutoSchedulerLayoutTransformAttrs::src_layout</a></div><div class="ttdeci">std::string src_layout</div><div class="ttdef"><b>Definition:</b> transform.h:418</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html_a6c2ed7bdf83375c58a687b7698f4cc05"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html#a6c2ed7bdf83375c58a687b7698f4cc05">tvm::relay::AutoSchedulerLayoutTransformAttrs::src_layout</a></div><div class="ttdeci">std::string src_layout</div><div class="ttdef"><b>Definition:</b> transform.h:421</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1TransposeAttrs_html_a99db019c5b5fe6ac6fa59f566a72bad6"><div class="ttname"><a href="structtvm_1_1relay_1_1TransposeAttrs.html#a99db019c5b5fe6ac6fa59f566a72bad6">tvm::relay::TransposeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(TransposeAttrs, "relay.attrs.TransposeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:113</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_a205a39a589b271918a3f562a91a123b1"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#a205a39a589b271918a3f562a91a123b1">tvm::relay::SplitAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SplitAttrs, "relay.attrs.SplitAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:330</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html">tvm::relay::NdarraySizeAttrs</a></div><div class="ttdoc">Attributes for ndarray_size operator. </div><div class="ttdef"><b>Definition:</b> transform.h:459</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_aefeb0aab0b9793cbf4b22cb9c1063d4e"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#aefeb0aab0b9793cbf4b22cb9c1063d4e">tvm::relay::StridedSliceAttrs::axes</a></div><div class="ttdeci">Optional< Array< Integer > > axes</div><div class="ttdef"><b>Definition:</b> transform.h:348</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterNDAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html">tvm::relay::ScatterNDAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:163</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html_ad927fd556dd3d0bbedff021bcb5ca502"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html#ad927fd556dd3d0bbedff021bcb5ca502">tvm::relay::MeshgridAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(MeshgridAttrs, "relay.attrs.MeshgridAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:246</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html">tvm::relay::StackAttrs</a></div><div class="ttdoc">Attributes used in stack operators. </div><div class="ttdef"><b>Definition:</b> transform.h:256</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_ac5095656867b0bad8cd53d0f957a1d9d"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#ac5095656867b0bad8cd53d0f957a1d9d">tvm::relay::FixedPointMultiplyAttrs::shift</a></div><div class="ttdeci">int32_t shift</div><div class="ttdef"><b>Definition:</b> transform.h:394</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html">tvm::relay::TakeAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:196</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SplitAttrs_html_a205a39a589b271918a3f562a91a123b1"><div class="ttname"><a href="structtvm_1_1relay_1_1SplitAttrs.html#a205a39a589b271918a3f562a91a123b1">tvm::relay::SplitAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(SplitAttrs, "relay.attrs.SplitAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:333</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html">tvm::relay::NdarraySizeAttrs</a></div><div class="ttdoc">Attributes for ndarray_size operator. </div><div class="ttdef"><b>Definition:</b> transform.h:462</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_aefeb0aab0b9793cbf4b22cb9c1063d4e"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#aefeb0aab0b9793cbf4b22cb9c1063d4e">tvm::relay::StridedSliceAttrs::axes</a></div><div class="ttdeci">Optional< Array< Integer > > axes</div><div class="ttdef"><b>Definition:</b> transform.h:351</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterNDAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterNDAttrs.html">tvm::relay::ScatterNDAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:166</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MeshgridAttrs_html_ad927fd556dd3d0bbedff021bcb5ca502"><div class="ttname"><a href="structtvm_1_1relay_1_1MeshgridAttrs.html#ad927fd556dd3d0bbedff021bcb5ca502">tvm::relay::MeshgridAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(MeshgridAttrs, "relay.attrs.MeshgridAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:249</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html">tvm::relay::StackAttrs</a></div><div class="ttdoc">Attributes used in stack operators. </div><div class="ttdef"><b>Definition:</b> transform.h:259</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_ac5095656867b0bad8cd53d0f957a1d9d"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#ac5095656867b0bad8cd53d0f957a1d9d">tvm::relay::FixedPointMultiplyAttrs::shift</a></div><div class="ttdeci">int32_t shift</div><div class="ttdef"><b>Definition:</b> transform.h:397</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html">tvm::relay::TakeAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:199</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SlidingWindowAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SlidingWindowAttrs.html">tvm::relay::SlidingWindowAttrs</a></div><div class="ttdoc">Attributes used for the sliding_window operator. </div><div class="ttdef"><b>Definition:</b> transform.h:37</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a89976b047aa6fa83747077ed0260a5aa"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a89976b047aa6fa83747077ed0260a5aa">tvm::relay::SequenceMaskAttrs::mask_value</a></div><div class="ttdeci">double mask_value</div><div class="ttdef"><b>Definition:</b> transform.h:439</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html_a58d630300fa3ce26c47a6ba7a7362fab"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html#a58d630300fa3ce26c47a6ba7a7362fab">tvm::relay::NdarraySizeAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:460</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html_a89976b047aa6fa83747077ed0260a5aa"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html#a89976b047aa6fa83747077ed0260a5aa">tvm::relay::SequenceMaskAttrs::mask_value</a></div><div class="ttdeci">double mask_value</div><div class="ttdef"><b>Definition:</b> transform.h:442</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1NdarraySizeAttrs_html_a58d630300fa3ce26c47a6ba7a7362fab"><div class="ttname"><a href="structtvm_1_1relay_1_1NdarraySizeAttrs.html#a58d630300fa3ce26c47a6ba7a7362fab">tvm::relay::NdarraySizeAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:463</div></div>
<div class="ttc" id="classtvm_1_1AttrsNode_html"><div class="ttname"><a href="classtvm_1_1AttrsNode.html">tvm::AttrsNode</a></div><div class="ttdoc">The base class of the all the Use "curiously recurring template pattern". </div><div class="ttdef"><b>Definition:</b> attrs.h:834</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html_a4971bcf217d49330d12c48997274f264"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html#a4971bcf217d49330d12c48997274f264">tvm::relay::ShapeOfAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:431</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a1acfc2cf9788e7bef4798d059bd72aee"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a1acfc2cf9788e7bef4798d059bd72aee">tvm::relay::MatrixSetDiagAttrs::sub_diag_right_align</a></div><div class="ttdeci">bool sub_diag_right_align</div><div class="ttdef"><b>Definition:</b> transform.h:485</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_a66c911549720cca0fcc461a707b47a75"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#a66c911549720cca0fcc461a707b47a75">tvm::relay::ReverseSequenceAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReverseSequenceAttrs, "relay.attrs.ReverseSequenceAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:301</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a8ebfd7b6ec520741643adb6742ffdfd5"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a8ebfd7b6ec520741643adb6742ffdfd5">tvm::relay::MatrixSetDiagAttrs::k1</a></div><div class="ttdeci">int k1</div><div class="ttdef"><b>Definition:</b> transform.h:482</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_aabe51ead537f676d53ffedf91b16ae66"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#aabe51ead537f676d53ffedf91b16ae66">tvm::relay::ArangeAttrs::step</a></div><div class="ttdeci">Expr step</div><div class="ttdef"><b>Definition:</b> transform.h:231</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html">tvm::relay::RepeatAttrs</a></div><div class="ttdoc">Attributes used in repeat operators. </div><div class="ttdef"><b>Definition:</b> transform.h:265</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ab8c4942d4242425714b21488bae72fec"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ab8c4942d4242425714b21488bae72fec">tvm::relay::StridedSliceAttrs::strides</a></div><div class="ttdeci">Optional< Array< Integer > > strides</div><div class="ttdef"><b>Definition:</b> transform.h:346</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html">tvm::relay::SqueezeAttrs</a></div><div class="ttdoc">Attributes used in squeeze operators. </div><div class="ttdef"><b>Definition:</b> transform.h:311</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html_a4971bcf217d49330d12c48997274f264"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html#a4971bcf217d49330d12c48997274f264">tvm::relay::ShapeOfAttrs::dtype</a></div><div class="ttdeci">DataType dtype</div><div class="ttdef"><b>Definition:</b> transform.h:434</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a1acfc2cf9788e7bef4798d059bd72aee"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a1acfc2cf9788e7bef4798d059bd72aee">tvm::relay::MatrixSetDiagAttrs::sub_diag_right_align</a></div><div class="ttdeci">bool sub_diag_right_align</div><div class="ttdef"><b>Definition:</b> transform.h:488</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_a66c911549720cca0fcc461a707b47a75"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#a66c911549720cca0fcc461a707b47a75">tvm::relay::ReverseSequenceAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ReverseSequenceAttrs, "relay.attrs.ReverseSequenceAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:304</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a8ebfd7b6ec520741643adb6742ffdfd5"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a8ebfd7b6ec520741643adb6742ffdfd5">tvm::relay::MatrixSetDiagAttrs::k1</a></div><div class="ttdeci">int k1</div><div class="ttdef"><b>Definition:</b> transform.h:485</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ArangeAttrs_html_aabe51ead537f676d53ffedf91b16ae66"><div class="ttname"><a href="structtvm_1_1relay_1_1ArangeAttrs.html#aabe51ead537f676d53ffedf91b16ae66">tvm::relay::ArangeAttrs::step</a></div><div class="ttdeci">Expr step</div><div class="ttdef"><b>Definition:</b> transform.h:234</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html">tvm::relay::RepeatAttrs</a></div><div class="ttdoc">Attributes used in repeat operators. </div><div class="ttdef"><b>Definition:</b> transform.h:268</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_ab8c4942d4242425714b21488bae72fec"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#ab8c4942d4242425714b21488bae72fec">tvm::relay::StridedSliceAttrs::strides</a></div><div class="ttdeci">Optional< Array< Integer > > strides</div><div class="ttdef"><b>Definition:</b> transform.h:349</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html">tvm::relay::SqueezeAttrs</a></div><div class="ttdoc">Attributes used in squeeze operators. </div><div class="ttdef"><b>Definition:</b> transform.h:314</div></div>
<div class="ttc" id="relay_2base_8h_html"><div class="ttname"><a href="relay_2base_8h.html">base.h</a></div><div class="ttdoc">Base classes for the Relay IR. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Optional_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Optional.html">tvm::runtime::Optional</a></div><div class="ttdoc">Optional container that to represent to a Nullable variant of T. </div><div class="ttdef"><b>Definition:</b> optional.h:51</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_ab7f5ccbb4c1f408da1f7a9d76c35fcf4"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#ab7f5ccbb4c1f408da1f7a9d76c35fcf4">tvm::relay::LayoutTransformAttrs::dst_layout</a></div><div class="ttdeci">std::string dst_layout</div><div class="ttdef"><b>Definition:</b> transform.h:407</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html_ac12e95580d7c77a3f7221c528ab3bcb2"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html#ac12e95580d7c77a3f7221c528ab3bcb2">tvm::relay::SqueezeAttrs::axis</a></div><div class="ttdeci">Array< Integer > axis</div><div class="ttdef"><b>Definition:</b> transform.h:313</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_a3922777717859c05ff19eb0690a4529e"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#a3922777717859c05ff19eb0690a4529e">tvm::relay::RepeatAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(RepeatAttrs, "relay.attrs.RepeatAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:268</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1LayoutTransformAttrs_html_ab7f5ccbb4c1f408da1f7a9d76c35fcf4"><div class="ttname"><a href="structtvm_1_1relay_1_1LayoutTransformAttrs.html#ab7f5ccbb4c1f408da1f7a9d76c35fcf4">tvm::relay::LayoutTransformAttrs::dst_layout</a></div><div class="ttdeci">std::string dst_layout</div><div class="ttdef"><b>Definition:</b> transform.h:410</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SqueezeAttrs_html_ac12e95580d7c77a3f7221c528ab3bcb2"><div class="ttname"><a href="structtvm_1_1relay_1_1SqueezeAttrs.html#ac12e95580d7c77a3f7221c528ab3bcb2">tvm::relay::SqueezeAttrs::axis</a></div><div class="ttdeci">Array< Integer > axis</div><div class="ttdef"><b>Definition:</b> transform.h:316</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_a3922777717859c05ff19eb0690a4529e"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#a3922777717859c05ff19eb0690a4529e">tvm::relay::RepeatAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(RepeatAttrs, "relay.attrs.RepeatAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:271</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ConcatenateAttrs_html_adfcdf16b2e6e74b0e88b3886384e8077"><div class="ttname"><a href="structtvm_1_1relay_1_1ConcatenateAttrs.html#adfcdf16b2e6e74b0e88b3886384e8077">tvm::relay::ConcatenateAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> transform.h:100</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html">tvm::relay::AutoSchedulerLayoutTransformAttrs</a></div><div class="ttdoc">Attributes for AutoSchedulerLayoutTransform operator. </div><div class="ttdef"><b>Definition:</b> transform.h:416</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1AutoSchedulerLayoutTransformAttrs.html">tvm::relay::AutoSchedulerLayoutTransformAttrs</a></div><div class="ttdoc">Attributes for AutoSchedulerLayoutTransform operator. </div><div class="ttdef"><b>Definition:</b> transform.h:419</div></div>
<div class="ttc" id="namespacetvm_html_ab6c242e8ac09beb463fba306948b7f15"><div class="ttname"><a href="namespacetvm.html#ab6c242e8ac09beb463fba306948b7f15">tvm::NullValue</a></div><div class="ttdeci">TObjectRef NullValue()</div><div class="ttdoc">Create a NodeRef type that represents null. </div><div class="ttdef"><b>Definition:</b> attrs.h:84</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a7a3061c9224a6b2f36d1237d88d68e33"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a7a3061c9224a6b2f36d1237d88d68e33">tvm::relay::TakeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(TakeAttrs, "relay.attrs.TakeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:201</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html">tvm::relay::SequenceMaskAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:438</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a6d8d5503c7880be0e179c0f54972afad"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a6d8d5503c7880be0e179c0f54972afad">tvm::relay::ReshapeLikeAttrs::rhs_end</a></div><div class="ttdeci">Integer rhs_end</div><div class="ttdef"><b>Definition:</b> transform.h:132</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html">tvm::relay::ReverseSequenceAttrs</a></div><div class="ttdoc">Attributes used in reverse_sequence operators. </div><div class="ttdef"><b>Definition:</b> transform.h:297</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a7a3061c9224a6b2f36d1237d88d68e33"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a7a3061c9224a6b2f36d1237d88d68e33">tvm::relay::TakeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(TakeAttrs, "relay.attrs.TakeAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:204</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SequenceMaskAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SequenceMaskAttrs.html">tvm::relay::SequenceMaskAttrs</a></div><div class="ttdef"><b>Definition:</b> transform.h:441</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReshapeLikeAttrs_html_a6d8d5503c7880be0e179c0f54972afad"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeLikeAttrs.html#a6d8d5503c7880be0e179c0f54972afad">tvm::relay::ReshapeLikeAttrs::rhs_end</a></div><div class="ttdeci">Integer rhs_end</div><div class="ttdef"><b>Definition:</b> transform.h:135</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html">tvm::relay::ReverseSequenceAttrs</a></div><div class="ttdoc">Attributes used in reverse_sequence operators. </div><div class="ttdef"><b>Definition:</b> transform.h:300</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ReshapeAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></div><div class="ttdoc">Attributes used in reshape operators. </div><div class="ttdef"><b>Definition:</b> transform.h:119</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_ac5ca397146a579021c2915226785b547"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#ac5ca397146a579021c2915226785b547">tvm::relay::GatherNDAttrs::index_rank</a></div><div class="ttdeci">Optional< Integer > index_rank</div><div class="ttdef"><b>Definition:</b> transform.h:184</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_ab42aac00000fd8bf664ce05d971d683f"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#ab42aac00000fd8bf664ce05d971d683f">tvm::relay::OneHotAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(OneHotAttrs, "relay.attrs.OneHotAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:473</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html_a641f7409b6194a04a6a9889fe19dc3fb"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html#a641f7409b6194a04a6a9889fe19dc3fb">tvm::relay::ScatterAddAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:156</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html">tvm::relay::ShapeOfAttrs</a></div><div class="ttdoc">Attributes for ShapeOf operator. </div><div class="ttdef"><b>Definition:</b> transform.h:430</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html_afebf3efdcef2b99e2515056a464dcdc0"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html#afebf3efdcef2b99e2515056a464dcdc0">tvm::relay::GatherAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:173</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_a3c6d3993844391992ebe9702a2f1b87b"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#a3c6d3993844391992ebe9702a2f1b87b">tvm::relay::ScanopAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScanopAttrs, "relay.attrs.ScanopAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:504</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html_a96725ff7c8a481e81a2fd0ad163b4ecf"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html#a96725ff7c8a481e81a2fd0ad163b4ecf">tvm::relay::SparseToDenseAttrs::output_shape</a></div><div class="ttdeci">Array< Integer > output_shape</div><div