You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/05/06 21:18:04 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@98aa41e329c20a5b8b34a34387fcc9067db5f22a)
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 73e274524 deploying docs (apache/tvm@98aa41e329c20a5b8b34a34387fcc9067db5f22a)
73e274524 is described below
commit 73e27452425196914ca6fd2049203bd207a83622
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri May 6 21:17:59 2022 +0000
deploying docs (apache/tvm@98aa41e329c20a5b8b34a34387fcc9067db5f22a)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 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 | 974 +++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 226 +----
.../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 | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 67 +-
.../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 | 44 +-
docs/commit_hash | 2 +-
docs/genindex.html | 2 +
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 95 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 67 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../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 | 974 +++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 226 +----
.../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 | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/objects.inv | Bin 22186 -> 22214 bytes
docs/reference/api/python/auto_scheduler.html | 10 +-
docs/reference/api/python/autotvm.html | 16 +-
docs/reference/api/python/relay/transform.html | 60 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_relay_x86.html | 168 ++--
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 | 44 +-
119 files changed, 2556 insertions(+), 1537 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 21c2e1781..cf8628af4 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.zip16a551bd-dfd6-4755-89de-01f306aa40c5 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7b2c8157-3e66-49a7-8ef6-d3d761608d4d 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 ad9d0fe0d..bf14bb163 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<10:27, 69.3kB/s]
0%| | 48.0k/41.5M [00:00<06:10, 117kB/s]
0%| | 96.0k/41.5M [00:00<04:11, 172kB/s]
0%| | 160k/41.5M [00:01<06:00, 120kB/s]
1%| | 272k/41.5M [00:01<03:17, 219kB/s]
1%|1 | 488k/41.5M [00:01<01:42, 418kB/s]
2%|1 | 768k/41.5M [00:02<01:06, 641kB/s]
3%|2 | 1.05M/41.5M [00:02<00:48, 869kB/s]
3%|3 | 1.34M/41.5M [00:02<00:40, 1.04MB/s]
4%|4 | 1.66M/41.5M [00:02<00:35, 1.18MB/s]
5%|4 | 1.99M/41.5M [00:02<00:32, 1.26MB/s]
6%|5 | 2.34M/41.5M [00:03<00:29, 1.41MB/s]
7%|6 | 2.71M/41.5M [00:03<00:26, 1.55MB/s]
7%|7 | 3.10M/41.5M [00:03<00:24, 1.63MB/s]
8%|8 | 3.51M/41.5M [00:03<00:23, 1.68MB/s]
9%|9 | 3.93M/41.5M [00:03<00:21, 1.80MB/s]
11%|# | 4.38M/41.5M [00:04<00:19
, 1.95MB/s]
12%|#1 | 4.85M/41.5M [00:04<00:18, 2.03MB/s]
13%|#2 | 5.34M/41.5M [00:04<00:18, 2.08MB/s]
14%|#4 | 5.86M/41.5M [00:04<00:16, 2.22MB/s]
15%|#5 | 6.40M/41.5M [00:05<00:15, 2.38MB/s]
17%|#6 | 6.97M/41.5M [00:05<00:14, 2.46MB/s]
18%|#8 | 7.56M/41.5M [00:05<00:14, 2.52MB/s]
20%|#9 | 8.19M/41.5M [00:05<00:12, 2.71MB/s]
21%|##1 | 8.84M/41.5M [00:05<00:11, 2.88MB/s]
23%|##2 | 9.52M/41.5M [00:06<00:11, 2.98MB/s]
25%|##4 | 10.2M/41.5M [00:06<00:10, 3.05MB/s]
27%|##6 | 11.0M/41.5M [00:06<00:09, 3.29MB/s]
28%|##8 | 11.8M/41.5M [00:06<00:09, 3.46MB/s]
30%|### | 12.6M/41.5M [00:07<00:08, 3.53MB/s]
32%|###2 | 13.4M/41.5M [00:07<00:08, 3.57MB/s]
34%|###4 | 14.2M/41.5M [00:07<00:07, 3.81MB/s]
37%|###6 | 15.2M/41.5M [00:07<00:06, 4.04MB/s]
39%|###8 | 16.1M/41.5M [00:07<00:06, 4.16MB/s]
41%|####1
| 17.1M/41.5M [00:08<00:05, 4.26MB/s]
44%|####3 | 18.2M/41.5M [00:08<00:05, 4.61MB/s]
47%|####6 | 19.3M/41.5M [00:08<00:04, 4.89MB/s]
49%|####9 | 20.5M/41.5M [00:08<00:04, 5.03MB/s]
52%|#####2 | 21.7M/41.5M [00:08<00:04, 5.15MB/s]
55%|#####5 | 23.0M/41.5M [00:09<00:03, 5.57MB/s]
59%|#####8 | 24.3M/41.5M [00:09<00:03, 5.93MB/s]
62%|######1 | 25.7M/41.5M [00:09<00:02, 6.10MB/s]
66%|######5 | 27.2M/41.5M [00:09<00:02, 6.23MB/s]
69%|######9 | 28.7M/41.5M [00:10<00:02, 6.62MB/s]
73%|#######2 | 30.2M/41.5M [00:10<00:01, 6.90MB/s]
76%|#######6 | 31.6M/41.5M [00:10<00:01, 8.25MB/s]
78%|#######8 | 32.5M/41.5M [00:10<00:01, 7.97MB/s]
80%|######## | 33.3M/41.5M [00:10<00:01, 6.37MB/s]
83%|########3 | 34.6M/41.5M [00:10<00:01, 6.45MB/s]
87%|########6 | 36.1M/41.5M [00:11<00:00, 6.83MB/s]
91%|######### | 37.6M/41.5M [00:11<00:00, 6.83MB/s]
94%|#########4| 39.0M/41.5M [00:11<00:0
0, 6.73MB/s]
98%|#########7| 40.5M/41.5M [00:11<00:00, 7.00MB/s]
100%|##########| 41.5M/41.5M [00:11<00:00, 3.68MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:50, 92.4kB/s]
0%| | 48.0k/41.5M [00:00<04:57, 146kB/s]
0%| | 96.0k/41.5M [00:00<03:31, 205kB/s]
0%| | 168k/41.5M [00:00<02:30, 288kB/s]
1%| | 344k/41.5M [00:00<01:18, 548kB/s]
1%|1 | 536k/41.5M [00:01<00:58, 737kB/s]
3%|2 | 1.06M/41.5M [00:01<00:27, 1.53MB/s]
5%|5 | 2.09M/41.5M [00:01<00:13, 2.96MB/s]
9%|8 | 3.57M/41.5M [00:01<00:08, 4.76MB/s]
12%|#2 | 5.05M/41.5M [00:01<00:06, 5.97MB/s]
16%|#5 | 6.53M/41.5M [00:01<00:05, 6.81MB/s]
19%|#9 | 8.02M/41.5M [00:02<00:04, 7.40MB/s]
23%|##2 | 9.48M/41.5M [00:02<00:04, 7.77MB/s]
26%|##6 | 11.0M/41.5M [00:02<00:03, 8.05MB/s]
30%|##9 | 12.4M/41.5M [00:02<00:03, 8.25MB/s]
34%|###3 | 13.9M/41.5M [00:02<00:03, 8.39MB/s]
37%|###7 | 15.4M/41.5M [00:03<00
:03, 8.49MB/s]
41%|#### | 16.9M/41.5M [00:03<00:03, 8.55MB/s]
44%|####4 | 18.4M/41.5M [00:03<00:02, 8.60MB/s]
48%|####7 | 19.9M/41.5M [00:03<00:02, 9.74MB/s]
51%|##### | 21.0M/41.5M [00:03<00:02, 10.2MB/s]
53%|#####3 | 22.0M/41.5M [00:03<00:02, 9.21MB/s]
55%|#####5 | 22.9M/41.5M [00:03<00:02, 7.98MB/s]
59%|#####8 | 24.3M/41.5M [00:04<00:01, 9.26MB/s]
61%|###### | 25.2M/41.5M [00:04<00:01, 9.39MB/s]
63%|######3 | 26.2M/41.5M [00:04<00:01, 8.38MB/s]
66%|######5 | 27.3M/41.5M [00:04<00:01, 8.90MB/s]
69%|######8 | 28.5M/41.5M [00:04<00:01, 9.88MB/s]
71%|#######1 | 29.5M/41.5M [00:04<00:01, 8.79MB/s]
73%|#######3 | 30.4M/41.5M [00:04<00:01, 7.55MB/s]
76%|#######6 | 31.7M/41.5M [00:04<00:01, 8.95MB/s]
79%|#######8 | 32.6M/41.5M [00:05<00:01, 9.12MB/s]
81%|######## | 33.5M/41.5M [00:05<00:01, 8.12MB/s]
83%|########3 | 34.6M/41.5M [00:05<00:00, 8.82MB/s]
86%|####
####6 | 35.8M/41.5M [00:05<00:00, 9.73MB/s]
89%|########8 | 36.8M/41.5M [00:05<00:00, 8.66MB/s]
91%|######### | 37.7M/41.5M [00:05<00:00, 7.45MB/s]
94%|#########4| 39.0M/41.5M [00:05<00:00, 8.99MB/s]
96%|#########6| 40.0M/41.5M [00:05<00:00, 9.13MB/s]
99%|#########8| 40.9M/41.5M [00:06<00:00, 8.12MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 7.14MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 276a62016..80b2a00fb 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 12.515 seconds)
+ **Total running time of the script:** ( 1 minutes 6.899 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 6883934e0..d27d00a48 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]
31%|### | 13.7M/44.7M [00:00<00:00, 142MB/s]
61%|######1 | 27.3M/44.7M [00:00<00:00, 107MB/s]
89%|########9 | 39.8M/44.7M [00:00<00:00, 115MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 122MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
39%|###8 | 17.2M/44.7M [00:00<00:00, 180MB/s]