class="ttdef"><b>Definition:</b> transform.h:451</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_a2492ceafc309edf983ba8c78fae5afe2"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#a2492ceafc309edf983ba8c78fae5afe2">tvm::relay::StridedSliceAttrs::end</a></div><div class="ttdeci">Optional< Array< Integer > > end</div><div class="ttdef"><b>Definition:</b> transform.h:345</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_a91f67f0c8914efd2b7359eea9074b43f"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#a91f67f0c8914efd2b7359eea9074b43f">tvm::relay::RepeatAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:267</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html_a5baf92c2303bbdabf5aa90f1ab66ad12"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html#a5baf92c2303bbdabf5aa90f1ab66ad12">tvm::relay::StackAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:257</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_a2811e219660dbb0834e6b46b5725ae95"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#a2811e219660dbb0834e6b46b5725ae95">tvm::relay::FixedPointMultiplyAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(FixedPointMultiplyAttrs, "relay.attrs.FixedPointMultiplyAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:396</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a181f59c653c46220afdd98605b6d6e34"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a181f59c653c46220afdd98605b6d6e34">tvm::relay::MatrixSetDiagAttrs::k2</a></div><div class="ttdeci">int k2</div><div class="ttdef"><b>Definition:</b> transform.h:483</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherNDAttrs_html_ac5ca397146a579021c2915226785b547"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherNDAttrs.html#ac5ca397146a579021c2915226785b547">tvm::relay::GatherNDAttrs::index_rank</a></div><div class="ttdeci">Optional< Integer > index_rank</div><div class="ttdef"><b>Definition:</b> transform.h:187</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1OneHotAttrs_html_ab42aac00000fd8bf664ce05d971d683f"><div class="ttname"><a href="structtvm_1_1relay_1_1OneHotAttrs.html#ab42aac00000fd8bf664ce05d971d683f">tvm::relay::OneHotAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(OneHotAttrs, "relay.attrs.OneHotAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:476</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScatterAddAttrs_html_a641f7409b6194a04a6a9889fe19dc3fb"><div class="ttname"><a href="structtvm_1_1relay_1_1ScatterAddAttrs.html#a641f7409b6194a04a6a9889fe19dc3fb">tvm::relay::ScatterAddAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:159</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ShapeOfAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ShapeOfAttrs.html">tvm::relay::ShapeOfAttrs</a></div><div class="ttdoc">Attributes for ShapeOf operator. </div><div class="ttdef"><b>Definition:</b> transform.h:433</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1GatherAttrs_html_afebf3efdcef2b99e2515056a464dcdc0"><div class="ttname"><a href="structtvm_1_1relay_1_1GatherAttrs.html#afebf3efdcef2b99e2515056a464dcdc0">tvm::relay::GatherAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:176</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ScanopAttrs_html_a3c6d3993844391992ebe9702a2f1b87b"><div class="ttname"><a href="structtvm_1_1relay_1_1ScanopAttrs.html#a3c6d3993844391992ebe9702a2f1b87b">tvm::relay::ScanopAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(ScanopAttrs, "relay.attrs.ScanopAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:507</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1SparseToDenseAttrs_html_a96725ff7c8a481e81a2fd0ad163b4ecf"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseToDenseAttrs.html#a96725ff7c8a481e81a2fd0ad163b4ecf">tvm::relay::SparseToDenseAttrs::output_shape</a></div><div class="ttdeci">Array< Integer > output_shape</div><div class="ttdef"><b>Definition:</b> transform.h:454</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StridedSliceAttrs_html_a2492ceafc309edf983ba8c78fae5afe2"><div class="ttname"><a href="structtvm_1_1relay_1_1StridedSliceAttrs.html#a2492ceafc309edf983ba8c78fae5afe2">tvm::relay::StridedSliceAttrs::end</a></div><div class="ttdeci">Optional< Array< Integer > > end</div><div class="ttdef"><b>Definition:</b> transform.h:348</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1RepeatAttrs_html_a91f67f0c8914efd2b7359eea9074b43f"><div class="ttname"><a href="structtvm_1_1relay_1_1RepeatAttrs.html#a91f67f0c8914efd2b7359eea9074b43f">tvm::relay::RepeatAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:270</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1StackAttrs_html_a5baf92c2303bbdabf5aa90f1ab66ad12"><div class="ttname"><a href="structtvm_1_1relay_1_1StackAttrs.html#a5baf92c2303bbdabf5aa90f1ab66ad12">tvm::relay::StackAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:260</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1FixedPointMultiplyAttrs_html_a2811e219660dbb0834e6b46b5725ae95"><div class="ttname"><a href="structtvm_1_1relay_1_1FixedPointMultiplyAttrs.html#a2811e219660dbb0834e6b46b5725ae95">tvm::relay::FixedPointMultiplyAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(FixedPointMultiplyAttrs, "relay.attrs.FixedPointMultiplyAttrs")</div><div class="ttdef"><b>Definition:</b> transform.h:399</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1MatrixSetDiagAttrs_html_a181f59c653c46220afdd98605b6d6e34"><div class="ttname"><a href="structtvm_1_1relay_1_1MatrixSetDiagAttrs.html#a181f59c653c46220afdd98605b6d6e34">tvm::relay::MatrixSetDiagAttrs::k2</a></div><div class="ttdeci">int k2</div><div class="ttdef"><b>Definition:</b> transform.h:486</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ConcatenateAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ConcatenateAttrs.html">tvm::relay::ConcatenateAttrs</a></div><div class="ttdoc">Attributes used in concatenate operators. </div><div class="ttdef"><b>Definition:</b> transform.h:99</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_a922eb49dd420d3a148f206efca0e0b48"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#a922eb49dd420d3a148f206efca0e0b48">tvm::relay::ReverseSequenceAttrs::batch_axis</a></div><div class="ttdeci">Integer batch_axis</div><div class="ttdef"><b>Definition:</b> transform.h:299</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1ReverseSequenceAttrs_html_a922eb49dd420d3a148f206efca0e0b48"><div class="ttname"><a href="structtvm_1_1relay_1_1ReverseSequenceAttrs.html#a922eb49dd420d3a148f206efca0e0b48">tvm::relay::ReverseSequenceAttrs::batch_axis</a></div><div class="ttdeci">Integer batch_axis</div><div class="ttdef"><b>Definition:</b> transform.h:302</div></div>
<div class="ttc" id="classtvm_1_1Integer_html"><div class="ttname"><a href="classtvm_1_1Integer.html">tvm::Integer</a></div><div class="ttdoc">Container of constant int that adds more constructors. </div><div class="ttdef"><b>Definition:</b> expr.h:403</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a5d4f821c5541cb9deb71d835b144cb22"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a5d4f821c5541cb9deb71d835b144cb22">tvm::relay::TakeAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:198</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1TakeAttrs_html_a5d4f821c5541cb9deb71d835b144cb22"><div class="ttname"><a href="structtvm_1_1relay_1_1TakeAttrs.html#a5d4f821c5541cb9deb71d835b144cb22">tvm::relay::TakeAttrs::axis</a></div><div class="ttdeci">Integer axis</div><div class="ttdef"><b>Definition:</b> transform.h:201</div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/relay_2expr__functor_8h_source.html b/docs/reference/api/doxygen/relay_2expr__functor_8h_source.html
index ab7141b1b..b9ab4c73c 100644
--- a/docs/reference/api/doxygen/relay_2expr__functor_8h_source.html
+++ b/docs/reference/api/doxygen/relay_2expr__functor_8h_source.html
@@ -126,7 +126,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1relay_html_a18f47bbeaf5ccedf5e4cf525710a0c41"><div class="ttname"><a href="namespacetvm_1_1relay.html#a18f47bbeaf5ccedf5e4cf525710a0c41">tvm::relay::ExpandANormalForm</a></div><div class="ttdeci">void ExpandANormalForm(const LetNode *op, std::function< void(const LetNode *)> pre_visit, std::function< void(const LetNode *)> post_visit)</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1ExprFunctor_3_01R_07const_01Expr_01_6n_00_01Args_8_8_8_08_4_html"><div class="ttname"><a href="classtvm_1_1relay_1_1ExprFunctor_3_01R_07const_01Expr_01_6n_00_01Args_8_8_8_08_4.html">tvm::relay::ExprFunctor< R(const Expr &n, Args...)></a></div><div class="ttdef"><b>Definition:</b> expr_functor.h:68</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_a17d8d5ad92691f9e18e3e0ae8ef69e4f"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#a17d8d5ad92691f9e18e3e0ae8ef69e4f">tvm::runtime::ObjectRef::defined</a></div><div class="ttdeci">bool defined() const</div><div class="ttdef"><b>Definition:</b> object.h:544</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_acb438962b08475a05e086907bf8eb26a"><div class="ttname"><a href="namespacetvm_1_1topi.html#acb438962b08475a05e086907bf8eb26a">tvm::topi::stack</a></div><div class="ttdeci">Tensor stack(const Array< Tensor > &inputs, int axis=0, std::string name="T_stack", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along a new axis. </div><div class="ttdef"><b>Definition:</b> transform.h:527</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_acb438962b08475a05e086907bf8eb26a"><div class="ttname"><a href="namespacetvm_1_1topi.html#acb438962b08475a05e086907bf8eb26a">tvm::topi::stack</a></div><div class="ttdeci">Tensor stack(const Array< Tensor > &inputs, int axis=0, std::string name="T_stack", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along a new axis. </div><div class="ttdef"><b>Definition:</b> transform.h:528</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1ExprFunctor_3_01R_07const_01Expr_01_6n_00_01Args_8_8_8_08_4_html_a9259dfd39c812685890921178980e10a"><div class="ttname"><a href="classtvm_1_1relay_1_1ExprFunctor_3_01R_07const_01Expr_01_6n_00_01Args_8_8_8_08_4.html#a9259dfd39c812685890921178980e10a">tvm::relay::ExprFunctor< R(const Expr &n, Args...)>::VisitExpr_</a></div><div class="ttdeci">virtual R VisitExpr_(const ConstructorNode *op, Args... args)</div><div class="ttdef"><b>Definiti [...]
<div class="ttc" id="classtvm_1_1relay_1_1FunctionNode_html"><div class="ttname"><a href="classtvm_1_1relay_1_1FunctionNode.html">tvm::relay::FunctionNode</a></div><div class="ttdoc">Relay Function container. </div><div class="ttdef"><b>Definition:</b> function.h:39</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1ExprVisitor_html_a8fda55f01b88a56b25770a66ea988152"><div class="ttname"><a href="classtvm_1_1relay_1_1ExprVisitor.html#a8fda55f01b88a56b25770a66ea988152">tvm::relay::ExprVisitor::VisitPattern</a></div><div class="ttdeci">virtual void VisitPattern(const Pattern &c)</div></div>
diff --git a/docs/reference/api/doxygen/search/all_11.js b/docs/reference/api/doxygen/search/all_11.js
index 83413fcd5..12e511ba2 100644
--- a/docs/reference/api/doxygen/search/all_11.js
+++ b/docs/reference/api/doxygen/search/all_11.js
@@ -33,7 +33,7 @@ var searchData=
['page_5fallocator_2eh',['page_allocator.h',['../page__allocator_8h.html',1,'']]],
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
['papi_2eh',['papi.h',['../papi_8h.html',1,'']]],
- ['parallel',['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()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()']]],
+ ['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']]],
['parallel_5ffor_2eh',['parallel_for.h',['../parallel__for_8h.html',1,'']]],
['parallel_5ffor_5fdynamic',['parallel_for_dynamic',['../namespacetvm_1_1support.html#afe4271363c794f1644ce7af5c2266530',1,'tvm::support']]],
diff --git a/docs/reference/api/doxygen/search/all_13.js b/docs/reference/api/doxygen/search/all_13.js
index c7fdcd295..d8fcdb43f 100644
--- a/docs/reference/api/doxygen/search/all_13.js
+++ b/docs/reference/api/doxygen/search/all_13.js
@@ -79,7 +79,7 @@ var searchData=
['registerconfigoption',['RegisterConfigOption',['../classtvm_1_1transform_1_1PassContext.html#a6f1d1040cc97320414b4690203f87919',1,'tvm::transform::PassContext']]],
['registergenericfunc',['RegisterGenericFunc',['../classtvm_1_1GenericFunc.html#a909acecbf2f34f847a34e587a4570dce',1,'tvm::GenericFunc']]],
['registerorget',['RegisterOrGet',['../classtvm_1_1OpRegEntry.html#a39a4d3e7f905eb4e29ca464bcedb05bd',1,'tvm::OpRegEntry::RegisterOrGet()'],['../classtvm_1_1relay_1_1ExecutorRegEntry.html#a03347a2b68269b853a7c0399994951ef',1,'tvm::relay::ExecutorRegEntry::RegisterOrGet()'],['../classtvm_1_1relay_1_1RuntimeRegEntry.html#ae8b479159ccd8b35b75950fcda58dd9d',1,'tvm::relay::RuntimeRegEntry::RegisterOrGet()'],['../classtvm_1_1TargetTagRegEntry.html#a07e0631600484dc0985ca62b1620461c',1,'tvm::T [...]
- ['registry',['Registry',['../classtvm_1_1ReflectionVTable_1_1Registry.html',1,'tvm::ReflectionVTable::Registry'],['../classtvm_1_1runtime_1_1Registry.html',1,'tvm::runtime::Registry'],['../structTVMMutableFuncRegistry.html#acc1fcd6554c627c1bf3b3c00e1120e9b',1,'TVMMutableFuncRegistry::registry()'],['../structTVMModule.html#a6db21005b9e983207b341e65af4c4ab7',1,'TVMModule::registry()'],['../classtvm_1_1ReflectionVTable_1_1Registry.html#ac8f4637640aa9dffed745303a4cfa827',1,'tvm::Reflection [...]
+ ['registry',['Registry',['../classtvm_1_1ReflectionVTable_1_1Registry.html',1,'tvm::ReflectionVTable::Registry'],['../classtvm_1_1runtime_1_1Registry.html',1,'tvm::runtime::Registry'],['../classtvm_1_1ReflectionVTable_1_1Registry.html#ac8f4637640aa9dffed745303a4cfa827',1,'tvm::ReflectionVTable::Registry::Registry()'],['../structTVMMutableFuncRegistry.html#acc1fcd6554c627c1bf3b3c00e1120e9b',1,'TVMMutableFuncRegistry::registry()'],['../structTVMModule.html#a6db21005b9e983207b341e65af4c4a [...]
['registry_2eh',['registry.h',['../registry_8h.html',1,'']]],
['regname',['RegName',['../namespacetvm_1_1runtime_1_1vm.html#a3bbbf700719e9dc3dda2bc25210c18ae',1,'tvm::runtime::vm']]],
['reinterpret',['reinterpret',['../namespacetvm_1_1tir_1_1builtin.html#a7b555bc5cca2f5e7b26c1037bc0001ce',1,'tvm::tir::builtin::reinterpret()'],['../namespacetvm.html#a34084606675cd2c73c6b0f10e1618280',1,'tvm::reinterpret()'],['../namespacetvm_1_1topi.html#a25239505894bdae140e53f4abc146f92',1,'tvm::topi::reinterpret()']]],
@@ -111,7 +111,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
- ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
+ ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html',1,'tvm::auto_scheduler::ReorderStep'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array< Integer > &after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
['reorderstepnode',['ReorderStepNode',['../classtvm_1_1auto__scheduler_1_1ReorderStepNode.html',1,'tvm::auto_scheduler']]],
['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
@@ -135,7 +135,7 @@ var searchData=
['required',['required',['../classtvm_1_1transform_1_1PassInfoNode.html#abc4fdfbc0e6db41ae6296d7b2816b534',1,'tvm::transform::PassInfoNode']]],
['required_5fpass',['required_pass',['../classtvm_1_1transform_1_1PassContextNode.html#a029074685b6cfcc0431098697f2bc927',1,'tvm::transform::PassContextNode']]],
['reserve',['reserve',['../classtvm_1_1runtime_1_1Array.html#a1a7727b86efaf35c58a5198ab1c139c8',1,'tvm::runtime::Array']]],
- ['reset',['Reset',['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a73b14ea360a9902c291d5bf6e97636cd',1,'tvm::auto_scheduler::ProgramMeasurerNode::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#ae6279154fe70e9eb85937b51e70a4bf8',1,'tvm::runtime::micro_rpc::Unframer::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Framer.html#a44ff9650ecca8785e33c25c369d2570a',1,'tvm::runtime::micro_rpc::Framer::Reset()'],['../classtvm_1_1tir_1_1StmtSRefNode.html#a0a81 [...]
+ ['reset',['reset',['../classtvm_1_1runtime_1_1NDArray.html#af2a8ccab95d432d1ecad7a389e11bcd3',1,'tvm::runtime::NDArray::reset()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#ac4461465ba0e785794794e0405c96590',1,'tvm::runtime::ObjectPtr::reset()'],['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a73b14ea360a9902c291d5bf6e97636cd',1,'tvm::auto_scheduler::ProgramMeasurerNode::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#ae6279154fe70e9eb85937b51e70a4bf8',1, [...]
['reset_5fattr',['reset_attr',['../classtvm_1_1OpRegEntry.html#a67628f8d3d6dea5b0a47e462c06b7790',1,'tvm::OpRegEntry']]],
['resetthreadpool',['ResetThreadPool',['../namespacetvm_1_1runtime_1_1threading.html#aafdb21c00248ff146b614a7e888b4fd7',1,'tvm::runtime::threading']]],
['reshape',['reshape',['../namespacetvm_1_1topi.html#a3aad65f2505802109ba7d05359ce9005',1,'tvm::topi']]],
@@ -181,7 +181,7 @@ var searchData=
['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a190932261c8574b7e85e804938f8ad0d',1,'tvm::meta_schedule::Postproc']]],
['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
- ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
+ ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html',1,'tvm::auto_scheduler::RfactorStep'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
['rfactorstepnode',['RfactorStepNode',['../classtvm_1_1auto__scheduler_1_1RfactorStepNode.html',1,'tvm::auto_scheduler']]],
['rhs',['rhs',['../classtvm_1_1relay_1_1ClauseNode.html#a93217eeea15c1f7c1a659da3da86d3bd',1,'tvm::relay::ClauseNode::rhs()'],['../classtvm_1_1tir_1_1CommReducerNode.html#a2902b0d55dd823febc6941fae9f32337',1,'tvm::tir::CommReducerNode::rhs()']]],
diff --git a/docs/reference/api/doxygen/search/all_14.js b/docs/reference/api/doxygen/search/all_14.js
index f91e8221e..5c2cc0dc5 100644
--- a/docs/reference/api/doxygen/search/all_14.js
+++ b/docs/reference/api/doxygen/search/all_14.js
@@ -91,7 +91,7 @@ var searchData=
['selectshashreduce_3c_20t_2c_20traitname_2c_20false_20_3e',['SelectSHashReduce< T, TraitName, false >',['../structtvm_1_1detail_1_1SelectSHashReduce_3_01T_00_01TraitName_00_01false_01_4.html',1,'tvm::detail']]],
['selectvisitattrs',['SelectVisitAttrs',['../structtvm_1_1detail_1_1SelectVisitAttrs.html',1,'tvm::detail']]],
['selectvisitattrs_3c_20t_2c_20traitname_2c_20false_20_3e',['SelectVisitAttrs< T, TraitName, false >',['../structtvm_1_1detail_1_1SelectVisitAttrs_3_01T_00_01TraitName_00_01false_01_4.html',1,'tvm::detail']]],
- ['self',['self',['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a5bac4439279428fb3c0d44aa6b1cc798',1,'tvm::runtime::MapNode::iterator::self()'],['../classtvm_1_1runtime_1_1InplaceArrayBase.html#ae447f7c7a742fb3f5613a632706509df',1,'tvm::runtime::InplaceArrayBase::Self()']]],
+ ['self',['Self',['../classtvm_1_1runtime_1_1InplaceArrayBase.html#ae447f7c7a742fb3f5613a632706509df',1,'tvm::runtime::InplaceArrayBase::Self()'],['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a5bac4439279428fb3c0d44aa6b1cc798',1,'tvm::runtime::MapNode::iterator::self()']]],
['sendbodychunk',['SendBodyChunk',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a37b77101825145283cced6cd05eb502c',1,'tvm::runtime::micro_rpc::Session']]],
['sendmessage',['SendMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#a6e540521a7e9188564da712c0641619c',1,'tvm::runtime::micro_rpc::Session']]],
['seq',['seq',['../classtvm_1_1tir_1_1SeqStmtNode.html#a0e548955529d35c56e646fcaac38f865',1,'tvm::tir::SeqStmtNode']]],
@@ -237,7 +237,7 @@ var searchData=
['solvelinearequations',['SolveLinearEquations',['../namespacetvm_1_1arith.html#ae0290f04432523ab8e5f76edde80071a',1,'tvm::arith']]],
['solvelinearinequalities',['SolveLinearInequalities',['../namespacetvm_1_1arith.html#ac59d63560e04431f108e81457b212fdc',1,'tvm::arith']]],
['sorted',['sorted',['../structtvm_1_1relay_1_1UniqueAttrs.html#aef434799646533ec9d796393ba01db44',1,'tvm::relay::UniqueAttrs']]],
- ['source',['Source',['../classtvm_1_1parser_1_1Source.html',1,'tvm::parser::Source'],['../classtvm_1_1parser_1_1Source.html#a0ef9f726abcc6c4c9e81b3a257055df8',1,'tvm::parser::Source::Source()'],['../classtvm_1_1arith_1_1IterMarkNode.html#a8b885a675c88e5a5d142fa68bcba048a',1,'tvm::arith::IterMarkNode::source()'],['../classtvm_1_1arith_1_1IterSplitExprNode.html#a7a129dc9b432359a07c1a1e286c3c66f',1,'tvm::arith::IterSplitExprNode::source()'],['../classtvm_1_1parser_1_1SourceNode.html#a51cc [...]
+ ['source',['Source',['../classtvm_1_1parser_1_1Source.html',1,'tvm::parser::Source'],['../classtvm_1_1arith_1_1IterMarkNode.html#a8b885a675c88e5a5d142fa68bcba048a',1,'tvm::arith::IterMarkNode::source()'],['../classtvm_1_1arith_1_1IterSplitExprNode.html#a7a129dc9b432359a07c1a1e286c3c66f',1,'tvm::arith::IterSplitExprNode::source()'],['../classtvm_1_1parser_1_1SourceNode.html#a51cc3c98e4cdacf0ffdc643c848e09af',1,'tvm::parser::SourceNode::source()'],['../classtvm_1_1tir_1_1ReduceNode.html# [...]
['source_5fmap',['source_map',['../classtvm_1_1IRModuleNode.html#a49470c0bfb4b85d9eda7576a837b7031',1,'tvm::IRModuleNode::source_map()'],['../classtvm_1_1parser_1_1SourceMapNode.html#ae22bc1181b066f17f8938868ef22610a',1,'tvm::parser::SourceMapNode::source_map()']]],
['source_5fmap_2eh',['source_map.h',['../source__map_8h.html',1,'']]],
['source_5fname',['source_name',['../classtvm_1_1DiagnosticBuilder.html#a92d320e1ede24fe5ff47862365002691',1,'tvm::DiagnosticBuilder::source_name()'],['../classtvm_1_1SpanNode.html#ad573167f93facbfbee19983b08bbba3d',1,'tvm::SpanNode::source_name()'],['../classtvm_1_1parser_1_1SourceNode.html#a8d4c50a18eb3e99b14d73d7db2a52af3',1,'tvm::parser::SourceNode::source_name()']]],
@@ -309,7 +309,7 @@ var searchData=
['stagenode',['StageNode',['../classtvm_1_1auto__scheduler_1_1StageNode.html',1,'tvm::auto_scheduler::StageNode'],['../classtvm_1_1te_1_1StageNode.html',1,'tvm::te::StageNode']]],
['stages',['stages',['../classtvm_1_1auto__scheduler_1_1StateNode.html#a881e14990bf228ee3fddb3721c451b9e',1,'tvm::auto_scheduler::StateNode::stages()'],['../classtvm_1_1te_1_1ScheduleNode.html#ab5649969db603d6b7b4d155c0d09cdd5',1,'tvm::te::ScheduleNode::stages()']]],
['stagetoaxesmap',['StageToAxesMap',['../namespacetvm_1_1auto__scheduler.html#a8f12e558fc4b8fbb990e7e204c06beeb',1,'tvm::auto_scheduler']]],
- ['start',['start',['../structtvm_1_1relay_1_1ArangeAttrs.html#ae8ae5bc1551b406a4f52395af343c2ce',1,'tvm::relay::ArangeAttrs::start()'],['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88',1,'tvm::runtime::profiling::Me [...]
+ ['start',['Start',['../classtvm_1_1runtime_1_1TimerNode.html#aa11fc338c39ee2137448e54a10efe0ae',1,'tvm::runtime::TimerNode::Start()'],['../classtvm_1_1runtime_1_1Timer.html#a89bcaa433499bc68902cb473d5eba6ca',1,'tvm::runtime::Timer::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a44fadfb7b0f961a7fb2275e3b5dbcd88',1,'tvm::runtime::profiling::MetricCollectorNode::Start()'],['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#aee5452075c8e022b8aaa6fb365f68e14 [...]
['start_5findex',['start_index',['../namespacetvm_1_1topi_1_1nn.html#a752c4130dac73fd2de0390c5f6b24b15',1,'tvm::topi::nn']]],
['startcall',['StartCall',['../classtvm_1_1runtime_1_1profiling_1_1Profiler.html#a1fe322f7ba92be44d7e7c8cb184f3833',1,'tvm::runtime::profiling::Profiler']]],
['startmessage',['StartMessage',['../classtvm_1_1runtime_1_1micro__rpc_1_1Session.html#acd512b977c6dd888f90c4fd6d2b9500f',1,'tvm::runtime::micro_rpc::Session']]],
diff --git a/docs/reference/api/doxygen/search/all_15.js b/docs/reference/api/doxygen/search/all_15.js
index 45ee238f6..eae8bacb6 100644
--- a/docs/reference/api/doxygen/search/all_15.js
+++ b/docs/reference/api/doxygen/search/all_15.js
@@ -32,7 +32,7 @@ var searchData=
['takeattrs',['TakeAttrs',['../structtvm_1_1relay_1_1TakeAttrs.html',1,'tvm::relay']]],
['tan',['tan',['../namespacetvm.html#af99838098788d40c80b402f29b3c2e8c',1,'tvm::tan()'],['../namespacetvm_1_1topi.html#a13b757fe52775f43a58d91c0a1330f97',1,'tvm::topi::tan()']]],
['tanh',['tanh',['../namespacetvm.html#a12c5457301d8a2c03a2ba1163edd7cee',1,'tvm::tanh()'],['../namespacetvm_1_1topi.html#aec153e599d33c78a7592007cde1c02cb',1,'tvm::topi::tanh()']]],
- ['target',['Target',['../classtvm_1_1Target.html',1,'tvm::Target'],['../classtvm_1_1auto__scheduler_1_1SearchTaskNode.html#acf4407e0c8dced81b05b34ec0426c933',1,'tvm::auto_scheduler::SearchTaskNode::target()'],['../classtvm_1_1meta__schedule_1_1BuilderInputNode.html#afc001f3e427cfc8c05236b615cfd2868',1,'tvm::meta_schedule::BuilderInputNode::target()'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#ab9cbbf8eb7941995e9c7552948eac02b',1,'tvm::meta_schedule::TuningRecordNode::targ [...]
+ ['target',['Target',['../classtvm_1_1Target.html',1,'tvm::Target'],['../classtvm_1_1Target.html#a58a5a1e042e265fe5a6973045226fe1a',1,'tvm::Target::Target(std::nullptr_t)'],['../classtvm_1_1Target.html#a77f3d7cc97d8cfd7172af58b4e784d89',1,'tvm::Target::Target(const String &tag_or_config_or_target_str)'],['../classtvm_1_1Target.html#ab825b350cf478bf948d807b6fdf636a0',1,'tvm::Target::Target(const Map< String, ObjectRef > &config)'],['../classtvm_1_1Target.html#a1abb29217d8e3 [...]
['target_2eh',['target.h',['../target_8h.html',1,'']]],
['target_5faccess',['target_access',['../structtvm_1_1PoolInfoNode.html#a78514ba53ee1471fa6069800c56c0612',1,'tvm::PoolInfoNode']]],
['target_5fburst_5fbytes',['target_burst_bytes',['../structtvm_1_1PoolInfoNode.html#a747c03e3eafc83b053637b735244c6d7',1,'tvm::PoolInfoNode']]],
@@ -147,7 +147,7 @@ var searchData=
['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
['tparent',['TParent',['../classtvm_1_1OpAttrMap.html#a316480ca7450209650fc1a62f7ce4a14',1,'tvm::OpAttrMap::TParent()'],['../classtvm_1_1TargetKindAttrMap.html#a37eb6bfb0d881cf897147b17ff7d3265',1,'tvm::TargetKindAttrMap::TParent()']]],
- ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::tra [...]
+ ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html',1,'tvm::tir::Trace'],['../classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29',1,'tvm::meta_schedule::TuningRecordNode::trace()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb [...]
['trace_2eh',['trace.h',['../trace_8h.html',1,'']]],
['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
['tracenode',['TraceNode',['../classtvm_1_1tir_1_1TraceNode.html',1,'tvm::tir']]],
diff --git a/docs/reference/api/doxygen/search/all_16.js b/docs/reference/api/doxygen/search/all_16.js
index 375a999ac..08dc5ba40 100644
--- a/docs/reference/api/doxygen/search/all_16.js
+++ b/docs/reference/api/doxygen/search/all_16.js
@@ -21,7 +21,7 @@ var searchData=
['units',['units',['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#a5373b2f2aac19653ae21aec74c69cdb0',1,'tvm::relay::BinaryDenseAttrs::units()'],['../structtvm_1_1relay_1_1MatmulAttrs.html#a5893df9ad99c6717c4e6cb440d60c6a1',1,'tvm::relay::MatmulAttrs::units()'],['../structtvm_1_1relay_1_1DenseAttrs.html#a497487f7ccced8c7492a5ed03f78fa8f',1,'tvm::relay::DenseAttrs::units()'],['../structtvm_1_1relay_1_1DensePackAttrs.html#aa0096c26c832166de13881a032ba3fbf',1,'tvm::relay::DensePackAttrs:: [...]
['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
- ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
+ ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
['update_5ffunc',['update_func',['../classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#ade9364c152a36501d4f24fa4f0111519',1,'tvm::auto_scheduler::PythonBasedModelNode']]],
diff --git a/docs/reference/api/doxygen/search/all_2.js b/docs/reference/api/doxygen/search/all_2.js
index cf567de3f..a34879a2d 100644
--- a/docs/reference/api/doxygen/search/all_2.js
+++ b/docs/reference/api/doxygen/search/all_2.js
@@ -79,6 +79,7 @@ var searchData=
['alloctensorreg',['AllocTensorReg',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#af67759dc5ab3f0285b0b3ad30edca6da',1,'tvm::runtime::vm::Instruction::AllocTensorReg()'],['../namespacetvm_1_1runtime_1_1vm.html#a8d8d95ce8d629c7213f2f595917870ecac8086b44868c71384cfec25bf1f1a6e6',1,'tvm::runtime::vm::AllocTensorReg()']]],
['allocworkspace',['AllocWorkspace',['../classtvm_1_1runtime_1_1DeviceAPI.html#abaa7af17b1662dd0907cc5ade826c281',1,'tvm::runtime::DeviceAPI']]],
['allow_5fcopy_5fon_5fwrite_5f',['allow_copy_on_write_',['../classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f',1,'tvm::tir::StmtMutator']]],
+ ['allowzero',['allowzero',['../structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930',1,'tvm::relay::ReshapeAttrs']]],
['alltypevars',['AllTypeVars',['../namespacetvm_1_1relay.html#ae67484a25663dfe2f87cbad53075abbf',1,'tvm::relay::AllTypeVars(const Expr &expr, const IRModule &mod)'],['../namespacetvm_1_1relay.html#ad24361b252cdb636192641e6801f2666',1,'tvm::relay::AllTypeVars(const Type &t, const IRModule &mod)']]],
['allvars',['AllVars',['../namespacetvm_1_1relay.html#a6b1e94cf8d97514fe4a9493a0dec1559',1,'tvm::relay']]],
['alpha',['alpha',['../structtvm_1_1relay_1_1LeakyReluAttrs.html#a78576f4cbcc1139b98c4fc00b99d0e07',1,'tvm::relay::LeakyReluAttrs::alpha()'],['../structtvm_1_1relay_1_1LRNAttrs.html#a76f869f2e2c27773e73744ac05bd3d1e',1,'tvm::relay::LRNAttrs::alpha()']]],
diff --git a/docs/reference/api/doxygen/search/all_a.js b/docs/reference/api/doxygen/search/all_a.js
index ebfe725f9..d95a77e2f 100644
--- a/docs/reference/api/doxygen/search/all_a.js
+++ b/docs/reference/api/doxygen/search/all_a.js
@@ -58,7 +58,7 @@ var searchData=
['infile',['infile',['../classtvm_1_1auto__scheduler_1_1RecordReaderNode.html#af196412cddedace59401d2f16f946871',1,'tvm::auto_scheduler::RecordReaderNode']]],
['infinity',['infinity',['../namespacetvm.html#a8934beb918da0e451d3aab7ccbcd9859',1,'tvm']]],
['info',['Info',['../classtvm_1_1transform_1_1PassNode.html#ab602b215ed172c9f09cf0fa2862858af',1,'tvm::transform::PassNode::Info()'],['../classtvm_1_1transform_1_1SequentialNode.html#a4873bfc55a74cb39b692884b7b9aa5c2',1,'tvm::transform::SequentialNode::Info()']]],
- ['init',['init',['../classtvm_1_1te_1_1ScanOpNode.html#a729243cd385db2e3f74c3a92a44db935',1,'tvm::te::ScanOpNode::init()'],['../classtvm_1_1tir_1_1ReduceNode.html#a1eeb307d22091f6ad8b718c67060f6b0',1,'tvm::tir::ReduceNode::init()'],['../classtvm_1_1tir_1_1BlockNode.html#a767ad1e6898cdbf522e7fe60d7c92520',1,'tvm::tir::BlockNode::init()'],['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a6685fdd01930e2c35d3c32529e398877',1,'tvm::runtime::profiling::MetricCollectorNode::I [...]
+ ['init',['Init',['../classtvm_1_1runtime_1_1profiling_1_1MetricCollectorNode.html#a6685fdd01930e2c35d3c32529e398877',1,'tvm::runtime::profiling::MetricCollectorNode::Init()'],['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a29c724a8ff2f88d8f4b5ba72e873b9c3',1,'tvm::runtime::vm::VirtualMachine::Init()'],['../classtvm_1_1te_1_1ScanOpNode.html#a729243cd385db2e3f74c3a92a44db935',1,'tvm::te::ScanOpNode::init()'],['../classtvm_1_1tir_1_1ReduceNode.html#a1eeb307d22091f6ad8b718c67060f6b0 [...]
['init_5fstate',['init_state',['../classtvm_1_1auto__scheduler_1_1ComputeDAGNode.html#a284eaa79b5d1fa15f4ad38bfbff9a41b',1,'tvm::auto_scheduler::ComputeDAGNode']]],
['initbypackedargs',['InitByPackedArgs',['../classtvm_1_1BaseAttrsNode.html#a375ef57a9dcf85e7961f91699927e50b',1,'tvm::BaseAttrsNode::InitByPackedArgs()'],['../classtvm_1_1DictAttrsNode.html#a06f561f072ccdd91c5c791b26331cc2f',1,'tvm::DictAttrsNode::InitByPackedArgs()'],['../classtvm_1_1AttrsNode.html#acfba199ef906818f35432d2e5532559a',1,'tvm::AttrsNode::InitByPackedArgs()']]],
['initbyseq',['InitBySeq',['../classtvm_1_1BaseAttrsNode.html#abcc04a722102d16fd4d86f9b7dcdd1e1',1,'tvm::BaseAttrsNode']]],
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index b7d1c7bc2..4683711fe 100644
--- a/docs/reference/api/doxygen/search/all_e.js
+++ b/docs/reference/api/doxygen/search/all_e.js
@@ -63,7 +63,7 @@ var searchData=
['matmulattrs',['MatmulAttrs',['../structtvm_1_1relay_1_1MatmulAttrs.html',1,'tvm::relay']]],
['matrix_5fset_5fdiag',['matrix_set_diag',['../namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c',1,'tvm::topi']]],
['matrixsetdiagattrs',['MatrixSetDiagAttrs',['../structtvm_1_1relay_1_1MatrixSetDiagAttrs.html',1,'tvm::relay']]],
- ['max',['Max',['../classtvm_1_1tir_1_1Max.html',1,'tvm::tir::Max'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, [...]
+ ['max',['Max',['../classtvm_1_1tir_1_1Max.html',1,'tvm::tir::Max'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, [...]
['max_5fcontinuous_5ferror',['max_continuous_error',['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#abdc38da91bcdf77be765c1e3d5af3648',1,'tvm::auto_scheduler::ProgramMeasurerNode']]],
['max_5fdisplacement',['max_displacement',['../structtvm_1_1relay_1_1CorrelationAttrs.html#ad1d16e2ba537736c8baee2553e1e32bf',1,'tvm::relay::CorrelationAttrs']]],
['max_5ffunctions',['max_functions',['../structTVMMutableFuncRegistry.html#a41745f8e0f73f8e4fb2074f5b154b49c',1,'TVMMutableFuncRegistry']]],
@@ -156,7 +156,7 @@ var searchData=
['microtvmruntimegetoutput',['MicroTVMRuntimeGetOutput',['../microtvm__runtime_8h.html#a76129be7b6de972791a3f9a1b312acfa',1,'microtvm_runtime.h']]],
['microtvmruntimerun',['MicroTVMRuntimeRun',['../microtvm__runtime_8h.html#ac43a544f675dd716e8c279c3e41f6e45',1,'microtvm_runtime.h']]],
['microtvmruntimesetinput',['MicroTVMRuntimeSetInput',['../microtvm__runtime_8h.html#aa593edc600f4356f2b560702aa01b113',1,'microtvm_runtime.h']]],
- ['min',['Min',['../classtvm_1_1tir_1_1Min.html',1,'tvm::tir::Min'],['../classtvm_1_1RangeNode.html#a43d2fb12bb61cf05936a1972d0158b49',1,'tvm::RangeNode::min()'],['../classtvm_1_1tir_1_1ForNode.html#a1d1aa2006328bd84e4911f6d43ceca5c',1,'tvm::tir::ForNode::min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongrue [...]
+ ['min',['Min',['../classtvm_1_1tir_1_1Min.html',1,'tvm::tir::Min'],['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../classtvm_1_1RangeNode.html#a43d2fb12bb61cf05936a1972d0158b49',1,'tvm::RangeNode::min()'],['../classtvm_1_1tir_1_1ForNode.html#a1d1aa2006328bd84e4911f6d43ceca5c',1,'tvm::tir::ForNode::min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1L [...]
['min_5frepeat_5fms',['min_repeat_ms',['../classtvm_1_1auto__scheduler_1_1ProgramRunnerNode.html#a39a865216db9ed6f57dfb22160cae1ff',1,'tvm::auto_scheduler::ProgramRunnerNode']]],
['min_5fvalue',['min_value',['../classtvm_1_1arith_1_1ConstIntBoundNode.html#a0761897bf16ab73b848bf360e9b195a3',1,'tvm::arith::ConstIntBoundNode::min_value()'],['../namespacetvm.html#a3b37fa55ea93d6868751a2441996b072',1,'tvm::min_value()']]],
['minimum',['minimum',['../namespacetvm_1_1topi.html#a7ac1dc0d99ce93090a4cdf90ab19d4b8',1,'tvm::topi::minimum(const tvm::PrimExpr &a, const tvm::PrimExpr &b)'],['../namespacetvm_1_1topi.html#a0e19dc06a2b1ecbb83b0942fdf836169',1,'tvm::topi::minimum(const tvm::te::Tensor &A, const tvm::te::Tensor &B, std::string name="T_" "minimum", std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a28d4ef4b3426bff237215ce356dd5681',1,'tvm::topi::minimum(con [...]
@@ -174,7 +174,7 @@ var searchData=
['modularset',['ModularSet',['../classtvm_1_1arith_1_1ModularSet.html',1,'tvm::arith::ModularSet'],['../classtvm_1_1arith_1_1ModularSet.html#a9f54896d98169246c6a24cc338fde500',1,'tvm::arith::ModularSet::ModularSet()']]],
['modularsetanalyzer',['ModularSetAnalyzer',['../classtvm_1_1arith_1_1ModularSetAnalyzer.html',1,'tvm::arith']]],
['modularsetnode',['ModularSetNode',['../classtvm_1_1arith_1_1ModularSetNode.html',1,'tvm::arith']]],
- ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536',1,'tvm::DiagnosticContextNode::module()'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f81 [...]
+ ['module',['Module',['../classtvm_1_1runtime_1_1Module.html',1,'tvm::runtime::Module'],['../classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d',1,'tvm::runtime::ModuleNode::Module()'],['../classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9',1,'tvm::runtime::Module::Module()'],['../classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4',1,'tvm::runtime::Module::Module(ObjectPtr< Object > n)'],['../classtvm_1_1DiagnosticContextN [...]