77%|#######6 | 34.4M/44.7M [00:00<00:00, 149MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 157MB/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 2672f456f..6d56d1d35 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.805 seconds)
+ **Total running time of the script:** ( 1 minutes 4.401 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 e040354a5..491b2bd62 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,15 +5,15 @@
Computation times
=================
-**05:30.804** total execution time for **how_to_compile_models** files:
+**05:22.520** total execution time for **how_to_compile_models** files:
-- **01:12.515**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:00.805**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:57.171**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:36.437**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:26.046**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.613**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.357**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.680**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:12.515**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.665**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:06.899**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:04.401**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:57.651**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:30.145**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.110**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.744**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:21.411**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:18.941**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.701**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.516**: :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 cd428968f..01decf9e2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1265 16.0957 16.4350 16.0224 0.1131
+ 16.2510 15.8680 17.0769 15.7228 0.5397
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 d952699f9..74f4ac6e2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.31M/170M [00:00<00:03, 55.5MB/s]
6%|6 | 10.6M/170M [00:00<00:03, 43.3MB/s]
9%|8 | 15.1M/170M [00:00<00:03, 44.3MB/s]
11%|#1 | 19.4M/170M [00:00<00:04, 39.0MB/s]
14%|#3 | 23.3M/170M [00:00<00:04, 34.6MB/s]
16%|#5 | 26.7M/170M [00:00<00:05, 28.3MB/s]
17%|#7 | 29.5M/170M [00:00<00:05, 25.8MB/s]
19%|#8 | 32.1M/170M [00:01<00:05, 25.9MB/s]
20%|## | 34.7M/170M [00:01<00:05, 24.5MB/s]
22%|##2 | 37.5M/170M [00:01<00:05, 25.6MB/s]
25%|##4 | 42.0M/170M [00:01<00:04, 31.2MB/s]
27%|##6 | 45.0M/170M [00:01<00:04, 31.0MB/s]
28%|##8 | 48.1M/170M [00:01<00:04, 29.4MB/s]
30%|### | 51.1M/170M [00:01<00:04, 30.0MB/s]
33%|###3 | 56.2M/170M [00:01<00:03, 34.5MB/s]
36%|###6 | 61.4M/170M [00:01<00:02, 39.9MB/s]
39%|###8 | 65.9M/170M [00:02<00:02, 41.9MB/
s]
41%|####1 | 70.3M/170M [00:02<00:02, 43.0MB/s]
44%|####3 | 74.4M/170M [00:02<00:02, 37.4MB/s]
46%|####6 | 78.3M/170M [00:02<00:02, 38.3MB/s]
48%|####8 | 82.1M/170M [00:02<00:02, 31.5MB/s]
50%|##### | 85.4M/170M [00:02<00:02, 30.8MB/s]
52%|#####2 | 88.5M/170M [00:02<00:03, 26.8MB/s]
54%|#####3 | 91.2M/170M [00:02<00:03, 27.1MB/s]
56%|#####5 | 94.4M/170M [00:03<00:02, 28.5MB/s]
58%|#####7 | 97.7M/170M [00:03<00:02, 30.1MB/s]
59%|#####9 | 101M/170M [00:03<00:02, 26.9MB/s]
61%|###### | 103M/170M [00:03<00:02, 23.4MB/s]
62%|######2 | 106M/170M [00:03<00:02, 23.3MB/s]
64%|######3 | 108M/170M [00:03<00:02, 23.8MB/s]
65%|######5 | 110M/170M [00:03<00:02, 22.6MB/s]
66%|######6 | 113M/170M [00:03<00:02, 20.4MB/s]
68%|######7 | 115M/170M [00:04<00:02, 21.5MB/s]
69%|######9 | 118M/170M [00:04<00:02, 22.5MB/s]
71%|####### | 120M/170M [00:04<00:02, 23.6
MB/s]
73%|#######2 | 124M/170M [00:04<00:01, 27.3MB/s]
75%|#######4 | 127M/170M [00:04<00:01, 25.8MB/s]
76%|#######5 | 129M/170M [00:04<00:01, 24.8MB/s]
79%|#######8 | 134M/170M [00:04<00:01, 31.8MB/s]
81%|######## | 137M/170M [00:04<00:01, 32.6MB/s]
83%|########2 | 140M/170M [00:04<00:01, 30.8MB/s]
84%|########4 | 143M/170M [00:05<00:00, 29.3MB/s]
86%|########6 | 146M/170M [00:05<00:00, 29.3MB/s]
89%|########9 | 151M/170M [00:05<00:00, 35.8MB/s]
92%|#########2| 156M/170M [00:05<00:00, 40.2MB/s]
94%|#########4| 160M/170M [00:05<00:00, 40.4MB/s]
97%|#########6| 164M/170M [00:05<00:00, 30.3MB/s]
99%|#########9| 168M/170M [00:05<00:00, 33.2MB/s]
100%|##########| 170M/170M [00:05<00:00, 30.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.16M/170M [00:00<00:03, 54.0MB/s]
9%|9 | 15.7M/170M [00:00<00:01, 84.9MB/s]
14%|#3 | 23.8M/170M [00:00<00:02, 67.0MB/s]
20%|#9 | 33.5M/170M [00:00<00:01, 78.9MB/s]
27%|##6 | 45.2M/170M [00:00<00:01, 92.8MB/s]
33%|###3 | 56.8M/170M [00:00<00:01, 102MB/s]
40%|#### | 68.5M/170M [00:00<00:00, 108MB/s]
47%|####6 | 79.1M/170M [00:00<00:01, 92.6MB/s]
54%|#####4 | 91.9M/170M [00:01<00:00, 104MB/s]
61%|######1 | 104M/170M [00:01<00:00, 110MB/s]
69%|######8 | 116M/170M [00:01<00:00, 116MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 95.9MB/s]
82%|########1 | 139M/170M [00:01<00:00, 101MB/s]
88%|########7 | 149M/170M [00:01<00:00, 95.5MB/s]
95%|#########4| 161M/170M [00:01<00:00, 102MB/s]
100%|##########| 170M/170M [00:01<00:00, 94.4MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -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 14.754 seconds)
+ **Total running time of the script:** ( 3 minutes 11.218 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 8d51f2e4d..27f299ce6 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]
35%|###4 | 4.70M/13.6M [00:00<00:00, 49.2MB/s]
74%|#######3 | 10.0M/13.6M [00:00<00:00, 52.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 53.8MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
32%|###1 | 4.30M/13.6M [00:00<00:00, 45.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 78.3MB/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)
- 90.4861 90.3578 95.5018 90.1938 0.5526
+ 90.6081 90.4701 93.1976 90.2701 0.3699
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.712 seconds)
+ **Total running time of the script:** ( 1 minutes 7.115 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 b83a8e864..8ab3c8b19 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)
- 120.3253 120.2978 124.9795 119.7389 0.5480
+ 120.2118 120.1631 123.9041 119.4701 0.5162
@@ -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 58.020 seconds)
+ **Total running time of the script:** ( 1 minutes 53.331 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 a27bff677..04cb2294e 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 11.942 seconds)
+ **Total running time of the script:** ( 1 minutes 57.106 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 822cb3cfa..0f55fedaa 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]
2%|2 | 3174/132723 [00:00<00:04, 31735.26KB/s]
7%|7 | 9932/132723 [00:00<00:02, 52815.43KB/s]
13%|#3 | 17892/132723 [00:00<00:01, 65042.08KB/s]
20%|#9 | 26053/132723 [00:00<00:01, 71578.44KB/s]
26%|##5 | 34267/132723 [00:00<00:01, 75384.53KB/s]
32%|###1 | 42422/132723 [00:00<00:01, 77478.41KB/s]
38%|###8 | 50566/132723 [00:00<00:01, 78772.32KB/s]
44%|####4 | 58737/132723 [00:00<00:00, 79702.00KB/s]