['module_2eh',['module.h',['../ir_2module_8h.html',1,'(Global Namespace)'],['../runtime_2crt_2module_8h.html',1,'(Global Namespace)'],['../runtime_2module_8h.html',1,'(Global Namespace)']]],
['moduleinternal',['ModuleInternal',['../classtvm_1_1runtime_1_1ModuleNode.html#a2b490c1acecd166b5824e4e96f17c64e',1,'tvm::runtime::ModuleNode']]],
['modulenode',['ModuleNode',['../classtvm_1_1runtime_1_1ModuleNode.html',1,'tvm::runtime::ModuleNode'],['../classtvm_1_1runtime_1_1Module.html#a908d19538a4fcadd6e93f39e4aa5292b',1,'tvm::runtime::Module::ModuleNode()']]],
diff --git a/docs/reference/api/doxygen/search/functions_10.js b/docs/reference/api/doxygen/search/functions_10.js
index 134a2c594..0bea9cdd7 100644
--- a/docs/reference/api/doxygen/search/functions_10.js
+++ b/docs/reference/api/doxygen/search/functions_10.js
@@ -9,7 +9,7 @@ var searchData=
['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 [...]
['pagememorymanagercreate',['PageMemoryManagerCreate',['../page__allocator_8h.html#a720dbc7474ac13b93fafb974cfc20bc7',1,'page_allocator.h']]],
- ['parallel',['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()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a553dc17c0b49b175cd16881c81b6c789',1,'tvm::tir::ScheduleNode::Parallel()']]],
+ ['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']]],
['parallel_5ffor_5fdynamic',['parallel_for_dynamic',['../namespacetvm_1_1support.html#afe4271363c794f1644ce7af5c2266530',1,'tvm::support']]],
['parallelizevectorizeunroll',['ParallelizeVectorizeUnroll',['../classtvm_1_1meta__schedule_1_1ScheduleRule.html#a0ef9b604081db7a8bf960f3fbfd3a804',1,'tvm::meta_schedule::ScheduleRule']]],
diff --git a/docs/reference/api/doxygen/search/functions_12.js b/docs/reference/api/doxygen/search/functions_12.js
index 0be558956..ed71b3ad3 100644
--- a/docs/reference/api/doxygen/search/functions_12.js
+++ b/docs/reference/api/doxygen/search/functions_12.js
@@ -49,7 +49,7 @@ var searchData=
['rendererrors',['RenderErrors',['../classtvm_1_1ErrorReporter.html#a54699ec5f538bd207b5aa4e3f55181c6',1,'tvm::ErrorReporter']]],
['renewdefs',['RenewDefs',['../namespacetvm_1_1tir.html#a2e639c81d1c6875ead7764ab8a7cd553',1,'tvm::tir']]],
['renormalizesplitpattern',['RenormalizeSplitPattern',['../namespacetvm_1_1tir_1_1transform.html#a5c670c9efcd740f2f168b62e624c8c57',1,'tvm::tir::transform']]],
- ['reorder',['Reorder',['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()'],['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()']]],
+ ['reorder',['reorder',['../classtvm_1_1auto__scheduler_1_1State.html#a16e95966b46977eff629a5f4f1564533',1,'tvm::auto_scheduler::State::reorder()'],['../classtvm_1_1te_1_1Stage.html#ad96cd240a92df9cafae89cdf2a7e302e',1,'tvm::te::Stage::reorder()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a059229fe0e254961da406807a97f7a3d',1,'tvm::tir::ScheduleNode::Reorder()']]],
['reorderstep',['ReorderStep',['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a83b9dab5f38d5a4d42c6424ba437bc10',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(int stage_id, const Array< Integer > &after_ids)'],['../classtvm_1_1auto__scheduler_1_1ReorderStep.html#a9586534afef3e0f57ab31e8374e70792',1,'tvm::auto_scheduler::ReorderStep::ReorderStep(dmlc::JSONReader *reader)']]],
['reorg',['reorg',['../namespacetvm_1_1topi_1_1vision.html#a1014df582489005202c4218e51792314',1,'tvm::topi::vision']]],
['repeat',['repeat',['../namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687',1,'tvm::topi']]],
@@ -62,7 +62,7 @@ var searchData=
['reportat',['ReportAt',['../classtvm_1_1ErrorReporter.html#a3e1c300e60077c38bc9540dddcd1a019',1,'tvm::ErrorReporter::ReportAt(const GlobalVar &global, const ObjectRef &node, std::stringstream &err)'],['../classtvm_1_1ErrorReporter.html#a04384ff3175673b4ff08fe46abca281c',1,'tvm::ErrorReporter::ReportAt(const GlobalVar &global, const ObjectRef &node, const CompileError &err)']]],
['reprprinter',['ReprPrinter',['../classtvm_1_1ReprPrinter.html#a05b878a528f2dec33e28278b17ddeb6b',1,'tvm::ReprPrinter']]],
['reserve',['reserve',['../classtvm_1_1runtime_1_1Array.html#a1a7727b86efaf35c58a5198ab1c139c8',1,'tvm::runtime::Array']]],
- ['reset',['Reset',['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a73b14ea360a9902c291d5bf6e97636cd',1,'tvm::auto_scheduler::ProgramMeasurerNode::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#ae6279154fe70e9eb85937b51e70a4bf8',1,'tvm::runtime::micro_rpc::Unframer::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Framer.html#a44ff9650ecca8785e33c25c369d2570a',1,'tvm::runtime::micro_rpc::Framer::Reset()'],['../classtvm_1_1tir_1_1StmtSRefNode.html#a0a81 [...]
+ ['reset',['reset',['../classtvm_1_1runtime_1_1NDArray.html#af2a8ccab95d432d1ecad7a389e11bcd3',1,'tvm::runtime::NDArray::reset()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#ac4461465ba0e785794794e0405c96590',1,'tvm::runtime::ObjectPtr::reset()'],['../classtvm_1_1auto__scheduler_1_1ProgramMeasurerNode.html#a73b14ea360a9902c291d5bf6e97636cd',1,'tvm::auto_scheduler::ProgramMeasurerNode::Reset()'],['../classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#ae6279154fe70e9eb85937b51e70a4bf8',1, [...]
['reset_5fattr',['reset_attr',['../classtvm_1_1OpRegEntry.html#a67628f8d3d6dea5b0a47e462c06b7790',1,'tvm::OpRegEntry']]],
['resetthreadpool',['ResetThreadPool',['../namespacetvm_1_1runtime_1_1threading.html#aafdb21c00248ff146b614a7e888b4fd7',1,'tvm::runtime::threading']]],
['reshape',['reshape',['../namespacetvm_1_1topi.html#a3aad65f2505802109ba7d05359ce9005',1,'tvm::topi']]],
@@ -86,7 +86,7 @@ var searchData=
['rewritetensorize',['RewriteTensorize',['../classtvm_1_1meta__schedule_1_1Postproc.html#a95db036cfced4c2575367a26a41498ff',1,'tvm::meta_schedule::Postproc']]],
['rewriteunboundblock',['RewriteUnboundBlock',['../classtvm_1_1meta__schedule_1_1Postproc.html#a190932261c8574b7e85e804938f8ad0d',1,'tvm::meta_schedule::Postproc']]],
['rewriteunsafeselect',['RewriteUnsafeSelect',['../namespacetvm_1_1tir_1_1transform.html#a4fe43327c4454dd05b6e925577443f49',1,'tvm::tir::transform']]],
- ['rfactor',['rfactor',['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()'],['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()']]],
+ ['rfactor',['RFactor',['../classtvm_1_1tir_1_1ScheduleNode.html#ab185c8eac1065290d84d58e7f4617232',1,'tvm::tir::ScheduleNode::RFactor()'],['../classtvm_1_1auto__scheduler_1_1State.html#a21c27b06d439267f8b981fa05c5f48a0',1,'tvm::auto_scheduler::State::rfactor()'],['../classtvm_1_1te_1_1Schedule.html#a34ae85add41bbed0140726d024d08862',1,'tvm::te::Schedule::rfactor()']]],
['rfactorstep',['RfactorStep',['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a26e6f85b55307f18fab4469e3bd4be0c',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(int stage_id, int iter_id, int factor_iter_id)'],['../classtvm_1_1auto__scheduler_1_1RfactorStep.html#a95575c21441177634178245ab562cb4f',1,'tvm::auto_scheduler::RfactorStep::RfactorStep(dmlc::JSONReader *reader)']]],
['right_5fshift',['right_shift',['../namespacetvm.html#ae8ecc0382685a855187bede0c97d93e6',1,'tvm::right_shift(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.html#af49dde9dfdeea62e8ad3a6d8db53de0b',1,'tvm::right_shift(const PrimExpr &a, int b, Span span=Span())'],['../namespacetvm.html#a98ff4361d0a24570f8dc32d03cde972a',1,'tvm::right_shift(int a, const PrimExpr &b, Span span=Span())'],['../namespacetvm_1_1topi.html#a9673b9caffb46404b566c3f04a492dfe',1,'tvm::topi:: [...]
['rocblas_5fbatch_5fmatmul',['rocblas_batch_matmul',['../namespacetvm_1_1topi_1_1contrib.html#abf1113dd429e1285752b48f62fe12848',1,'tvm::topi::contrib']]],
diff --git a/docs/reference/api/doxygen/search/functions_14.js b/docs/reference/api/doxygen/search/functions_14.js
index fc228d5aa..cd0094a0f 100644
--- a/docs/reference/api/doxygen/search/functions_14.js
+++ b/docs/reference/api/doxygen/search/functions_14.js
@@ -48,7 +48,7 @@ var searchData=
['totupletype',['ToTupleType',['../namespacetvm_1_1relay.html#ae6757a008816e31cce4109e8dfc2bc16',1,'tvm::relay']]],
['touchtask',['TouchTask',['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#af6fa276674945d3432c129bdf9cea599',1,'tvm::meta_schedule::TaskSchedulerNode::TouchTask()'],['../classtvm_1_1meta__schedule_1_1PyTaskSchedulerNode.html#a7de09f81c8aceb580b43107f266e6b40',1,'tvm::meta_schedule::PyTaskSchedulerNode::TouchTask()']]],
['tovar',['ToVar',['../classtvm_1_1tir_1_1AnyNode.html#ae01ebbba2378afb6509a22de97f8fb30',1,'tvm::tir::AnyNode']]],
- ['trace',['Trace',['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)'],['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()']]],
+ ['trace',['trace',['../classtvm_1_1tir_1_1ScheduleNode.html#a953bca4123b5a758adfdcd65634a5f3b',1,'tvm::tir::ScheduleNode::trace()'],['../classtvm_1_1tir_1_1Trace.html#a8e09abffd0b9b1afac7b832cf16c142d',1,'tvm::tir::Trace::Trace()'],['../classtvm_1_1tir_1_1Trace.html#af79bccf1bde25efea387bb1b82dacaa6',1,'tvm::tir::Trace::Trace(Array< Instruction > insts, Map< Instruction, ObjectRef > decisions)']]],
['traced',['Traced',['../classtvm_1_1tir_1_1Schedule.html#a295d432b86621101f67b20fadb367b91',1,'tvm::tir::Schedule']]],
['transform',['Transform',['../classtvm_1_1te_1_1Transform.html#a51422cc2290f6b87fe61edb0db691125',1,'tvm::te::Transform']]],
['transform_5flayout',['transform_layout',['../classtvm_1_1te_1_1Stage.html#acec77eca6c9a4f1738a7c119d7ac2c2c',1,'tvm::te::Stage']]],
diff --git a/docs/reference/api/doxygen/search/functions_15.js b/docs/reference/api/doxygen/search/functions_15.js
index ddc30ff83..86d8ad114 100644
--- a/docs/reference/api/doxygen/search/functions_15.js
+++ b/docs/reference/api/doxygen/search/functions_15.js
@@ -15,7 +15,7 @@ var searchData=
['unique',['unique',['../classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7',1,'tvm::runtime::Object::unique()'],['../classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314',1,'tvm::runtime::ObjectPtr::unique()'],['../classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7',1,'tvm::runtime::ObjectRef::unique()'],['../classtvm_1_1VirtualDeviceCache.html#a25ba1351484aa58a2cc7cef8f8e4423c',1,'tvm::VirtualDeviceCache::Unique()']]],
['unmatchedcases',['UnmatchedCases',['../namespacetvm_1_1relay.html#aa3a8cace40f8056fd6412f39c3eaa605',1,'tvm::relay']]],
['unravel_5findex',['unravel_index',['../namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e',1,'tvm::topi']]],
- ['unroll',['Unroll',['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()'],['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()']]],
+ ['unroll',['unroll',['../classtvm_1_1auto__scheduler_1_1State.html#aa68a9d2e226bae38a36e4be4af1d1ae4',1,'tvm::auto_scheduler::State::unroll()'],['../classtvm_1_1te_1_1Stage.html#af83ad8672660403504f472228b044b33',1,'tvm::te::Stage::unroll()'],['../classtvm_1_1tir_1_1ScheduleNode.html#a84ec742f6295f59390592a6d0d90a552',1,'tvm::tir::ScheduleNode::Unroll()']]],
['unrollloop',['UnrollLoop',['../namespacetvm_1_1tir_1_1transform.html#ab2f279e91071fa96a1edb24fa004ea6a',1,'tvm::tir::transform']]],
['update',['Update',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#a5ae0699196c4bbc754bbdd4c3a6c7ca7',1,'tvm::arith::ConstIntBoundAnalyzer::Update()'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a04156fac580981f3005af3b8e676720d',1,'tvm::arith::ModularSetAnalyzer::Update()'],['../classtvm_1_1arith_1_1RewriteSimplifier.html#a5e6752c0702dc2d3e4235797d9d3ac7b',1,'tvm::arith::RewriteSimplifier::Update()'],['../classtvm_1_1arith_1_1CanonicalSimplifier.html#a790c032e12c7d93e9e940 [...]
['updatecostmodel',['UpdateCostModel',['../classtvm_1_1meta__schedule_1_1MeasureCallback.html#afdf5503c6e6f53767de132d91a7b53f9',1,'tvm::meta_schedule::MeasureCallback']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index 6cb1896a7..7ab178fa9 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -31,7 +31,7 @@ var searchData=
['matchrange',['MatchRange',['../classtvm_1_1arith_1_1IntSet.html#a2f2999336fbba4f436b66bdddce5c57a',1,'tvm::arith::IntSet']]],
['matmul',['matmul',['../namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994',1,'tvm::topi']]],
['matrix_5fset_5fdiag',['matrix_set_diag',['../namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c',1,'tvm::topi']]],
- ['max',['Max',['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
+ ['max',['max',['../classtvm_1_1arith_1_1IntSet.html#ac215840d3e9fb2817f1e5648e31317c5',1,'tvm::arith::IntSet::max()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#a2c5ea87b1155aa7810e0beb3b69b955b',1,'tvm::support::LinearCongruentialEngine::max()'],['../classtvm_1_1tir_1_1Max.html#a7dff11b4dea01bfc7a03eacd077f0729',1,'tvm::tir::Max::Max()'],['../namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb',1,'tvm::max(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
['max_5fvalue',['max_value',['../namespacetvm.html#a4f1398024c0af23699447ef910b654b8',1,'tvm']]],
['maxconcurrency',['MaxConcurrency',['../namespacetvm_1_1runtime_1_1threading.html#af8c1c389a74e67bcc3680555288219f8',1,'tvm::runtime::threading']]],
['maximum',['maximum',['../namespacetvm_1_1topi.html#afd64bc3e27dfc97002d3add5d7ce4174',1,'tvm::topi::maximum(const tvm::PrimExpr &a, const tvm::PrimExpr &b)'],['../namespacetvm_1_1topi.html#a5338e9297463bc745027fca67daa2ebb',1,'tvm::topi::maximum(const tvm::te::Tensor &A, const tvm::te::Tensor &B, std::string name="T_" "maximum", std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a4076a8d6a2b243c548d741e9f6bcfe69',1,'tvm::topi::maximum(con [...]
@@ -55,7 +55,7 @@ var searchData=
['microtvmruntimegetoutput',['MicroTVMRuntimeGetOutput',['../microtvm__runtime_8h.html#a76129be7b6de972791a3f9a1b312acfa',1,'microtvm_runtime.h']]],
['microtvmruntimerun',['MicroTVMRuntimeRun',['../microtvm__runtime_8h.html#ac43a544f675dd716e8c279c3e41f6e45',1,'microtvm_runtime.h']]],
['microtvmruntimesetinput',['MicroTVMRuntimeSetInput',['../microtvm__runtime_8h.html#aa593edc600f4356f2b560702aa01b113',1,'microtvm_runtime.h']]],
- ['min',['min',['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongruentialEngine::min()'],['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../namespacetvm.html#aac2abc149c1a47944c37b560181b15c0',1,'tvm::min(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
+ ['min',['Min',['../classtvm_1_1tir_1_1Min.html#a3a4403aec40029a5206e22cd334e356b',1,'tvm::tir::Min::Min()'],['../classtvm_1_1arith_1_1IntSet.html#ae5517de2862e93a801224eed98a57001',1,'tvm::arith::IntSet::min()'],['../classtvm_1_1support_1_1LinearCongruentialEngine.html#aec5f11b588fa3a12294a46c945c34411',1,'tvm::support::LinearCongruentialEngine::min()'],['../namespacetvm.html#aac2abc149c1a47944c37b560181b15c0',1,'tvm::min(PrimExpr a, PrimExpr b, Span span=Span())'],['../namespacetvm.ht [...]
['min_5fvalue',['min_value',['../namespacetvm.html#a3b37fa55ea93d6868751a2441996b072',1,'tvm']]],
['minimum',['minimum',['../namespacetvm_1_1topi.html#a7ac1dc0d99ce93090a4cdf90ab19d4b8',1,'tvm::topi::minimum(const tvm::PrimExpr &a, const tvm::PrimExpr &b)'],['../namespacetvm_1_1topi.html#a0e19dc06a2b1ecbb83b0942fdf836169',1,'tvm::topi::minimum(const tvm::te::Tensor &A, const tvm::te::Tensor &B, std::string name="T_" "minimum", std::string tag=kBroadcast)'],['../namespacetvm_1_1topi.html#a28d4ef4b3426bff237215ce356dd5681',1,'tvm::topi::minimum(con [...]
['minop',['MinOp',['../namespacetvm_1_1topi.html#aea9a989b0aaa2aef03fe8ee237d8257e',1,'tvm::topi']]],
diff --git a/docs/reference/api/doxygen/search/variables_1.js b/docs/reference/api/doxygen/search/variables_1.js
index 04dcf84c8..57972d785 100644
--- a/docs/reference/api/doxygen/search/variables_1.js
+++ b/docs/reference/api/doxygen/search/variables_1.js
@@ -20,6 +20,7 @@ var searchData=
['allocation_5fsize',['allocation_size',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a4f907889caa7c348a3a2dea88e89b827',1,'tvm::runtime::vm::Instruction']]],
['allocators_5f',['allocators_',['../classtvm_1_1runtime_1_1vm_1_1VirtualMachine.html#a0ef00d527a1c03221030c5fec2ad519d',1,'tvm::runtime::vm::VirtualMachine']]],
['allow_5fcopy_5fon_5fwrite_5f',['allow_copy_on_write_',['../classtvm_1_1tir_1_1StmtMutator.html#a620e6041832441d25ee4f4d65921231f',1,'tvm::tir::StmtMutator']]],
+ ['allowzero',['allowzero',['../structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930',1,'tvm::relay::ReshapeAttrs']]],
['alpha',['alpha',['../structtvm_1_1relay_1_1LeakyReluAttrs.html#a78576f4cbcc1139b98c4fc00b99d0e07',1,'tvm::relay::LeakyReluAttrs::alpha()'],['../structtvm_1_1relay_1_1LRNAttrs.html#a76f869f2e2c27773e73744ac05bd3d1e',1,'tvm::relay::LRNAttrs::alpha()']]],
['always_5funroll_5finner',['always_unroll_inner',['../structtvm_1_1auto__scheduler_1_1SearchPolicyKey.html#a71838ac1b909b52ffcf083a98ff4eddc',1,'tvm::auto_scheduler::SearchPolicyKey']]],
['annotation',['annotation',['../classtvm_1_1auto__scheduler_1_1IteratorNode.html#ac37155c7dbf930ce7bd9de34cdc6c1af',1,'tvm::auto_scheduler::IteratorNode::annotation()'],['../classtvm_1_1auto__scheduler_1_1AnnotationStepNode.html#a7b255ca54942d929a2a1a2feb8ebf910',1,'tvm::auto_scheduler::AnnotationStepNode::annotation()']]],
diff --git a/docs/reference/api/doxygen/shape__tuple_8h_source.html b/docs/reference/api/doxygen/shape__tuple_8h_source.html
index 0665c4d9c..218839933 100644
--- a/docs/reference/api/doxygen/shape__tuple_8h_source.html
+++ b/docs/reference/api/doxygen/shape__tuple_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a6836ad757cbcac207ddf025a74ac2ef2"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a6836ad757cbcac207ddf025a74ac2ef2">tvm::runtime::ShapeTuple::ShapeTuple</a></div><div class="ttdeci">ShapeTuple(IterType begin, IterType end)</div><div class="ttdoc">Constructor from iterator. </div><div class="ttdef"><b>Definition:</b> shape_tuple.h:98</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a93afa6c6de6d38665b62a007892a8632"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a93afa6c6de6d38665b62a007892a8632">tvm::runtime::ShapeTuple::begin</a></div><div class="ttdeci">const index_type * begin() const</div><div class="ttdef"><b>Definition:</b> shape_tuple.h:158</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a7e4f6df331fcf589c3f5544c88931561"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a7e4f6df331fcf589c3f5544c88931561">tvm::runtime::ShapeTuple::empty</a></div><div class="ttdeci">bool empty() const</div><div class="ttdef"><b>Definition:</b> shape_tuple.h:149</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTupleObj_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTupleObj.html">tvm::runtime::ShapeTupleObj</a></div><div class="ttdoc">An object representing a shape tuple. </div><div class="ttdef"><b>Definition:</b> shape_tuple.h:36</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1TypeIndex_html_aed93c7318efc8052201d4c404b21a40dae2bdfcaf2a93d7e1dfef9012bd0cae77"><div class="ttname"><a href="structtvm_1_1runtime_1_1TypeIndex.html#aed93c7318efc8052201d4c404b21a40dae2bdfcaf2a93d7e1dfef9012bd0cae77">tvm::runtime::TypeIndex::kRuntimeShapeTuple</a></div><div class="ttdoc">runtime::ShapeTuple. </div><div class="ttdef"><b>Definition:</b> object.h:72</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>
diff --git a/docs/reference/api/doxygen/strided__slice_8h_source.html b/docs/reference/api/doxygen/strided__slice_8h_source.html
index 02e0f1ab5..21e2e10ab 100644
--- a/docs/reference/api/doxygen/strided__slice_8h_source.html
+++ b/docs/reference/api/doxygen/strided__slice_8h_source.html
@@ -68,7 +68,7 @@ $(function() {
<div class="contents">
<a href="strided__slice_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_html_ab2a3c98ef29937defd6accb9b171a940"><div class="ttname"><a href="namespacetvm.html#ab2a3c98ef29937defd6accb9b171a940">tvm::abs</a></div><div class="ttdeci">PrimExpr abs(PrimExpr x, Span span=Span())</div><div class="ttdoc">Calculate absolute value of x. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_aff75b2e533b654909ca1bd9485ef4e6b"><div class="ttname"><a href="namespacetvm_1_1topi.html#aff75b2e533b654909ca1bd9485ef4e6b">tvm::topi::StridedSliceOutputShape</a></div><div class="ttdeci">Array< PrimExpr > StridedSliceOutputShape(const Array< PrimExpr > &ishape, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, co [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_aff75b2e533b654909ca1bd9485ef4e6b"><div class="ttname"><a href="namespacetvm_1_1topi.html#aff75b2e533b654909ca1bd9485ef4e6b">tvm::topi::StridedSliceOutputShape</a></div><div class="ttdeci">Array< PrimExpr > StridedSliceOutputShape(const Array< PrimExpr > &ishape, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, co [...]
<div class="ttc" id="namespacetvm_1_1tir_html_a1a071208bbbab6b220cf46f5cdccdd86"><div class="ttname"><a href="namespacetvm_1_1tir.html#a1a071208bbbab6b220cf46f5cdccdd86">tvm::tir::make_const</a></div><div class="ttdeci">PrimExpr make_const(DataType t, ValueType value, Span span=Span())</div><div class="ttdoc">Make a const value with certain data type. </div><div class="ttdef"><b>Definition:</b> op.h:1144</div></div>
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> autodiff.h:35</div></div>
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs-members.html b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs-members.html
index c186e54ab..99fdb87f6 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs-members.html
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs-members.html
@@ -78,42 +78,43 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a74e9f076b50b8b335b4a321e9b0bf03c">_type_has_method_visit_attrs</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af6aed95d70af7e44ce376a8d7be6c5f1">_type_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a8e4fd4e728774e0556cda84b0c2b80d6">_type_key</a></td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a70fb5361147634605d6595bb89381f03">DecRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af4407d2b59132e803ff791482dbe0145">deleter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span [...]
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acfba199ef906818f35432d2e5532559a">InitByPackedArgs</a>(const runtime::TVMArgs &args, bool allow_unknown) final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#abcc04a722102d16fd4d86f9b7dcdd1e1">InitBySeq</a>(Args &&... args)</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acefe615381b5d881870af9db7ce6a981">ListFieldInfo</a>() const final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a9bca32c3acff2ed8fd6bc63a50f82051">newshape</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a80929190102473038bce5b4f6c42dff6">PrintDocString</a>(std::ostream &os) const</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a07bcda7b450ba8dbea70e1889d021443">SEqualReduce</a>(const ReshapeAttrs *other, SEqualReducer equal) const</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a3c10c6d2eb267521a96479d002ad93d5">SHashReduce</a>(SHashReducer hash_reducer) const</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#adb72dc00148149948a282e4fdbd1cd28">TVM_DECLARE_ATTRS</a>(ReshapeAttrs, "relay.attrs.ReshapeAttrs")</td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#aaca524319f015a18a1385cfea5ba8895">TVM_DECLARE_BASE_OBJECT_INFO</a>(BaseAttrsNode, Object)</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a257561dad74174cbdc08f6725a45d8ac">TVMArgs</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb">TVMRetValue</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a481f01923b14e1851ebd38506e9c66ea">type_index</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4bfc2586cb55f2af47728187b3256255">type_index_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">TypeIndex2Key</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6ee32a02dd44257da105fbbe5d9c8622">TypeIndex2KeyHash</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6841f97e06e6614dd7e82c6dd41b818a">TypeKey2Index</a>(const std::string &key)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a5da687ced06b4f2dfa04b142a34a9c72">VisitAttrs</a>(AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acd05137ba529ac7cd07053e3da885205">VisitNonDefaultAttrs</a>(AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a225581a40231b2de219da30fced428a2">~BaseAttrsNode</a>()</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930">allowzero</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a70fb5361147634605d6595bb89381f03">DecRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af4407d2b59132e803ff791482dbe0145">deleter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a9e84841ca982bff376a978ade0132631">FDeleter</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a726972ff315c446192df94027ddea032">GetOrAllocRuntimeTypeIndex</a>(const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4d951e51832081b85875669eac90e940">GetTypeKey</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a5693cbadcc1168b96db7b1cc5c200b86">GetTypeKeyHash</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ac9e5eed7719e322117bde996a171e33a">IncRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acfba199ef906818f35432d2e5532559a">InitByPackedArgs</a>(const runtime::TVMArgs &args, bool allow_unknown) final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#abcc04a722102d16fd4d86f9b7dcdd1e1">InitBySeq</a>(Args &&... args)</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acefe615381b5d881870af9db7ce6a981">ListFieldInfo</a>() const final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a9bca32c3acff2ed8fd6bc63a50f82051">newshape</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ab7968feb6ad38ecaffc320e13819d826">Object</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#aa1612f69ea5b4225d4cda759cd517323">Object</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a80929190102473038bce5b4f6c42dff6">PrintDocString</a>(std::ostream &os) const</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a0d492efee331e2239a093f4b2017c10f">ref_counter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a55549a6c23987890246248682560a03d">RefCounterType</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ad94d79729ac85aa7c976e23d39066383">RuntimeTypeIndex</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a07bcda7b450ba8dbea70e1889d021443">SEqualReduce</a>(const ReshapeAttrs *other, SEqualReducer equal) const</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a3c10c6d2eb267521a96479d002ad93d5">SHashReduce</a>(SHashReducer hash_reducer) const</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#adb72dc00148149948a282e4fdbd1cd28">TVM_DECLARE_ATTRS</a>(ReshapeAttrs, "relay.attrs.ReshapeAttrs")</td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html">tvm::relay::ReshapeAttrs</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#aaca524319f015a18a1385cfea5ba8895">TVM_DECLARE_BASE_OBJECT_INFO</a>(BaseAttrsNode, Object)</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a257561dad74174cbdc08f6725a45d8ac">TVMArgs</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a1f56f080d0c1fab79d9469029aef8ebb">TVMRetValue</a> typedef</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a481f01923b14e1851ebd38506e9c66ea">type_index</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a4bfc2586cb55f2af47728187b3256255">type_index_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">TypeIndex2Key</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6ee32a02dd44257da105fbbe5d9c8622">TypeIndex2KeyHash</a>(uint32_t tindex)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a6841f97e06e6614dd7e82c6dd41b818a">TypeKey2Index</a>(const std::string &key)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#a5da687ced06b4f2dfa04b142a34a9c72">VisitAttrs</a>(AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acd05137ba529ac7cd07053e3da885205">VisitNonDefaultAttrs</a>(AttrVisitor *v)</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< ReshapeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a225581a40231b2de219da30fced428a2">~BaseAttrsNode</a>()</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
</table></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs.html b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs.html
index f386e69d2..fef7ce228 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs.html
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs.html
@@ -78,7 +78,7 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::relay::ReshapeAttrs:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg" width="287" height="1154"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg" width="287" height="1168"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<div class="dynheader">
@@ -148,6 +148,8 @@ Public Member Functions</h2></td></tr>
Public Attributes</h2></td></tr>
<tr class="memitem:a9bca32c3acff2ed8fd6bc63a50f82051"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1Integer.html">Integer</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a9bca32c3acff2ed8fd6bc63a50f82051">newshape</a></td></tr>
<tr class="separator:a9bca32c3acff2ed8fd6bc63a50f82051"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a53162b9a7f6232a8d599f58ffafce930"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1ReshapeAttrs.html#a53162b9a7f6232a8d599f58ffafce930">allowzero</a></td></tr>
+<tr class="separator:a53162b9a7f6232a8d599f58ffafce930"><td class="memSeparator" colspan="2"> </td></tr>
</table><table class="memberdecls">
<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="inherited"></a>
Additional Inherited Members</h2></td></tr>
@@ -262,6 +264,20 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
<h2 class="groupheader">Member Data Documentation</h2>
+<a id="a53162b9a7f6232a8d599f58ffafce930"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a53162b9a7f6232a8d599f58ffafce930">◆ </a></span>allowzero</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">bool tvm::relay::ReshapeAttrs::allowzero</td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
<a id="a9bca32c3acff2ed8fd6bc63a50f82051"></a>
<h2 class="memtitle"><span class="permalink"><a href="#a9bca32c3acff2ed8fd6bc63a50f82051">◆ </a></span>newshape</h2>
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__coll__graph.svg b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__coll__graph.svg
index cf868aa18..1bbdad41c 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__coll__graph.svg
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__coll__graph.svg
@@ -15,7 +15,7 @@
<polygon fill="#bfbfbf" stroke="#000000" points="157,-.5 157,-57.5 300,-57.5 300,-.5 157,-.5"/>
<text text-anchor="middle" x="228.5" y="-45.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::relay::ReshapeAttrs</text>
<polyline fill="none" stroke="#000000" points="157,-38.5 300,-38.5 "/>
-<text text-anchor="middle" x="228.5" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<text text-anchor="start" x="165" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ allowzero</text>
<polyline fill="none" stroke="#000000" points="157,-19.5 300,-19.5 "/>
<text text-anchor="start" x="165" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_ATTRS()</text>
</g>
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg
index e1a66e2f7..e5e62d9f8 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1ReshapeAttrs__inherit__graph.svg
@@ -4,18 +4,19 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::relay::ReshapeAttrs Pages: 1 -->
-<svg width="215pt" height="865pt"
- viewBox="0.00 0.00 215.00 865.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 861)">
+<svg width="215pt" height="876pt"
+ viewBox="0.00 0.00 215.00 876.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 872)">
<title>tvm::relay::ReshapeAttrs</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-861 211,-861 211,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-872 211,-872 211,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="32,-.5 32,-57.5 175,-57.5 175,-.5 32,-.5"/>
-<text text-anchor="middle" x="103.5" y="-45.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::relay::ReshapeAttrs</text>
-<polyline fill="none" stroke="#000000" points="32,-38.5 175,-38.5 "/>
-<text text-anchor="start" x="40" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ newshape</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="32,-.5 32,-68.5 175,-68.5 175,-.5 32,-.5"/>
+<text text-anchor="middle" x="103.5" y="-56.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::relay::ReshapeAttrs</text>
+<polyline fill="none" stroke="#000000" points="32,-49.5 175,-49.5 "/>
+<text text-anchor="start" x="40" y="-37.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ newshape</text>
+<text text-anchor="start" x="40" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ allowzero</text>
<polyline fill="none" stroke="#000000" points="32,-19.5 175,-19.5 "/>
<text text-anchor="start" x="40" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_ATTRS()</text>
</g>
@@ -23,105 +24,105 @@
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1AttrsNode.html" target="_top" xlink:title="{tvm::AttrsNode\< ReshapeAttrs \>\n||+ VisitAttrs()\l+ VisitNonDefaultAttrs()\l+ InitByPackedArgs()\l+ SEqualReduce()\l+ SHashReduce()\l+ ListFieldInfo()\l}">
-<polygon fill="#ffffff" stroke="#000000" points="14.5,-94.5 14.5,-206.5 192.5,-206.5 192.5,-94.5 14.5,-94.5"/>
-<text text-anchor="middle" x="103.5" y="-194.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::AttrsNode< ReshapeAttrs ></text>
-<polyline fill="none" stroke="#000000" points="14.5,-187.5 192.5,-187.5 "/>
-<text text-anchor="middle" x="103.5" y="-175.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="14.5,-168.5 192.5,-168.5 "/>
-<text text-anchor="start" x="22.5" y="-156.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="22.5" y="-145.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
-<text text-anchor="start" x="22.5" y="-134.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
-<text text-anchor="start" x="22.5" y="-123.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SEqualReduce()</text>
-<text text-anchor="start" x="22.5" y="-112.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SHashReduce()</text>
-<text text-anchor="start" x="22.5" y="-101.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
+<polygon fill="#ffffff" stroke="#000000" points="14.5,-105.5 14.5,-217.5 192.5,-217.5 192.5,-105.5 14.5,-105.5"/>
+<text text-anchor="middle" x="103.5" y="-205.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::AttrsNode< ReshapeAttrs ></text>
+<polyline fill="none" stroke="#000000" points="14.5,-198.5 192.5,-198.5 "/>
+<text text-anchor="middle" x="103.5" y="-186.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="14.5,-179.5 192.5,-179.5 "/>
+<text text-anchor="start" x="22.5" y="-167.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="22.5" y="-156.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
+<text text-anchor="start" x="22.5" y="-145.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
+<text text-anchor="start" x="22.5" y="-134.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SEqualReduce()</text>
+<text text-anchor="start" x="22.5" y="-123.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SHashReduce()</text>
+<text text-anchor="start" x="22.5" y="-112.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M103.5,-84.2502C103.5,-74.9452 103.5,-65.8136 103.5,-57.7385"/>
-<polygon fill="none" stroke="#191970" points="100.0001,-84.3734 103.5,-94.3735 107.0001,-84.3735 100.0001,-84.3734"/>
+<path fill="none" stroke="#191970" d="M103.5,-95.4261C103.5,-86.2025 103.5,-77.0514 103.5,-68.753"/>
+<polygon fill="none" stroke="#191970" points="100.0001,-95.4262 103.5,-105.4263 107.0001,-95.4263 100.0001,-95.4262"/>
</g>
<!-- Node2 -->
<g id="node3" class="node">
<title>Node2</title>
<g id="a_node3"><a xlink:href="classtvm_1_1BaseAttrsNode.html" target="_top" xlink:title="Base class of all attribute class. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-243.5 0,-421.5 207,-421.5 207,-243.5 0,-243.5"/>
-<text text-anchor="middle" x="103.5" y="-409.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseAttrsNode</text>
-<polyline fill="none" stroke="#000000" points="0,-402.5 207,-402.5 "/>
-<text text-anchor="start" x="8" y="-390.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="8" y="-379.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-368.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="8" y="-357.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-346.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<polyline fill="none" stroke="#000000" points="0,-339.5 207,-339.5 "/>
-<text text-anchor="start" x="8" y="-327.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~BaseAttrsNode()</text>
-<text text-anchor="start" x="8" y="-316.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="8" y="-305.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitBySeq()</text>
-<text text-anchor="start" x="8" y="-294.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrintDocString()</text>
-<text text-anchor="start" x="8" y="-283.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
-<text text-anchor="start" x="8" y="-272.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
-<text text-anchor="start" x="8" y="-261.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
-<text text-anchor="start" x="8" y="-250.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_BASE_OBJECT_INFO()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-254.5 0,-432.5 207,-432.5 207,-254.5 0,-254.5"/>
+<text text-anchor="middle" x="103.5" y="-420.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseAttrsNode</text>
+<polyline fill="none" stroke="#000000" points="0,-413.5 207,-413.5 "/>
+<text text-anchor="start" x="8" y="-401.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="8" y="-390.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="8" y="-379.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="8" y="-368.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="8" y="-357.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<polyline fill="none" stroke="#000000" points="0,-350.5 207,-350.5 "/>