50%|##### | 66886/132723 [00:00<00:00, 80258.54KB/s]
57%|#####6 | 75034/132723 [00:01<00:00, 80630.94KB/s]
63%|######2 | 83173/132723 [00:01<00:00, 80860.00KB/s]
69%|######8 | 91329/132723 [00:01<00:00, 81069.31KB/s]
75%|#######4 | 99436/132723 [00:01<00:00, 81031.62KB/s]
81%|########1 | 107587/132723 [00:01<00:00, 81174.91KB/s]
87%|########7 | 115725/132723 [00:01<00:00, 81232.71KB/s]
93%|#########3
| 123892/132723 [00:01<00:00, 81363.16KB/s]
100%|#########9| 132131/132723 [00:01<00:00, 81666.28KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77652.34KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
2%|2 | 2679/132723 [00:00<00:04, 26786.64KB/s]
6%|6 | 8269/132723 [00:00<00:02, 43907.22KB/s]
12%|#2 | 16374/132723 [00:00<00:01, 60123.44KB/s]
17%|#6 | 22546/132723 [00:00<00:01, 60746.74KB/s]
23%|##3 | 31054/132723 [00:00<00:01, 69477.15KB/s]
30%|##9 | 39323/132723 [00:00<00:01, 73952.96KB/s]
36%|###6 | 47803/132723 [00:00<00:01, 77489.43KB/s]
42%|####2 | 56396/132723 [00:00<00:00, 80169.15KB/s]
49%|####8 | 64959/132723 [00:00<00:00, 81872.80KB/s]
55%|#####5 | 73625/132723 [00:01<00:00, 83346.13KB/s]
62%|######1 | 82285/132723 [00:01<00:00, 84338.82KB/s]
68%|######8 | 90890/132723 [00:01<00:00, 84857.90KB/s]
75%|#######4 | 99376/132723 [00:01<00:00, 82695.87KB/s]
81%|########1 | 108022/132723 [00:01<00:00, 83810.75KB/s]
88%|########7 | 116414/132723 [00:01<00:00, 66191.21KB/s]
93%|#########3
| 123611/132723 [00:01<00:00, 63721.97KB/s]
99%|#########8| 131062/132723 [00:01<00:00, 66446.63KB/s]
100%|##########| 132723/132723 [00:01<00:00, 71864.16KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 26.356 seconds)
+ **Total running time of the script:** ( 2 minutes 26.685 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 241c3e737..e0d2071bb 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
=================
-**10:48.435** total execution time for **how_to_deploy_models** files:
+**11:26.792** total execution time for **how_to_deploy_models** files:
-- **03:14.754**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:26.356**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:58.020**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:11.942**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:06.712**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.678**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.764**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **03:11.218**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:26.685**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:57.106**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:53.331**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:07.115**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.368**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.760**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
- **00:00.209**: :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 17bcd3afd..eedc38fc4 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.zip463a2a1d-3b7b-4837-a02d-b86d5f887657 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb6163e60-6cc7-441f-8e4f-531b7765a8e9 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 9c86c1f55..4bb7efaf8 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.160** total execution time for **how_to_extend_tvm** files:
+**00:38.790** total execution time for **how_to_extend_tvm** files:
-- **00:34.696**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.214**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.039**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.211**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:35.215**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.273**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.092**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.210**: :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 b0f57d2d2..82514fe5a 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: 5877us [5877us] (44.50%; 44.50%)
- FoldScaleAxis: 7331us [2us] (55.50%; 55.50%)
- FoldConstant: 7329us [1552us] (55.49%; 99.97%)
- InferType: 5777us [5777us] (43.74%; 78.83%)
+ InferType: 6149us [6149us] (45.45%; 45.45%)
+ FoldScaleAxis: 7381us [2us] (54.55%; 54.55%)
+ FoldConstant: 7379us [1525us] (54.54%; 99.97%)
+ InferType: 5854us [5854us] (43.26%; 79.33%)
@@ -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: 5707us [5707us] (44.76%; 44.76%)
- FoldScaleAxis: 7044us [2us] (55.24%; 55.24%)
- FoldConstant: 7042us [1495us] (55.23%; 99.97%)
- InferType: 5548us [5548us] (43.51%; 78.78%)
+ InferType: 5905us [5905us] (44.61%; 44.61%)
+ FoldScaleAxis: 7333us [2us] (55.39%; 55.39%)
+ FoldConstant: 7331us [1526us] (55.38%; 99.97%)
+ InferType: 5805us [5805us] (43.85%; 79.19%)
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 7ade96959..94c106105 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: 54.116121 ms
+ Convolution: 37.021404 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 b682584dc..90b547e6d 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: 6.246579 ms
+ conv2d with tensor core: 7.449030 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 8509882e4..cdb5d5d16 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: 0.019112
- Baseline: 3.265317
+ Numpy running time: 0.019271
+ Baseline: 3.169802
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.315681
+ Opt1: 0.309262
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.349897
+ Opt2: 0.343368
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116375
+ Opt3: 0.122711
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111497
+ Opt4: 0.111697
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111295
+ Opt5: 0.112147
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145145
+ Opt6: 0.144950
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 b9a8c90b0..bd9b6bc31 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.069** total execution time for **how_to_optimize_operators** files:
+**00:34.851** total execution time for **how_to_optimize_operators** files:
-- **00:32.366**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.434**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.269**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.161**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.439**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.250**: :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 40b3c5557..91409c06a 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
=================
-**04:57.938** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:23.093**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.069**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.024**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:16.261**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.868**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.623**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:56.803** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:21.494**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:20.656**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.438**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.546**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.065**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.605**: :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 db0d3d2b6..619562915 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