+<text text-anchor="start" x="8" y="-338.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~BaseAttrsNode()</text>
+<text text-anchor="start" x="8" y="-327.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="8" y="-316.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitBySeq()</text>
+<text text-anchor="start" x="8" y="-305.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrintDocString()</text>
+<text text-anchor="start" x="8" y="-294.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
+<text text-anchor="start" x="8" y="-283.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
+<text text-anchor="start" x="8" y="-272.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
+<text text-anchor="start" x="8" y="-261.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_BASE_OBJECT_INFO()</text>
</a>
</g>
</g>
<!-- Node2->Node1 -->
<g id="edge2" class="edge">
<title>Node2->Node1</title>
-<path fill="none" stroke="#191970" d="M103.5,-233.1054C103.5,-224.0423 103.5,-215.0912 103.5,-206.6158"/>
-<polygon fill="none" stroke="#191970" points="100.0001,-233.3661 103.5,-243.3661 107.0001,-233.3661 100.0001,-233.3661"/>
+<path fill="none" stroke="#191970" d="M103.5,-244.1054C103.5,-235.0423 103.5,-226.0912 103.5,-217.6158"/>
+<polygon fill="none" stroke="#191970" points="100.0001,-244.3661 103.5,-254.3661 107.0001,-244.3661 100.0001,-244.3661"/>
</g>
<!-- Node3 -->
<g id="node4" class="node">
<title>Node3</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1Object.html" target="_top" xlink:title="base class of all object containers. ">
-<polygon fill="#ffffff" stroke="#000000" points="12,-458.5 12,-856.5 195,-856.5 195,-458.5 12,-458.5"/>
-<text text-anchor="middle" x="103.5" y="-844.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="12,-837.5 195,-837.5 "/>
-<text text-anchor="start" x="20" y="-825.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="20" y="-814.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="20" y="-803.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="20" y="-792.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="20" y="-781.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="20" y="-770.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="20" y="-759.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="20" y="-748.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="20" y="-737.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="20" y="-726.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
-<text text-anchor="start" x="20" y="-715.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="20" y="-704.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="20" y="-693.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="20" y="-682.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<text text-anchor="start" x="20" y="-671.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
-<polyline fill="none" stroke="#000000" points="12,-664.5 195,-664.5 "/>
-<text text-anchor="start" x="20" y="-652.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="20" y="-641.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="20" y="-630.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="20" y="-619.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="20" y="-608.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<polygon fill="#ffffff" stroke="#000000" points="12,-469.5 12,-867.5 195,-867.5 195,-469.5 12,-469.5"/>
+<text text-anchor="middle" x="103.5" y="-855.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="12,-848.5 195,-848.5 "/>
+<text text-anchor="start" x="20" y="-836.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="20" y="-825.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="20" y="-814.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="20" y="-803.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="20" y="-792.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="20" y="-781.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="20" y="-770.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="20" y="-759.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
+<text text-anchor="start" x="20" y="-748.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="20" y="-737.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="20" y="-726.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="20" y="-715.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="20" y="-704.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="20" y="-693.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<text text-anchor="start" x="20" y="-682.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># deleter_</text>
+<polyline fill="none" stroke="#000000" points="12,-675.5 195,-675.5 "/>
+<text text-anchor="start" x="20" y="-663.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="20" y="-652.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="20" y="-641.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="20" y="-630.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="20" y="-619.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="20" y="-608.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
<text text-anchor="start" x="20" y="-597.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
<text text-anchor="start" x="20" y="-586.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="20" y="-575.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="20" y="-575.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
<text text-anchor="start" x="20" y="-564.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="20" y="-553.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="20" y="-542.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="20" y="-531.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="20" y="-520.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="20" y="-509.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="20" y="-498.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="20" y="-487.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="20" y="-476.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="20" y="-465.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-553.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="20" y="-542.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="20" y="-531.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="20" y="-520.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-509.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-498.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="20" y="-487.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="20" y="-476.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node3->Node2 -->
<g id="edge3" class="edge">
<title>Node3->Node2</title>
-<path fill="none" stroke="#191970" d="M103.5,-447.883C103.5,-438.8603 103.5,-430.0496 103.5,-421.5763"/>
-<polygon fill="none" stroke="#191970" points="100.0001,-448.1535 103.5,-458.1535 107.0001,-448.1535 100.0001,-448.1535"/>
+<path fill="none" stroke="#191970" d="M103.5,-458.883C103.5,-449.8603 103.5,-441.0496 103.5,-432.5763"/>
+<polygon fill="none" stroke="#191970" points="100.0001,-459.1535 103.5,-469.1535 107.0001,-459.1535 100.0001,-459.1535"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/tensor_8h_source.html b/docs/reference/api/doxygen/tensor_8h_source.html
index c671ffdf7..dda1d9902 100644
--- a/docs/reference/api/doxygen/tensor_8h_source.html
+++ b/docs/reference/api/doxygen/tensor_8h_source.html
@@ -95,7 +95,7 @@ $(function() {
<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="classtvm_1_1te_1_1TensorNode_html_a153569448cb1bf9d2924d35639c3b8b8"><div class="ttname"><a href="classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8">tvm::te::TensorNode::TensorNode</a></div><div class="ttdeci">TensorNode()</div><div class="ttdoc">constructor </div><div class="ttdef"><b>Definition:</b> tensor.h:79</div></div>
<div class="ttc" id="classtvm_1_1te_1_1Tensor_1_1Slice_html_a1a00e3ec5f80973c337b0e7ab9c0974d"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor_1_1Slice.html#a1a00e3ec5f80973c337b0e7ab9c0974d">tvm::te::Tensor::Slice::operator[]</a></div><div class="ttdeci">Slice operator[](PrimExpr i)</div><div class="ttdoc">get i-th slice from the current slice. </div><div class="ttdef"><b>Definition:</b> tensor.h:187</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_aadbc0886ffa80162ff31eefd0431ba09"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#aadbc0886ffa80162ff31eefd0431ba09">tvm::runtime::ObjectRef::get</a></div><div class="ttdeci">const Object * get() const</div><div class="ttdef"><b>Definition:</b> object.h:546</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>
diff --git a/docs/reference/api/doxygen/tensor__type_8h_source.html b/docs/reference/api/doxygen/tensor__type_8h_source.html
index 1bf8617ee..5868b7877 100644
--- a/docs/reference/api/doxygen/tensor__type_8h_source.html
+++ b/docs/reference/api/doxygen/tensor__type_8h_source.html
@@ -88,7 +88,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1TensorTypeNode_html_a84759da6fdc0984edcc65a8dda484505"><div class="ttname"><a href="classtvm_1_1TensorTypeNode.html#a84759da6fdc0984edcc65a8dda484505">tvm::TensorTypeNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const TensorTypeNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> tensor_type.h:77</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="classtvm_1_1TypeNode_html"><div class="ttname"><a href="classtvm_1_1TypeNode.html">tvm::TypeNode</a></div><div class="ttdoc">Type is the base type of all types. </div><div class="ttdef"><b>Definition:</b> type.h:74</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="classtvm_1_1BaseTensorTypeNode_html_afc675db92c700532b65fe819b1a37eb5"><div class="ttname"><a href="classtvm_1_1BaseTensorTypeNode.html#afc675db92c700532b65fe819b1a37eb5">tvm::BaseTensorTypeNode::TVM_DECLARE_BASE_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_BASE_OBJECT_INFO(BaseTensorTypeNode, TypeNode)</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="object_8h_html_a3aea9b3f65aeb9150c0fa7800e5573c6"><div class="ttname"><a href="object_8h.html#a3aea9b3f65aeb9150c0fa7800e5573c6">TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">#define TVM_DECLARE_FINAL_OBJECT_INFO(TypeName, ParentType)</div><div class="ttdoc">helper macro to declare type information in a final class. </div><div class="ttdef"><b>Definition:</b> object.h:671</div></div>
diff --git a/docs/reference/api/doxygen/topi_2nn_8h_source.html b/docs/reference/api/doxygen/topi_2nn_8h_source.html
index ad10cd1ae..a4b21400e 100644
--- a/docs/reference/api/doxygen/topi_2nn_8h_source.html
+++ b/docs/reference/api/doxygen/topi_2nn_8h_source.html
@@ -102,7 +102,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a0250c4095f19ae8a22ed85bc4ce5a40d"><div class="ttname"><a href="namespacetvm_1_1topi.html#a0250c4095f19ae8a22ed85bc4ce5a40d">tvm::topi::kElementWise</a></div><div class="ttdeci">constexpr auto kElementWise</div><div class="ttdef"><b>Definition:</b> tags.h:32</div></div>
<div class="ttc" id="namespacetvm_html_a8f30aa0685ca52f846843e76a1ad1dc7"><div class="ttname"><a href="namespacetvm.html#a8f30aa0685ca52f846843e76a1ad1dc7">tvm::indexdiv</a></div><div class="ttdeci">PrimExpr indexdiv(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute floor(a / b) where a and b are non-negative. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a786c950302117f8bdbbcab523f7b83bb"><div class="ttname"><a href="namespacetvm_1_1topi.html#a786c950302117f8bdbbcab523f7b83bb">tvm::topi::depthwise_conv2d_nchw</a></div><div class="ttdeci">tvm::te::Tensor depthwise_conv2d_nchw(const tvm::te::Tensor &I, const tvm::te::Tensor &W, int pad_h=0, int pad_w=0, int stride_h=1, int stride_w=1, std::string name="T_depthwise_conv2d_nchw", std::string tag=kDepthwiseConv2dNCHW)</div><div [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
<div class="ttc" id="namespacetvm_1_1te_html_aae384e9b73c2271905486e4a74b69265"><div class="ttname"><a href="namespacetvm_1_1te.html#aae384e9b73c2271905486e4a74b69265">tvm::te::reduce_axis</a></div><div class="ttdeci">IterVar reduce_axis(Range dom, std::string name="rv")</div><div class="ttdoc">Create a new IterVar for reduction operations. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a3305d377f96cd20c23032eeada2756d5"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi::pad</a></div><div class="ttdeci">tvm::te::Tensor 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=kElem [...]
<div class="ttc" id="namespacetvm_html_a27d5567b95675d383c4675fdcd85346c"><div class="ttname"><a href="namespacetvm.html#a27d5567b95675d383c4675fdcd85346c">tvm::logical_and</a></div><div class="ttdeci">PrimExpr logical_and(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">and </div></div>
@@ -120,7 +120,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1te_html_afe4f57aeb3dd5ae9c0b58135e14d67ca"><div class="ttname"><a href="namespacetvm_1_1te.html#afe4f57aeb3dd5ae9c0b58135e14d67ca">tvm::te::compute</a></div><div class="ttdeci">Tensor compute(Array< PrimExpr > shape, FCompute fcompute, std::string name="tensor", std::string tag="", Map< String, ObjectRef > attrs={})</div><div class="ttdoc">Construct a new tensor by computing over shape, using the computation rule: resul [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a3aad65f2505802109ba7d05359ce9005"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3aad65f2505802109ba7d05359ce9005">tvm::topi::reshape</a></div><div class="ttdeci">Tensor reshape(const Tensor &x, Array< PrimExpr > newshape, std::string name="T_reshape", std::string tag=kInjective)</div><div class="ttdoc">Reshape a tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:319</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_ae99fdff7b3aaceb091b636b8dadd4f5e"><div class="ttname"><a href="namespacetvm_1_1topi.html#ae99fdff7b3aaceb091b636b8dadd4f5e">tvm::topi::relu</a></div><div class="ttdeci">tvm::te::Tensor relu(const tvm::te::Tensor &t, T threshold=static_cast< T >(0), std::string name="T_relu", std::string tag=kElementWise)</div><div class="ttdoc">Creates an operation that performs a rectified linear unit. </div><div class="ttdef"><b>Defini [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a208e90d4a8db8cf2c7d77b4460f7df70"><div class="ttname"><a href="namespacetvm_1_1topi.html#a208e90d4a8db8cf2c7d77b4460f7df70">tvm::topi::strided_slice</a></div><div class="ttdeci">Tensor strided_slice(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, std::string slice_mode="end", std::string name="T_strided_slice", std::string tag [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a208e90d4a8db8cf2c7d77b4460f7df70"><div class="ttname"><a href="namespacetvm_1_1topi.html#a208e90d4a8db8cf2c7d77b4460f7df70">tvm::topi::strided_slice</a></div><div class="ttdeci">Tensor strided_slice(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, std::string slice_mode="end", std::string name="T_strided_slice", std::string tag [...]
<div class="ttc" id="classtvm_1_1PrimExpr_html"><div class="ttname"><a href="classtvm_1_1PrimExpr.html">tvm::PrimExpr</a></div><div class="ttdoc">Reference to PrimExprNode. </div><div class="ttdef"><b>Definition:</b> expr.h:112</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a315c34bbe2bf1be4c778acae08c906fc"><div class="ttname"><a href="namespacetvm_1_1topi.html#a315c34bbe2bf1be4c778acae08c906fc">tvm::topi::prelu</a></div><div class="ttdeci">tvm::te::Tensor prelu(const tvm::te::Tensor &x, const tvm::te::Tensor &slope, const int axis=1, std::string name="T_prelu", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation that performs a parametric rectified linear unit. </div><di [...]
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html">tvm::arith::Analyzer</a></div><div class="ttdoc">Analyzer that contains bunch of sub-analyzers. </div><div class="ttdef"><b>Definition:</b> analyzer.h:387</div></div>
diff --git a/docs/reference/api/doxygen/topi_2transform_8h_source.html b/docs/reference/api/doxygen/topi_2transform_8h_source.html
index d3c0dbce8..457146fa6 100644
--- a/docs/reference/api/doxygen/topi_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/topi_2transform_8h_source.html
@@ -66,66 +66,66 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="topi_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 [...]
+<a href="topi_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 [...]
<div class="ttc" id="namespacetvm_html_aac2abc149c1a47944c37b560181b15c0"><div class="ttname"><a href="namespacetvm.html#aac2abc149c1a47944c37b560181b15c0">tvm::min</a></div><div class="ttdeci">PrimExpr min(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take minimum of two values </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html_a35389f5ca857483ea65756bb2ceaa944"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a35389f5ca857483ea65756bb2ceaa944">tvm::tir::Layout::Equals</a></div><div class="ttdeci">bool Equals(const Layout &rhs) const</div><div class="ttdoc">Whether the two layouts are equal. </div><div class="ttdef"><b>Definition:</b> data_layout.h:276</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_acd9415b24624edac4edec4802d275062"><div class="ttname"><a href="namespacetvm_1_1topi.html#acd9415b24624edac4edec4802d275062">tvm::topi::strided_slice_with_axes</a></div><div class="ttdeci">Tensor strided_slice_with_axes(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, std::string slice_mode="end", s [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a877e6fdffb6b6c051c29602ec6fe995c"><div class="ttname"><a href="namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c">tvm::topi::sparse_to_dense</a></div><div class="ttdeci">Tensor sparse_to_dense(const Tensor &sparse_indices, const Array< PrimExpr > &output_shape, const Tensor &sparse_values, const PrimExpr &default_value, const std::string name="T_sparse_to_dense", const std::string tag=kInjective)</d [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_acd9415b24624edac4edec4802d275062"><div class="ttname"><a href="namespacetvm_1_1topi.html#acd9415b24624edac4edec4802d275062">tvm::topi::strided_slice_with_axes</a></div><div class="ttdeci">Tensor strided_slice_with_axes(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, std::string slice_mode="end", s [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a877e6fdffb6b6c051c29602ec6fe995c"><div class="ttname"><a href="namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c">tvm::topi::sparse_to_dense</a></div><div class="ttdeci">Tensor sparse_to_dense(const Tensor &sparse_indices, const Array< PrimExpr > &output_shape, const Tensor &sparse_values, const PrimExpr &default_value, const std::string name="T_sparse_to_dense", const std::string tag=kInjective)</d [...]
<div class="ttc" id="namespacetvm_html_ada5ad8338d3144221d8f16380e6c4855"><div class="ttname"><a href="namespacetvm.html#ada5ad8338d3144221d8f16380e6c4855">tvm::indexmod</a></div><div class="ttdeci">PrimExpr indexmod(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute the remainder floor(a / b) where a and b are non-negative. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_aff75b2e533b654909ca1bd9485ef4e6b"><div class="ttname"><a href="namespacetvm_1_1topi.html#aff75b2e533b654909ca1bd9485ef4e6b">tvm::topi::StridedSliceOutputShape</a></div><div class="ttdeci">Array< PrimExpr > StridedSliceOutputShape(const Array< PrimExpr > &ishape, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, co [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_aff75b2e533b654909ca1bd9485ef4e6b"><div class="ttname"><a href="namespacetvm_1_1topi.html#aff75b2e533b654909ca1bd9485ef4e6b">tvm::topi::StridedSliceOutputShape</a></div><div class="ttdeci">Array< PrimExpr > StridedSliceOutputShape(const Array< PrimExpr > &ishape, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, co [...]
<div class="ttc" id="namespacetvm_1_1tir_html_a1a071208bbbab6b220cf46f5cdccdd86"><div class="ttname"><a href="namespacetvm_1_1tir.html#a1a071208bbbab6b220cf46f5cdccdd86">tvm::tir::make_const</a></div><div class="ttdeci">PrimExpr make_const(DataType t, ValueType value, Span span=Span())</div><div class="ttdoc">Make a const value with certain data type. </div><div class="ttdef"><b>Definition:</b> op.h:1144</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a3230e1735957c2045c89cf190e0f8c34"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3230e1735957c2045c89cf190e0f8c34">tvm::topi::sliding_window</a></div><div class="ttdeci">Tensor sliding_window(const Tensor &x, int axis, Array< Integer > window_shape, Array< Integer > strides, std::string name="T_sliding_window", std::string tag="")</div><div class="ttdoc">Creates an operation to slide a window ove [...]
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> autodiff.h:35</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_abf2712c8265393c0582c9c7d5ae22da1"><div class="ttname"><a href="namespacetvm_1_1topi.html#abf2712c8265393c0582c9c7d5ae22da1">tvm::topi::tensordot</a></div><div class="ttdeci">Tensor tensordot(const Tensor &A, const tvm::te::Tensor &B, int axes=2, std::string name="T_tensordot", std::string tag=kMatMul)</div><div class="ttdoc">A generalization of matrix multiplication to tensors. </div><div class="ttdef"><b>Definition:</b> t [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a2f4969306206bc345bd3be840f56999e"><div class="ttname"><a href="namespacetvm_1_1topi.html#a2f4969306206bc345bd3be840f56999e">tvm::topi::dynamic_strided_slice</a></div><div class="ttdeci">Tensor dynamic_strided_slice(const Tensor &x, const Array< PrimExpr > &begin, const Array< PrimExpr > &end, const Array< PrimExpr > &strides, std::string name="T_dynamic_strided_slice", std::string tag=kInjective)< [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_abf2712c8265393c0582c9c7d5ae22da1"><div class="ttname"><a href="namespacetvm_1_1topi.html#abf2712c8265393c0582c9c7d5ae22da1">tvm::topi::tensordot</a></div><div class="ttdeci">Tensor tensordot(const Tensor &A, const tvm::te::Tensor &B, int axes=2, std::string name="T_tensordot", std::string tag=kMatMul)</div><div class="ttdoc">A generalization of matrix multiplication to tensors. </div><div class="ttdef"><b>Definition:</b> t [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a2f4969306206bc345bd3be840f56999e"><div class="ttname"><a href="namespacetvm_1_1topi.html#a2f4969306206bc345bd3be840f56999e">tvm::topi::dynamic_strided_slice</a></div><div class="ttdeci">Tensor dynamic_strided_slice(const Tensor &x, const Array< PrimExpr > &begin, const Array< PrimExpr > &end, const Array< PrimExpr > &strides, std::string name="T_dynamic_strided_slice", std::string tag=kInjective)< [...]
<div class="ttc" id="namespacetvm_html_a5e4738caa6bcd0259af64b25e25dfd93"><div class="ttname"><a href="namespacetvm.html#a5e4738caa6bcd0259af64b25e25dfd93">tvm::ceil</a></div><div class="ttdeci">PrimExpr ceil(PrimExpr x, Span span=Span())</div><div class="ttdoc">Calculate ceil(x) </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="namespacetvm_1_1topi_html_af011847b6e7f72f1bec25eee05c80590"><div class="ttname"><a href="namespacetvm_1_1topi.html#af011847b6e7f72f1bec25eee05c80590">tvm::topi::where</a></div><div class="ttdeci">Tensor where(const Tensor &condition, const Tensor &x, const Tensor &y, std::string name="T_where", std::string tag=kBroadcast)</div><div class="ttdoc">Return the elements, either from x or y, depending on the condition. </div><div class="ttdef"><b>Def [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a3cf4e56cbd8144b9029672b7c5ebd161"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3cf4e56cbd8144b9029672b7c5ebd161">tvm::topi::one_hot</a></div><div class="ttdeci">Tensor one_hot(const Tensor &indices, const PrimExpr on_value, const PrimExpr off_value, int depth, int axis, const DataType &dtype, Array< PrimExpr > oshape=Array< PrimExpr >(), const std::string name="T_one_hot", const std::string tag=kInje [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af011847b6e7f72f1bec25eee05c80590"><div class="ttname"><a href="namespacetvm_1_1topi.html#af011847b6e7f72f1bec25eee05c80590">tvm::topi::where</a></div><div class="ttdeci">Tensor where(const Tensor &condition, const Tensor &x, const Tensor &y, std::string name="T_where", std::string tag=kBroadcast)</div><div class="ttdoc">Return the elements, either from x or y, depending on the condition. </div><div class="ttdef"><b>Def [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a3cf4e56cbd8144b9029672b7c5ebd161"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3cf4e56cbd8144b9029672b7c5ebd161">tvm::topi::one_hot</a></div><div class="ttdeci">Tensor one_hot(const Tensor &indices, const PrimExpr on_value, const PrimExpr off_value, int depth, int axis, const DataType &dtype, Array< PrimExpr > oshape=Array< PrimExpr >(), const std::string name="T_one_hot", const std::string tag=kInje [...]
<div class="ttc" id="namespacetvm_html_a353217978feabae3575560bf1586885f"><div class="ttname"><a href="namespacetvm.html#a353217978feabae3575560bf1586885f">tvm::if_then_else</a></div><div class="ttdeci">PrimExpr if_then_else(PrimExpr cond, PrimExpr true_value, PrimExpr false_value, Span span=Span())</div><div class="ttdoc">Conditional expression. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_aead477c6c9d4f4589d22b8acff82040c"><div class="ttname"><a href="namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c">tvm::topi::matrix_set_diag</a></div><div class="ttdeci">Tensor matrix_set_diag(const Tensor &input, const Tensor &diagonal, int k1, int k2, bool super_diag_right_align, bool sub_diag_right_align, const std::string name="T_matrix_set_diag", const std::string tag=kInjective)</div><div class="ttdoc">Retu [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_aead477c6c9d4f4589d22b8acff82040c"><div class="ttname"><a href="namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c">tvm::topi::matrix_set_diag</a></div><div class="ttdeci">Tensor matrix_set_diag(const Tensor &input, const Tensor &diagonal, int k1, int k2, bool super_diag_right_align, bool sub_diag_right_align, const std::string name="T_matrix_set_diag", const std::string tag=kInjective)</div><div class="ttdoc">Retu [...]
<div class="ttc" id="namespacetvm_1_1topi_html_aa9f70e7392653f38da6ff53f5f554f98"><div class="ttname"><a href="namespacetvm_1_1topi.html#aa9f70e7392653f38da6ff53f5f554f98">tvm::topi::kMatMul</a></div><div class="ttdeci">constexpr auto kMatMul</div><div class="ttdef"><b>Definition:</b> tags.h:37</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a29e22aa45900dad3b6f9f705bb1dc688"><div class="ttname"><a href="namespacetvm_1_1topi.html#a29e22aa45900dad3b6f9f705bb1dc688">tvm::topi::kInjective</a></div><div class="ttdeci">constexpr auto kInjective</div><div class="ttdef"><b>Definition:</b> tags.h:33</div></div>
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html_a9b440f852f12ad0a4d8ed5ed97054425"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html#a9b440f852f12ad0a4d8ed5ed97054425">tvm::arith::Analyzer::Simplify</a></div><div class="ttdeci">PrimExpr Simplify(const PrimExpr &expr, int steps=2)</div><div class="ttdoc">Simplify expr. </div></div>
<div class="ttc" id="strided__slice_8h_html"><div class="ttname"><a href="strided__slice_8h.html">strided_slice.h</a></div><div class="ttdoc">Utility functions for strided_slice op. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a8811a02532bbe3047986bf1a8449ac0e"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e">tvm::topi::unravel_index</a></div><div class="ttdeci">Tensor unravel_index(const Tensor &x, const Tensor &shape, std::string name="T_unravel", std::string tag=kInjective)</div><div class="ttdoc">Converts a flat index or array of flat indices into a tuple of coordinate arrays. ...</div><div class="ttde [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_af4e59b01a5842baf6b47ad3f83731f53"><div class="ttname"><a href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi::split</a></div><div class="ttdeci">Array< Tensor > split(const Tensor &x, Array< PrimExpr > split_indices, int axis, std::string name="T_split", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into multiple sub-tensors. </div><div class="ttdef"><b>Definition:</b> [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a6fec3a88d419cd018cf1041cf3d99204"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6fec3a88d419cd018cf1041cf3d99204">tvm::topi::parse_auto_scheduler_layout</a></div><div class="ttdeci">void parse_auto_scheduler_layout(const String &layout, Array< PrimExpr > *shape, std::vector< std::string > *axes)</div><div class="ttdoc">Utility function for auto_scheduler_layout_transform. </div><div class="ttdef"><b>Definition:</b> [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_af392bc8e9dc0d34792652a4c0cf92243"><div class="ttname"><a href="namespacetvm_1_1topi.html#af392bc8e9dc0d34792652a4c0cf92243">tvm::topi::gather</a></div><div class="ttdeci">Tensor gather(const Tensor &data, int axis, const Tensor &indices, std::string name="T_gather", std::string tag=kInjective)</div><div class="ttdoc">Gather values along given axis from given indices. </div><div class="ttdef"><b>Definition:</b> transform.h: [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a8811a02532bbe3047986bf1a8449ac0e"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e">tvm::topi::unravel_index</a></div><div class="ttdeci">Tensor unravel_index(const Tensor &x, const Tensor &shape, std::string name="T_unravel", std::string tag=kInjective)</div><div class="ttdoc">Converts a flat index or array of flat indices into a tuple of coordinate arrays. ...</div><div class="ttde [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af4e59b01a5842baf6b47ad3f83731f53"><div class="ttname"><a href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi::split</a></div><div class="ttdeci">Array< Tensor > split(const Tensor &x, Array< PrimExpr > split_indices, int axis, std::string name="T_split", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into multiple sub-tensors. </div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a6fec3a88d419cd018cf1041cf3d99204"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6fec3a88d419cd018cf1041cf3d99204">tvm::topi::parse_auto_scheduler_layout</a></div><div class="ttdeci">void parse_auto_scheduler_layout(const String &layout, Array< PrimExpr > *shape, std::vector< std::string > *axes)</div><div class="ttdoc">Utility function for auto_scheduler_layout_transform. </div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af392bc8e9dc0d34792652a4c0cf92243"><div class="ttname"><a href="namespacetvm_1_1topi.html#af392bc8e9dc0d34792652a4c0cf92243">tvm::topi::gather</a></div><div class="ttdeci">Tensor gather(const Tensor &data, int axis, const Tensor &indices, std::string name="T_gather", std::string tag=kInjective)</div><div class="ttdoc">Gather values along given axis from given indices. </div><div class="ttdef"><b>Definition:</b> transform.h: [...]
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html_a7c8d978e9905bb0f0f88226d4f5cbe7a"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html#a7c8d978e9905bb0f0f88226d4f5cbe7a">tvm::te::Tensor::ndim</a></div><div class="ttdeci">size_t ndim() const</div><div class="ttdef"><b>Definition:</b> tensor.h:214</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a5efc5887d91eb272e31c10f4e014a034"><div class="ttname"><a href="namespacetvm_1_1topi.html#a5efc5887d91eb272e31c10f4e014a034">tvm::topi::dyn_tile</a></div><div class="ttdeci">Tensor dyn_tile(const Tensor &x, Array< PrimExpr > new_shape, size_t rdim, std::string name="T_tile", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to tile elements of an array. </div><div class="ttdef"><b>Definition:</b> tr [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a8a41a08eee70607889b738946ed97873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8a41a08eee70607889b738946ed97873">tvm::topi::layout_transform</a></div><div class="ttdeci">Tensor layout_transform(const Tensor &src, const std::string &src_layout, const std::string &dst_layout, const std::string name="T_layout_trans", const std::string tag=kInjective)</div><div class="ttdoc">Transform the layout according to src [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a8e10f74deef4f22a9dc4b0a0b4370b08"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8e10f74deef4f22a9dc4b0a0b4370b08">tvm::topi::auto_scheduler_layout_transform</a></div><div class="ttdeci">Tensor auto_scheduler_layout_transform(const Tensor &src, const String &src_layout, const String &dst_layout, const String name="T_auto_scheduler_layout_trans", const String tag=kInjective)</div><div class="ttdoc">Transform th [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a5efc5887d91eb272e31c10f4e014a034"><div class="ttname"><a href="namespacetvm_1_1topi.html#a5efc5887d91eb272e31c10f4e014a034">tvm::topi::dyn_tile</a></div><div class="ttdeci">Tensor dyn_tile(const Tensor &x, Array< PrimExpr > new_shape, size_t rdim, std::string name="T_tile", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to tile elements of an array. </div><div class="ttdef"><b>Definition:</b> tr [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a8a41a08eee70607889b738946ed97873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8a41a08eee70607889b738946ed97873">tvm::topi::layout_transform</a></div><div class="ttdeci">Tensor layout_transform(const Tensor &src, const std::string &src_layout, const std::string &dst_layout, const std::string name="T_layout_trans", const std::string tag=kInjective)</div><div class="ttdoc">Transform the layout according to src [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a8e10f74deef4f22a9dc4b0a0b4370b08"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8e10f74deef4f22a9dc4b0a0b4370b08">tvm::topi::auto_scheduler_layout_transform</a></div><div class="ttdeci">Tensor auto_scheduler_layout_transform(const Tensor &src, const String &src_layout, const String &dst_layout, const String name="T_auto_scheduler_layout_trans", const String tag=kInjective)</div><div class="ttdoc">Transform th [...]
<div class="ttc" id="namespacetvm_html_a4bfb789a86d95f6241b50fd26f269c28"><div class="ttname"><a href="namespacetvm.html#a4bfb789a86d95f6241b50fd26f269c28">tvm::cast</a></div><div class="ttdeci">PrimExpr cast(const DataType &t, PrimExpr value, Span span=Span())</div><div class="ttdoc">cast value to type. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a845e38c0f34017d45ec318935b6ddf17"><div class="ttname"><a href="namespacetvm_1_1topi.html#a845e38c0f34017d45ec318935b6ddf17">tvm::topi::squeeze</a></div><div class="ttdeci">Tensor squeeze(const Tensor &x, Array< Integer > axis, bool atleast1d=false, std::string name="T_squeeze", std::string tag=kInjective)</div><div class="ttdoc">Remove size 1 dimensions from the shape of a tensor. The removed dimensions must have a const [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a845e38c0f34017d45ec318935b6ddf17"><div class="ttname"><a href="namespacetvm_1_1topi.html#a845e38c0f34017d45ec318935b6ddf17">tvm::topi::squeeze</a></div><div class="ttdeci">Tensor squeeze(const Tensor &x, Array< Integer > axis, bool atleast1d=false, std::string name="T_squeeze", std::string tag=kInjective)</div><div class="ttdoc">Remove size 1 dimensions from the shape of a tensor. The removed dimensions must have a const [...]
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_ab5db2ee9a8be71931324dac552be24c4"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#ab5db2ee9a8be71931324dac552be24c4">tvm::runtime::Array::Set</a></div><div class="ttdeci">void Set(int64_t i, T value)</div><div class="ttdoc">set i-th element of the array. </div><div class="ttdef"><b>Definition:</b> array.h:567</div></div>
<div class="ttc" id="classtvm_1_1IntImmNode_html"><div class="ttname"><a href="classtvm_1_1IntImmNode.html">tvm::IntImmNode</a></div><div class="ttdoc">Constant integer literals in the program. </div><div class="ttdef"><b>Definition:</b> expr.h:274</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_aa026b914ee05f81b6c20130b8905f257"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#aa026b914ee05f81b6c20130b8905f257">tvm::runtime::Array::push_back</a></div><div class="ttdeci">void push_back(const T &item)</div><div class="ttdoc">push a new item to the back of the list </div><div class="ttdef"><b>Definition:</b> array.h:436</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a7ddbd03d0d29a05618a1ef42f717ec9f"><div class="ttname"><a href="namespacetvm_1_1topi.html#a7ddbd03d0d29a05618a1ef42f717ec9f">tvm::topi::expand_dims</a></div><div class="ttdeci">Tensor expand_dims(const Tensor &x, int axis, int num_newaxis=1, std::string name="T_expand_dims", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to insert new dimensions of length 1. </div><div class="ttdef"><b>Definition:</b> [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a46fb3ad8c3324ee094fb356ebc07245f"><div class="ttname"><a href="namespacetvm_1_1topi.html#a46fb3ad8c3324ee094fb356ebc07245f">tvm::topi::tile</a></div><div class="ttdeci">Tensor tile(const Tensor &x, Array< Integer > reps, std::string name="T_tile", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to tile elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1217</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a46fb3ad8c3324ee094fb356ebc07245f"><div class="ttname"><a href="namespacetvm_1_1topi.html#a46fb3ad8c3324ee094fb356ebc07245f">tvm::topi::tile</a></div><div class="ttdeci">Tensor tile(const Tensor &x, Array< Integer > reps, std::string name="T_tile", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to tile elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1218</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_abee7c35e8c15e2e61afe35852dfcb252"><div class="ttname"><a href="namespacetvm_1_1topi.html#abee7c35e8c15e2e61afe35852dfcb252">tvm::topi::sum</a></div><div class="ttdeci">Tensor sum(const Tensor &data, const Array< Integer > &axis, bool keepdims=false, bool atleast1d=false)</div><div class="ttdoc">Creates an operation that sums array elements over a given axis. </div><div class="ttdef"><b>Definition:</b> reduction.h:326</div></div>
<div class="ttc" id="constant__utils_8h_html"><div class="ttname"><a href="constant__utils_8h.html">constant_utils.h</a></div><div class="ttdoc">Utility functions for handling constants in TVM expressions. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a13aaf23f0ab77f1ed4a7d4b7816bf210"><div class="ttname"><a href="namespacetvm_1_1topi.html#a13aaf23f0ab77f1ed4a7d4b7816bf210">tvm::topi::kBroadcast</a></div><div class="ttdeci">constexpr auto kBroadcast</div><div class="ttdef"><b>Definition:</b> tags.h:36</div></div>
<div class="ttc" id="classtvm_1_1Range_html"><div class="ttname"><a href="classtvm_1_1Range.html">tvm::Range</a></div><div class="ttdoc">Range constainer. </div><div class="ttdef"><b>Definition:</b> expr.h:496</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a1db52a53bfb38341ef89b375562731c6"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1db52a53bfb38341ef89b375562731c6">tvm::topi::arange</a></div><div class="ttdeci">Tensor arange(const PrimExpr &start, const PrimExpr &stop, const PrimExpr &step, DataType dtype, std::string name="T_arange", std::string tag=kInjective)</div><div class="ttdef"><b>Definition:</b> transform.h:1534</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a1db52a53bfb38341ef89b375562731c6"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1db52a53bfb38341ef89b375562731c6">tvm::topi::arange</a></div><div class="ttdeci">Tensor arange(const PrimExpr &start, const PrimExpr &stop, const PrimExpr &step, DataType dtype, std::string name="T_arange", std::string tag=kInjective)</div><div class="ttdef"><b>Definition:</b> transform.h:1535</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_aed6387e67d18b9d5ad18f510fd600a25"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#aed6387e67d18b9d5ad18f510fd600a25">tvm::runtime::Array::size</a></div><div class="ttdeci">size_t size() const</div><div class="ttdef"><b>Definition:</b> array.h:399</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html">tvm::runtime::DataType</a></div><div class="ttdoc">Runtime primitive data type. </div><div class="ttdef"><b>Definition:</b> data_type.h:41</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_a17d8d5ad92691f9e18e3e0ae8ef69e4f"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#a17d8d5ad92691f9e18e3e0ae8ef69e4f">tvm::runtime::ObjectRef::defined</a></div><div class="ttdeci">bool defined() const</div><div class="ttdef"><b>Definition:</b> object.h:544</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_acb438962b08475a05e086907bf8eb26a"><div class="ttname"><a href="namespacetvm_1_1topi.html#acb438962b08475a05e086907bf8eb26a">tvm::topi::stack</a></div><div class="ttdeci">Tensor stack(const Array< Tensor > &inputs, int axis=0, std::string name="T_stack", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along a new axis. </div><div class="ttdef"><b>Definition:</b> transform.h:527</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_acb438962b08475a05e086907bf8eb26a"><div class="ttname"><a href="namespacetvm_1_1topi.html#acb438962b08475a05e086907bf8eb26a">tvm::topi::stack</a></div><div class="ttdeci">Tensor stack(const Array< Tensor > &inputs, int axis=0, std::string name="T_stack", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along a new axis. </div><div class="ttdef"><b>Definition:</b> transform.h:528</div></div>
<div class="ttc" id="tensor__utils_8h_html"><div class="ttname"><a href="tensor__utils_8h.html">tensor_utils.h</a></div><div class="ttdoc">Utility functions for handling tensor. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_a237a714a6a16e14aa01fa4ac52426551"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#a237a714a6a16e14aa01fa4ac52426551">tvm::runtime::DataType::Float</a></div><div class="ttdeci">static DataType Float(int bits, int lanes=1)</div><div class="ttdoc">Construct an float type. </div><div class="ttdef"><b>Definition:</b> data_type.h:168</div></div>
<div class="ttc" id="namespacetvm_html_afdad0c0329bd39949ba8d296cfb85d76"><div class="ttname"><a href="namespacetvm.html#afdad0c0329bd39949ba8d296cfb85d76">tvm::sum</a></div><div class="ttdeci">PrimExpr sum(PrimExpr source, Array< tir::IterVar > axis, Array< PrimExpr > init={}, Span span=Span())</div><div class="ttdoc">sum of of source expression over axis </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_html_a8f30aa0685ca52f846843e76a1ad1dc7"><div class="ttname"><a href="namespacetvm.html#a8f30aa0685ca52f846843e76a1ad1dc7">tvm::indexdiv</a></div><div class="ttdeci">PrimExpr indexdiv(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute floor(a / b) where a and b are non-negative. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a6f3c749dadc49aa100626ef85a04a66b"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6f3c749dadc49aa100626ef85a04a66b">tvm::topi::concatenate</a></div><div class="ttdeci">Tensor concatenate(const Array< Tensor > &inputs, int axis=0, std::string name="T_concat", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along an existing axis. </div><div class="ttdef"><b>Definition:</b> transform. [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_aa1468cc7d8f47a44800fa38d6377ae67"><div class="ttname"><a href="namespacetvm_1_1topi.html#aa1468cc7d8f47a44800fa38d6377ae67">tvm::topi::take</a></div><div class="ttdeci">Tensor take(const Tensor &a, const Tensor &indices, int batch_dims, std::string mode="clip", std::string name="T_take", std::string tag=kInjective)</div><div class="ttdoc">Take elements from an flattened input array when axis is None. </div><div c [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a6f3c749dadc49aa100626ef85a04a66b"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6f3c749dadc49aa100626ef85a04a66b">tvm::topi::concatenate</a></div><div class="ttdeci">Tensor concatenate(const Array< Tensor > &inputs, int axis=0, std::string name="T_concat", std::string tag=kInjective)</div><div class="ttdoc">Join a sequence of tensors along an existing axis. </div><div class="ttdef"><b>Definition:</b> transform. [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_aa1468cc7d8f47a44800fa38d6377ae67"><div class="ttname"><a href="namespacetvm_1_1topi.html#aa1468cc7d8f47a44800fa38d6377ae67">tvm::topi::take</a></div><div class="ttdeci">Tensor take(const Tensor &a, const Tensor &indices, int batch_dims, std::string mode="clip", std::string name="T_take", std::string tag=kInjective)</div><div class="ttdoc">Take elements from an flattened input array when axis is None. </div><div c [...]