@@ -222,12 +222,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=64)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -241,76 +241,501 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 3))), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 3) < 2)), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 70), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*3) + 294)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 295)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 296)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 49), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 98), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 98), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 196), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 147), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 196), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 392), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 245), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 490), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 294), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 82), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 343), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 686), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_6: int32 = (ff.outer.inner*4)
- let cse_var_5: int32 = (cse_var_6 + 3)
- let cse_var_4: int32 = (cse_var_6 + 2)
- let cse_var_3: int32 = (cse_var_6 + 1)
- {
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 75)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 78)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 81)]))
- }
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 10), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 80), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 128), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 144)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 9), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 144), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 3), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 160), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 160), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 176)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 176), 27)) && (floormod((threadIdx.x_1 + 14), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 176), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 176), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 208)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 19), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 208), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 208), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 16))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 32))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 48))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 10), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 22), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 26), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 30), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 34), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 38), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 46), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 50), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 58), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 62), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 66), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 74), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 78), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 82), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 86), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 94), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 102), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 106), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 110), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 114), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 118), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 122), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 130), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 134), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 138), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 142), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1168)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 146), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1200)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 150), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1264)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 158), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1296)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1328)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 166), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1360)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 170), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1392)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 174), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1424)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 178), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1488)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 186), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1520)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 190), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1552)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 194), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1584)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1616)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 202), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1648)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 206), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 210), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1712)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 214), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1744)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 218), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1776)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 222), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1808)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 226), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1840)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 230), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1872)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 238), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1936)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 242), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1968)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 246), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2000)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 250), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2032)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 254), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2064)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 258), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2096)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 262), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 266), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 274), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 278), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 282), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 286), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_29: int32 = (rc.outer.inner*27)