<div class="ttc" id="classtvm_1_1IntImm_html"><div class="ttname"><a href="classtvm_1_1IntImm.html">tvm::IntImm</a></div><div class="ttdoc">Managed reference class to IntImmNode. </div><div class="ttdef"><b>Definition:</b> expr.h:303</div></div>
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="classtvm_1_1IntImmNode_html_a81f4c116ffb5931fdd64639eacad415d"><div class="ttname"><a href="classtvm_1_1IntImmNode.html#a81f4c116ffb5931fdd64639eacad415d">tvm::IntImmNode::value</a></div><div class="ttdeci">int64_t value</div><div class="ttdoc">the Internal value. </div><div class="ttdef"><b>Definition:</b> expr.h:277</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_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1700</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a453f9f5a35a9852a086ce0228ee22164"><div class="ttname"><a href="namespacetvm_1_1topi.html#a453f9f5a35a9852a086ce0228ee22164">tvm::topi::meshgrid</a></div><div class="ttdeci">Array< Tensor > meshgrid(const Array< Tensor > &inputs, const std::string &indexing, std::string name="T_meshgrid", std::string tag=kInjective)</div><div class="ttdoc">Produce grids by expanding input over dimensions defined by other inputs. [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a453f9f5a35a9852a086ce0228ee22164"><div class="ttname"><a href="namespacetvm_1_1topi.html#a453f9f5a35a9852a086ce0228ee22164">tvm::topi::meshgrid</a></div><div class="ttdeci">Array< Tensor > meshgrid(const Array< Tensor > &inputs, const std::string &indexing, std::string name="T_meshgrid", std::string tag=kInjective)</div><div class="ttdoc">Produce grids by expanding input over dimensions defined by other inputs. [...]
<div class="ttc" id="namespacetvm_1_1te_html_aae384e9b73c2271905486e4a74b69265"><div class="ttname"><a href="namespacetvm_1_1te.html#aae384e9b73c2271905486e4a74b69265">tvm::te::reduce_axis</a></div><div class="ttdeci">IterVar reduce_axis(Range dom, std::string name="rv")</div><div class="ttdoc">Create a new IterVar for reduction operations. </div></div>
<div class="ttc" id="namespacetvm_html_a2428ea0e23bd9f7218aebd066bb2cd88"><div class="ttname"><a href="namespacetvm.html#a2428ea0e23bd9f7218aebd066bb2cd88">tvm::truncmod</a></div><div class="ttdeci">PrimExpr truncmod(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute the remainder of truncdiv </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
@@ -136,28 +136,28 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1Select_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Select.html">tvm::tir::Select</a></div><div class="ttdoc">Managed reference to SelectNode. </div><div class="ttdef"><b>Definition:</b> expr.h:589</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BijectiveLayout_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BijectiveLayout.html">tvm::tir::BijectiveLayout</a></div><div class="ttdoc">Bijective function mapping for data layout transformation. Given two Layout, BijectiveLayout build an...</div><div class="ttdef"><b>Definition:</b> data_layout.h:330</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a1488ee98fd053e8b01b481f720df77fa"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1488ee98fd053e8b01b481f720df77fa">tvm::topi::transpose</a></div><div class="ttdeci">Tensor transpose(const Tensor &x, Array< Integer > axes, std::string name="T_transpose", std::string tag=kInjective)</div><div class="ttdoc">Permute the dimensions of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:195</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a92d2a9f409bae6731c5e5247de0b8c48"><div class="ttname"><a href="namespacetvm_1_1topi.html#a92d2a9f409bae6731c5e5247de0b8c48">tvm::topi::ndarray_size</a></div><div class="ttdeci">Tensor ndarray_size(const Tensor &src, const DataType &dtype, const std::string &name="ndarray_size", const std::string &tag=kInjective)</div><div class="ttdoc">Get the size of input tensor. </div><div class="ttdef"><b>Definition:</b> transf [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a037a112cc5c556107797e36e7feb0873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a037a112cc5c556107797e36e7feb0873">tvm::topi::sequence_mask</a></div><div class="ttdeci">Tensor sequence_mask(const Tensor &data, const Tensor &valid_length, double mask_value, int axis, std::string name="T_sequence_mask", std::string tag=kInjective)</div><div class="ttdoc">Mask the out-of-boundary elements of each sequence. </div><div [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a92d2a9f409bae6731c5e5247de0b8c48"><div class="ttname"><a href="namespacetvm_1_1topi.html#a92d2a9f409bae6731c5e5247de0b8c48">tvm::topi::ndarray_size</a></div><div class="ttdeci">Tensor ndarray_size(const Tensor &src, const DataType &dtype, const std::string &name="ndarray_size", const std::string &tag=kInjective)</div><div class="ttdoc">Get the size of input tensor. </div><div class="ttdef"><b>Definition:</b> transf [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a037a112cc5c556107797e36e7feb0873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a037a112cc5c556107797e36e7feb0873">tvm::topi::sequence_mask</a></div><div class="ttdeci">Tensor sequence_mask(const Tensor &data, const Tensor &valid_length, double mask_value, int axis, std::string name="T_sequence_mask", std::string tag=kInjective)</div><div class="ttdoc">Mask the out-of-boundary elements of each sequence. </div><div [...]
<div class="ttc" id="namespacetvm_html_a0da40d3e210aa3b38a17982a7b7866b8"><div class="ttname"><a href="namespacetvm.html#a0da40d3e210aa3b38a17982a7b7866b8">tvm::ret</a></div><div class="ttdeci">PrimExpr ret(PrimExpr value, Span span=Span())</div><div class="ttdoc">Return the value. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a6d9189f6ceb05cf0a309dbe3f2730b16"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6d9189f6ceb05cf0a309dbe3f2730b16">tvm::topi::adv_index</a></div><div class="ttdeci">Tensor adv_index(const Tensor &data, const Array< Tensor > &indices, const std::string name="advanced_index", const std::string tag=kInjective)</div><div class="ttdoc">Numpy style advanced indexing with tensor. </div><div class="ttdef"><b>Definit [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a6d9189f6ceb05cf0a309dbe3f2730b16"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6d9189f6ceb05cf0a309dbe3f2730b16">tvm::topi::adv_index</a></div><div class="ttdeci">Tensor adv_index(const Tensor &data, const Array< Tensor > &indices, const std::string name="advanced_index", const std::string tag=kInjective)</div><div class="ttdoc">Numpy style advanced indexing with tensor. </div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="tags_8h_html"><div class="ttname"><a href="tags_8h.html">tags.h</a></div><div class="ttdoc">External function interface to rocBLAS libraries. </div></div>
<div class="ttc" id="namespacetvm_1_1te_html_afe4f57aeb3dd5ae9c0b58135e14d67ca"><div class="ttname"><a href="namespacetvm_1_1te.html#afe4f57aeb3dd5ae9c0b58135e14d67ca">tvm::te::compute</a></div><div class="ttdeci">Tensor compute(Array< PrimExpr > shape, FCompute fcompute, std::string name="tensor", std::string tag="", Map< String, ObjectRef > attrs={})</div><div class="ttdoc">Construct a new tensor by computing over shape, using the computation rule: resul [...]
<div class="ttc" id="namespacetvm_1_1topi_html_ab8ad5eed3079de21c92a7639ed370096"><div class="ttname"><a href="namespacetvm_1_1topi.html#ab8ad5eed3079de21c92a7639ed370096">tvm::topi::reverse_sequence</a></div><div class="ttdeci">Tensor reverse_sequence(const Tensor &x, const Tensor &seq_lengths, int seq_axis=1, int batch_axis=0, std::string name="T_reverse_sequence", std::string tag=kInjective)</div><div class="ttdoc">Reverse the tensor for variable length slices. Input [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a7da4c96db87c1459a2b097b87afd811f"><div class="ttname"><a href="namespacetvm_1_1topi.html#a7da4c96db87c1459a2b097b87afd811f">tvm::topi::cast</a></div><div class="ttdeci">Tensor cast(const Tensor &x, DataType type, std::string name="T_cast", std::string tag=kElementWise)</div><div class="ttdoc">Cast each element of x to the given type. If expr is scalar and type is a corresponding vector type...</div><div class="ttdef"><b>Defini [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a3aad65f2505802109ba7d05359ce9005"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3aad65f2505802109ba7d05359ce9005">tvm::topi::reshape</a></div><div class="ttdeci">Tensor reshape(const Tensor &x, Array< PrimExpr > newshape, std::string name="T_reshape", std::string tag=kInjective)</div><div class="ttdoc">Reshape a tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:319</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a545c1404478aba2e2a44c77438da9fd5"><div class="ttname"><a href="namespacetvm_1_1topi.html#a545c1404478aba2e2a44c77438da9fd5">tvm::topi::broadcast_to</a></div><div class="ttdeci">tvm::te::Tensor broadcast_to(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &output_shape, std::string name="T_broadcast_to", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation that broadcasts a tensor into a [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1170</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a208e90d4a8db8cf2c7d77b4460f7df70"><div class="ttname"><a href="namespacetvm_1_1topi.html#a208e90d4a8db8cf2c7d77b4460f7df70">tvm::topi::strided_slice</a></div><div class="ttdeci">Tensor strided_slice(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, std::string slice_mode="end", std::string name="T_strided_slice", std::string tag [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_afe9f6d9103b2dfbc601bfd2304a4e687"><div class="ttname"><a href="namespacetvm_1_1topi.html#afe9f6d9103b2dfbc601bfd2304a4e687">tvm::topi::repeat</a></div><div class="ttdeci">Tensor repeat(const Tensor &x, int repeats, int axis, std::string name="T_repeat", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to repeat elements of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:1171</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a208e90d4a8db8cf2c7d77b4460f7df70"><div class="ttname"><a href="namespacetvm_1_1topi.html#a208e90d4a8db8cf2c7d77b4460f7df70">tvm::topi::strided_slice</a></div><div class="ttdeci">Tensor strided_slice(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, std::string slice_mode="end", std::string name="T_strided_slice", std::string tag [...]
<div class="ttc" id="broadcast_8h_html"><div class="ttname"><a href="broadcast_8h.html">broadcast.h</a></div><div class="ttdoc">Broadcast op constructions. </div></div>
<div class="ttc" id="classtvm_1_1PrimExpr_html"><div class="ttname"><a href="classtvm_1_1PrimExpr.html">tvm::PrimExpr</a></div><div class="ttdoc">Reference to PrimExprNode. </div><div class="ttdef"><b>Definition:</b> expr.h:112</div></div>
<div class="ttc" id="data__layout_8h_html"><div class="ttname"><a href="data__layout_8h.html">data_layout.h</a></div><div class="ttdoc">Layout expression to describe the data organization of a tensor. And BijectiveLayout to mapping two d...</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_1topi_html_a07cd700149e466463dac9a6954baa2ed"><div class="ttname"><a href="namespacetvm_1_1topi.html#a07cd700149e466463dac9a6954baa2ed">tvm::topi::gather_nd</a></div><div class="ttdeci">Tensor gather_nd(const Tensor &data, const Tensor &indices, int batch_dims=0, std::string name="T_gather_nd", std::string tag=kInjective)</div><div class="ttdoc">Gather elements from a n-dimension array. </div><div class="ttdef"><b>Definition:</b> tran [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_acc643e2ed166fa2ed82a95853e145619"><div class="ttname"><a href="namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619">tvm::topi::split_sections</a></div><div class="ttdeci">Array< Tensor > split_sections(const Tensor &x, int num_sections, int axis, std::string name="T_split_sections", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into a number of sub-tensors. </div><div class="ttdef"><b>Definit [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a07cd700149e466463dac9a6954baa2ed"><div class="ttname"><a href="namespacetvm_1_1topi.html#a07cd700149e466463dac9a6954baa2ed">tvm::topi::gather_nd</a></div><div class="ttdeci">Tensor gather_nd(const Tensor &data, const Tensor &indices, int batch_dims=0, std::string name="T_gather_nd", std::string tag=kInjective)</div><div class="ttdoc">Gather elements from a n-dimension array. </div><div class="ttdef"><b>Definition:</b> tran [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_acc643e2ed166fa2ed82a95853e145619"><div class="ttname"><a href="namespacetvm_1_1topi.html#acc643e2ed166fa2ed82a95853e145619">tvm::topi::split_sections</a></div><div class="ttdeci">Array< Tensor > split_sections(const Tensor &x, int num_sections, int axis, std::string name="T_split_sections", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into a number of sub-tensors. </div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="detail_2broadcast_8h_html"><div class="ttname"><a href="detail_2broadcast_8h.html">broadcast.h</a></div><div class="ttdoc">Detail broadcast. </div></div>
<div class="ttc" id="ravel__unravel_8h_html"><div class="ttname"><a href="ravel__unravel_8h.html">ravel_unravel.h</a></div><div class="ttdoc">Index ravel and unraval operations. </div></div>
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html">tvm::arith::Analyzer</a></div><div class="ttdoc">Analyzer that contains bunch of sub-analyzers. </div><div class="ttdef"><b>Definition:</b> analyzer.h:387</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_adae7dcb7e951109ba72192202d182994"><div class="ttname"><a href="namespacetvm_1_1topi.html#adae7dcb7e951109ba72192202d182994">tvm::topi::matmul</a></div><div class="ttdeci">tvm::te::Tensor matmul(const tvm::te::Tensor &A, const tvm::te::Tensor &B, bool trans_a=false, bool trans_b=false, std::string name="T_matmul", std::string tag=kMatMul)</div><div class="ttdoc">Creates an operation that calculates a matrix multiplication ( [...]
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_ab45f13dd70d982d9f977c79b6f7fac98"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#ab45f13dd70d982d9f977c79b6f7fac98">tvm::runtime::DataType::Int</a></div><div class="ttdeci">static DataType Int(int bits, int lanes=1)</div><div class="ttdoc">Construct an int type. </div><div class="ttdef"><b>Definition:</b> data_type.h:154</div></div>
<div class="ttc" id="classtvm_1_1Integer_html"><div class="ttname"><a href="classtvm_1_1Integer.html">tvm::Integer</a></div><div class="ttdoc">Container of constant int that adds more constructors. </div><div class="ttdef"><b>Definition:</b> expr.h:403</div></div>
</div><!-- fragment --></div><!-- contents -->
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index d6832861b..bf0a167f0 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ 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">
@@ -1750,7 +1750,7 @@ 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/relay/index.html b/docs/reference/api/python/relay/index.html
index 2b511f451..e6a1db8cd 100644
--- a/docs/reference/api/python/relay/index.html
+++ b/docs/reference/api/python/relay/index.html
@@ -644,7 +644,7 @@
<tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">repeat</span></code>(data, repeats, axis)</p></td>
<td><p>Repeats elements of an array.</p></td>
</tr>
-<tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reshape</span></code>(data, newshape)</p></td>
+<tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reshape</span></code>(data, newshape[, allowzero])</p></td>
<td><p>Reshape the input array.</p></td>
</tr>
<tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reshape_like</span></code>(data, shape_like[, lhs_begin, ...])</p></td>
@@ -3697,7 +3697,7 @@ return a flat output array.</p>
<dl class="py function">
<dt class="sig sig-object py">
-<span class="sig-prename descclassname"><span class="pre">tvm.relay.</span></span><span class="sig-name descname"><span class="pre">reshape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">newshape</span></span></em><span class="sig-paren">)</span></dt>
+<span class="sig-prename descclassname"><span class="pre">tvm.relay.</span></span><span class="sig-name descname"><span class="pre">reshape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">newshape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allowzero</span></span><span class="o"><span class="pre">=</span></span><span class=" [...]
<dd><p>Reshape the input array.</p>
<p>To give user more convenience in without doing manual shape inference,
some dimensions of the shape can take special values from the set {0, -1, -2, -3, -4}.
@@ -3709,6 +3709,8 @@ The significance of each is explained below:</p>
</pre></div>
</div>
</div></blockquote>
+<p>Note: If the parameter allowzero is manually set to true, it specifies a
+special case where 0 actually means a true empty tensor.</p>
<p><code class="docutils literal notranslate"><span class="pre">-1</span></code> infers the dimension of the output shape by using the remainder of
the input dimensions keeping the size of the new array same as that of the input array.
At most one dimension of shape can be -1.</p>
@@ -3750,6 +3752,7 @@ to -4 in shape (can contain -1).</p>
<dd class="field-odd"><ul class="simple">
<li><p><strong>data</strong> (<em>relay.Expr</em>) – The input data to the operator.</p></li>
<li><p><strong>newshape</strong> (<em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>, </em><em>Tuple</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>]</em><em>, </em><em>List</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" t [...]
+<li><p><strong>allowzero</strong> (<em>Bool</em><em>, </em><em>optional</em>) – If true, then treat zero as true empty tensor rather than a copy instruction.</p></li>
</ul>
</dd>
<dt class="field-even">Returns</dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index f3b4de952..ee86856ea 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/552f06ed4/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 fecab58c6..a7d790e58 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/552f06ed4/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 44af014f9..c017b6f8a 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/552f06ed4/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 a2dcf6f2e..6f902daab 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/552f06ed4/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 ab10aaff7..01fbc5eca 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/552f06ed4/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 32cd40519..61dd7efda 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/552f06ed4/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 5ec512507..2444edef5 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/552f06ed4/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 c651e5b8b..591a74471 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/552f06ed4/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 4c1d41edc..343d1575a 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/552f06ed4/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 c856d756b..6e4b3fbd3 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/552f06ed4/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 ddb68178a..cf0eddf9c 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/552f06ed4/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 f56123c96..38f3717e4 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/552f06ed4/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 df3de8f8b..c557588f0 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/552f06ed4/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 aa6021c17..a7b923683 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/552f06ed4/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 8b4700a7a..e29faf95f 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/552f06ed4/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 a04d453e7..4fe9da088 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/552f06ed4/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 dcdfd6332..b4a2717aa 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/552f06ed4/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 13a34b0c0..66b372dd9 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/552f06ed4/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 531e64587..2e590b3d6 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/552f06ed4/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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 4cd3dab3e..657db5a46 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/552f06ed4/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/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/552f06ed4/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/17b687e40/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
... 1178 lines suppressed ...