+ let cse_var_28: int32 = (cse_var_29 + 1)
+ let cse_var_27: int32 = (cse_var_29 + 10)
+ let cse_var_26: int32 = (cse_var_29 + 11)
+ let cse_var_25: int32 = (cse_var_29 + 12)
+ let cse_var_24: int32 = (cse_var_29 + 13)
+ let cse_var_23: int32 = (cse_var_29 + 15)
+ let cse_var_22: int32 = (cse_var_29 + 16)
+ let cse_var_21: int32 = (cse_var_29 + 17)
+ let cse_var_20: int32 = (cse_var_29 + 18)
+ let cse_var_19: int32 = (cse_var_29 + 19)
+ let cse_var_18: int32 = (cse_var_29 + 2)
+ let cse_var_17: int32 = (cse_var_29 + 20)
+ let cse_var_16: int32 = (cse_var_29 + 21)
+ let cse_var_15: int32 = (cse_var_29 + 9)
+ let cse_var_14: int32 = (cse_var_29 + 8)
+ let cse_var_13: int32 = (cse_var_29 + 7)
+ let cse_var_12: int32 = (cse_var_29 + 6)
+ let cse_var_11: int32 = (cse_var_29 + 14)
+ let cse_var_10: int32 = (cse_var_29 + 5)
+ let cse_var_9: int32 = (cse_var_29 + 4)
+ let cse_var_8: int32 = (cse_var_29 + 3)
+ let cse_var_7: int32 = (cse_var_29 + 26)
+ let cse_var_6: int32 = (cse_var_29 + 25)
+ let cse_var_5: int32 = (cse_var_29 + 24)
+ let cse_var_4: int32 = (cse_var_29 + 23)
+ let cse_var_3: int32 = (cse_var_29 + 22)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
}
}
}
}
- for (i1.inner: int32, 0, 16) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*784)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*16)) + i1.inner)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 784)] = max((conv2d_nchw_1[7] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 791)] = max((conv2d_nchw_1[8] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 798)] = max((conv2d_nchw_1[9] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 805)] = max((conv2d_nchw_1[10] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 812)] = max((conv2d_nchw_1[11] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 819)] = max((conv2d_nchw_1[12] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 826)] = max((conv2d_nchw_1[13] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
}
}
@@ -362,7 +787,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.367 ms
+ Execution time of this operator: 0.303 ms
@@ -406,36 +831,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_ff_o_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=16)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_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=16)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_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=16)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -455,14 +880,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+ 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=98)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -480,10 +905,10 @@ 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__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[768];
+ extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -498,57 +923,312 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 3) + 294)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 295)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 296)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 2) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 294) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 490) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 10) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- if (((int)threadIdx.x) < 82) {
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 686) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 14) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 24)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 48)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 72)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 27)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 51)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 75)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 30)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 54)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 78)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 33)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 57)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 81)]));
- }
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 27) * 49)) + ((((((int)threadIdx.x) + 4) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 144)] = ((((((int)threadIdx.x) < 15) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 144) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 176)] = (((((3 <= ((((int)threadIdx.x) + 14) % 27)) && (((((int)threadIdx.x) + 14) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 176) / 27) * 49)) + ((((((int)threadIdx.x) + 14) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 1) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 8) {
+ pad_temp_shared[(((int)threadIdx.x) + 208)] = ((((((int)threadIdx.x) < 5) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 208) / 27) * 49)) + ((((((int)threadIdx.x) + 19) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 16)];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32)];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1168) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1200)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1264)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1264) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1296)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1328)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1360)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1392)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1424)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1488)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1520)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1520) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1552)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1552) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1584)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1616)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1648)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1712)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1744) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1776)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1808)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1808) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1840)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1840) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1872)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1936)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1968)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2000)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2032) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2064)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2096)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2096) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 2160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 2224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 27)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
}
}
- for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 784)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 16)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 784)] = max((conv2d_nchw[7] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 791)] = max((conv2d_nchw[8] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 798)] = max((conv2d_nchw[9] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 805)] = max((conv2d_nchw[10] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 812)] = max((conv2d_nchw[11] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 819)] = max((conv2d_nchw[12] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 826)] = max((conv2d_nchw[13] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
}
@@ -606,7 +1286,7 @@ 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 23.093 seconds)
+ **Total running time of the script:** ( 2 minutes 21.494 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 e874103a7..35b291095 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)
- 9.7522 9.7732 9.7778 9.7055 0.0331
+ 9.8366 9.8759 9.8844 9.7495 0.0617
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 9d5d68ec7..555aa671d 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)
- 757.3604 758.7667 759.3807 753.9339 2.4359
+ 758.4326 760.0705 760.1377 755.0895 2.3641
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.069 seconds)
+ **Total running time of the script:** ( 1 minutes 20.656 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 f60302589..41a7a6b3a 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
@@ -362,215 +362,29 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_1: int32 = (i.outer.inner*64)
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 16)] = 0f32
- compute_5[(cse_var_1 + 17)] = 0f32
- compute_5[(cse_var_1 + 18)] = 0f32
- compute_5[(cse_var_1 + 19)] = 0f32
- compute_5[(cse_var_1 + 20)] = 0f32
- compute_5[(cse_var_1 + 21)] = 0f32
- compute_5[(cse_var_1 + 22)] = 0f32
- compute_5[(cse_var_1 + 23)] = 0f32
- compute_5[(cse_var_1 + 24)] = 0f32
- compute_5[(cse_var_1 + 25)] = 0f32
- compute_5[(cse_var_1 + 26)] = 0f32
- compute_5[(cse_var_1 + 27)] = 0f32
- compute_5[(cse_var_1 + 28)] = 0f32
- compute_5[(cse_var_1 + 29)] = 0f32
- compute_5[(cse_var_1 + 30)] = 0f32
- compute_5[(cse_var_1 + 31)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 48)] = 0f32
- compute_5[(cse_var_1 + 49)] = 0f32
- compute_5[(cse_var_1 + 50)] = 0f32
- compute_5[(cse_var_1 + 51)] = 0f32
- compute_5[(cse_var_1 + 52)] = 0f32
- compute_5[(cse_var_1 + 53)] = 0f32
- compute_5[(cse_var_1 + 54)] = 0f32
- compute_5[(cse_var_1 + 55)] = 0f32
- compute_5[(cse_var_1 + 56)] = 0f32
- compute_5[(cse_var_1 + 57)] = 0f32
- compute_5[(cse_var_1 + 58)] = 0f32
- compute_5[(cse_var_1 + 59)] = 0f32
- compute_5[(cse_var_1 + 60)] = 0f32
- compute_5[(cse_var_1 + 61)] = 0f32
- compute_5[(cse_var_1 + 62)] = 0f32
- compute_5[(cse_var_1 + 63)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (cse_var_1 + 37)
- let cse_var_66: int32 = (cse_var_1 + 36)
- let cse_var_65: int32 = (cse_var_1 + 35)
- let cse_var_64: int32 = (cse_var_1 + 34)
- let cse_var_63: int32 = (cse_var_1 + 33)
- let cse_var_62: int32 = (cse_var_1 + 32)
- let cse_var_61: int32 = (cse_var_1 + 31)
- let cse_var_60: int32 = (cse_var_1 + 30)
- let cse_var_59: int32 = (cse_var_1 + 3)
- let cse_var_58: int32 = (cse_var_1 + 29)
- let cse_var_57: int32 = (cse_var_1 + 28)
- let cse_var_56: int32 = (cse_var_1 + 27)
- let cse_var_55: int32 = (cse_var_1 + 26)
- let cse_var_54: int32 = (cse_var_1 + 25)
- let cse_var_53: int32 = (cse_var_1 + 24)
- let cse_var_52: int32 = (cse_var_1 + 39)
- let cse_var_51: int32 = (cse_var_1 + 22)
- let cse_var_50: int32 = (cse_var_1 + 21)
- let cse_var_49: int32 = (cse_var_1 + 20)
- let cse_var_48: int32 = (cse_var_1 + 2)
- let cse_var_47: int32 = (cse_var_1 + 19)
- let cse_var_46: int32 = (cse_var_1 + 18)
- let cse_var_45: int32 = (cse_var_1 + 17)
- let cse_var_44: int32 = (cse_var_1 + 16)
- let cse_var_43: int32 = (cse_var_1 + 15)
- let cse_var_42: int32 = (cse_var_1 + 14)
- let cse_var_41: int32 = (cse_var_1 + 13)
- let cse_var_40: int32 = (cse_var_1 + 12)
- let cse_var_39: int32 = (cse_var_1 + 11)
- let cse_var_38: int32 = (cse_var_1 + 10)
- let cse_var_37: int32 = (cse_var_1 + 1)
- let cse_var_36: int32 = (cse_var_1 + 23)
- let cse_var_35: int32 = (elem_idx*16)
- let cse_var_34: int32 = (cse_var_1 + 9)
- let cse_var_33: int32 = (cse_var_1 + 8)
- let cse_var_32: int32 = (cse_var_1 + 7)
- let cse_var_31: int32 = (cse_var_1 + 63)
- let cse_var_30: int32 = (cse_var_1 + 62)
- let cse_var_29: int32 = (cse_var_1 + 61)
- let cse_var_28: int32 = (cse_var_1 + 60)
- let cse_var_27: int32 = (cse_var_1 + 6)
- let cse_var_26: int32 = (cse_var_1 + 59)
- let cse_var_25: int32 = (cse_var_1 + 58)
- let cse_var_24: int32 = (cse_var_1 + 57)
- let cse_var_23: int32 = (cse_var_1 + 56)
- let cse_var_22: int32 = (cse_var_1 + 55)
- let cse_var_21: int32 = (cse_var_1 + 54)
- let cse_var_20: int32 = (cse_var_1 + 38)
- let cse_var_19: int32 = (cse_var_1 + 4)
- let cse_var_18: int32 = (cse_var_1 + 40)
- let cse_var_17: int32 = (cse_var_1 + 41)
- let cse_var_16: int32 = (cse_var_1 + 42)
- let cse_var_15: int32 = (cse_var_1 + 43)
- let cse_var_14: int32 = (cse_var_1 + 44)
- let cse_var_13: int32 = (cse_var_1 + 45)
- let cse_var_12: int32 = (cse_var_1 + 46)
- let cse_var_11: int32 = (cse_var_1 + 47)
- let cse_var_10: int32 = (cse_var_1 + 48)
- let cse_var_9: int32 = (cse_var_1 + 49)
- let cse_var_8: int32 = (cse_var_1 + 5)
- let cse_var_7: int32 = (cse_var_1 + 50)
- let cse_var_6: int32 = (cse_var_1 + 51)
- let cse_var_5: int32 = (cse_var_1 + 53)
- let cse_var_4: int32 = (cse_var_1 + 52)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*1024))
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*512) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_68: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_68, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_68, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 2) {
+ let cse_var_4: int32 = (((i0.outer*1024) + (i0.inner*512)) + (i1.outer*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -624,7 +438,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.040 ms
+ Execution time of this operator: 1.870 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 16bf46883..3eb6cddab 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
=================
-**00:44.426** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.529** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.500**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.243**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.228**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.226**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:43.605**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.246**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.230**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.221**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
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 f581a0ee8..be72e9779 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: 67.42/67.42 result: MeasureResult(costs=(0.0034337007,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.743032693862915, timestamp=1651853234.041699) [('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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 108.25/108.25 result: MeasureResult(costs=(0.002138649875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6317508220672607, timestamp=1651868046.1444492) [('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: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/108.25 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: 0x00007fa069b0afa2
+ 12: 0x00007f45fdf53fa2
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: 145.08/145.08 result: MeasureResult(costs=(0.0015956777,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.425276279449463, timestamp=1651853260.5548215) [('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: 144.36/144.36 result: MeasureResult(costs=(0.00160366258,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.434868574142456, timestamp=1651868072.608344) [('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: 0.001954
+ Time cost of this operator: 0.002050
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 ba5220b82..ae9e78b29 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 313.8 98.75 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.966 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.284 (1, 1, 10, 10, 3) 1 1
- Total_time - 317.771 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.621 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.242 1.021 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.137 0.358 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.579 - - - -
@@ -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 136.8 98.072 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.255 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.939 0.673 (1, 1, 10, 10, 3) 1 1
- Total_time - 139.489 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.6 96.854 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.077 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.069 (1, 1, 10, 10, 3) 1 1
+ Total_time - 84.251 - - - -
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 e0c053adf..972e7f4be 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
=================
-**00:44.391** total execution time for **how_to_work_with_microtvm** files:
+**00:44.528** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.305**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.473**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:40.440**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.463**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.217**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.204**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.202**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 72a32cdfe..80e38f1f0 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
=================
-**00:09.429** total execution time for **how_to_work_with_relay** files:
+**00:09.299** total execution time for **how_to_work_with_relay** files:
-- **00:07.359**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.843**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.227**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.122**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.947**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.230**: :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 dbb6d9048..ecea4ba74 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
=================
-**00:05.821** total execution time for **how_to_work_with_schedules** files:
+**00:05.880** total execution time for **how_to_work_with_schedules** files:
-- **00:02.117**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.176**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:02.138**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.187**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
- **00:00.749**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.731**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.320**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.247**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.230**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:00.737**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.324**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.254**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.252**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.240**: :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 577782287..669d0ad58 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/tmpsszsjdw0/input0.cc'\nsource_filename = \"/tmp/tmpsszsjdw0/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/tmpig9au86g/input0.cc'\nsource_filename = \"/tmp/tmpig9au86g/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 480b8aff6..5bc8003d2 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
=================
-**00:20.731** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.893** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.512**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.219**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.676**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.218**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index ce305fc8d..839a56561 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 21.31s!
+ resnet18_v1 inference graph built in 21.98s!
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 aca52d025..e9316a9c1 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:431: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.15s!
+ yolov3-tiny inference graph built in 15.26s!
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 92be29931..7d3151442 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
=================
-**01:28.675** total execution time for **topic_vta_tutorials_frontend** files:
+**01:30.532** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.298**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.377**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:48.094**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:42.439**: :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 41f136576..1431c011f 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:
+**00:03.535** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.025**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.559**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.972**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.563**: :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 e095cebae..a7f09a8f6 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
=================
-**00:01.007** total execution time for **topic_vta_tutorials** files:
+**00:01.031** total execution time for **topic_vta_tutorials** files:
-- **00:00.511**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.496**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.518**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.513**: :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 ec4a9f767..5f3023af7 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
+ .T*E
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.825 ms
+ Execution time of this operator: 93.620 ms
@@ -415,6 +415,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 24.223 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 7fb942187..ee837fba3 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': 493.9763870700006, 'median': 493.863586949999, 'std': 0.6900472424638796}
+ {'mean': 497.1574179799994, 'median': 496.9821459000002, 'std': 1.1958401633421292}
@@ -482,32 +482,31 @@ 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: 5.90/ 22.79 GFLOPS | Progress: (4/10) | 7.50 s
[Task 1/25] Current/Best: 12.19/ 22.79 GFLOPS | Progress: (8/10) | 9.91 s
[Task 1/25] Current/Best: 17.96/ 22.79 GFLOPS | Progress: (10/10) | 10.75 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 21.07/ 21.07 GFLOPS | Progress: (4/10) | 2.56 s
[Task 2/25] Current/Best: 14.43/ 21.07 GFLOPS | Progress: (8/10) | 4.20 s
[Task 2/25] Current/Best: 12.91/ 21.07 GFLOPS | Progress: (10/10) | 5.00 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 17.16/ 17.16 GFLOPS | Progress: (4/10) | 2.91 s
[Task 3/25] Current/Best: 15.28/ 17.16 GFLOPS | Progress: (8/10) | 4.75 s
[Task 3/25] Current/Best: 1.61/ 17.59 GFLOPS | Progress: (10/10) | 6.93 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 12.29/ 16.00 GFLOPS | Progress: (4/10) | 3.57 s
[Task 4/25] Current/Best: 12.27/ 16.67 GFLOPS | Progress: (8/10) | 10.05 s
[Task 4/25] Current/Best: 8.78/ 21.85 GFLOPS | Progress: (10/10) | 10.72 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 6.33/ 18.31 GFLOPS | Progress: (4/10) | 2.45 s
[Task 5/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (8/10) | 4.74 s
[Task 5/25] Current/Best: 13.29/ 20.48 GFLOPS | Progress: (10/10) | 5.67 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 1.69/ 17.58 GFLOPS | Progress: (4/10) | 3.79 s
[Task 6/25] Current/Best: 20.96/ 20.96 GFLOPS | Progress: (8/10) | 7.10 s
[Task 6/25] Current/Best: 3.40/ 20.96 GFLOPS | Progress: (10/10) | 8.67 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 16.10/ 17.49 GFLOPS | Progress: (4/10) | 2.65 s
[Task 7/25] Current/Best: 3.12/ 17.49 GFLOPS | Progress: (8/10) | 5.49 s
[Task 7/25] Current/Best: 21.99/ 21.99 GFLOPS | Progress: (10/10) | 6.51 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 16.93/ 16.93 GFLOPS | Progress: (4/10) | 4.78 s
[Task 8/25] Current/Best: 7.34/ 16.93 GFLOPS | Progress: (8/10) | 7.26 s
[Task 8/25] Current/Best: 4.05/ 16.93 GFLOPS | Progress: (10/10) | 13.96 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 12.11/ 18.84 GFLOPS | Progress: (4/10) | 3.03 s
[Task 9/25] Current/Best: 7.52/ 18.84 GFLOPS | Progress: (8/10) | 4.77 s
[Task 9/25] Current/Best: 10.43/ 18.84 GFLOPS | Progress: (10/10) | 5.55 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 15.08/ 15.08 GFLOPS | Progress: (4/10) | 3.09 s
[Task 10/25] Current/Best: 5.95/ 16.83 GFLOPS | Progress: (8/10) | 4.49 s
[Task 10/25] Current/Best: 11.10/ 16.83 GFLOPS | Progress: (10/10) | 5.11 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 14.83/ 20.68 GFLOPS | Progress: (4/10) | 3.21 s
[Task 11/25] Current/Best: 17.86/ 20.68 GFLOPS | Progress: (8/10) | 5.49 s
[Task 11/25] Current/Best: 3.12/ 20.68 GFLOPS | Progress: (10/10) | 6.99 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 5.56/ 12.30 GFLOPS | Progress: (4/10) | 3.74 s
[Task 12/25] Current/Best: 12.93/ 16.33 GFLOPS | Progress: (8/10) | 5.60 s
[Task 12/25] Current/Best: 19.80/ 19.80 GFLOPS | Progress: (10/10) | 8.36 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 9.06/ 10.77 GFLOPS | Progress: (4/10) | 4.16 s
[Task 13/25] Current/Best: 6.22/ 13.53 GFLOPS | Progress: (8/10) | 7.64 s
[Task 13/25] Current/Best: 7.51/ 13.53 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: 3.72/ 17.74 GFLOPS | Progress: (4/10) | 4.32 s
[Task 14/25] Current/Best: 15.88/ 17.74 GFLOPS | Progress: (8/10) | 6.75 s
[Task 14/25] Current/Best: 14.18/ 21.73 GFLOPS | Progress: (10/10) | 7.55 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 4.82/ 21.80 GFLOPS | Progress: (4/10) | 2.90 s
[Task 15/25] Current/Best: 11.05/ 21.80 GFLOPS | Progress: (8/10) | 4.45 s
[Task 15/25] Current/Best: 21.31/ 21.80 GFLOPS | Progress: (10/10) | 5.04 s
[Task 16/25] 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: 14.05/ 19.14 GFLOPS | Progress: (4/10) | 5.19 s
[Task 1/25] Current/Best: 23.02/ 23.02 GFLOPS | Progress: (8/10) | 7.79 s
[Task 1/25] Current/Best: 1.93/ 23.02 GFLOPS | Progress: (10/10) | 13.50 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (4/10) | 2.69 s
[Task 2/25] Current/Best: 18.30/ 19.71 GFLOPS | Progress: (8/10) | 3.94 s
[Task 2/25] Current/Best: 12.36/ 19.71 GFLOPS | Progress: (10/10) | 4.92 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 14.98/ 22.43 GFLOPS | Progress: (4/10) | 2.73 s
[Task 3/25] Current/Best: 1.63/ 23.30 GFLOPS | Progress: (8/10) | 5.75 s
[Task 3/25] Current/Best: 20.58/ 23.30 GFLOPS | Progress: (10/10) | 6.51 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 16.58/ 17.21 GFLOPS | Progress: (4/10) | 3.34 s
[Task 4/25] Current/Best: 16.83/ 20.23 GFLOPS | Progress: (8/10) | 4.79 s
[Task 4/25] Current/Best: 12.13/ 20.23 GFLOPS | Progress: (10/10) | 6.56 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 10.05/ 11.63 GFLOPS | Progress: (4/10) | 2.58 s
[Task 5/25] Current/Best: 11.60/ 14.03 GFLOPS | Progress: (8/10) | 5.86 s
[Task 5/25] Current/Best: 7.87/ 14.03 GFLOPS | Progress: (10/10) | 7.69 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 4.29/ 15.11 GFLOPS | Progress: (4/10) | 3.37 s
[Task 6/25] Current/Best: 4.82/ 15.26 GFLOPS | Progress: (8/10) | 6.41 s
[Task 6/25] Current/Best: 10.29/ 19.62 GFLOPS | Progress: (10/10) | 7.48 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 12.91/ 18.80 GFLOPS | Progress: (4/10) | 3.17 s
[Task 7/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/10) | 5.10 s
[Task 7/25] Current/Best: 19.07/ 20.63 GFLOPS | Progress: (10/10) | 5.91 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 13.75/ 15.17 GFLOPS | Progress: (4/10) | 3.81 s
[Task 8/25] Current/Best: 10.49/ 15.17 GFLOPS | Progress: (8/10) | 9.88 s
[Task 8/25] Current/Best: 8.45/ 15.17 GFLOPS | Progress: (10/10) | 15.52 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 7.21/ 16.19 GFLOPS | Progress: (4/10) | 5.94 s
[Task 9/25] Current/Best: 15.87/ 16.19 GFLOPS | Progress: (8/10) | 8.76 s
[Task 9/25] Current/Best: 18.77/ 18.77 GFLOPS | Progress: (10/10) | 9.42 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 13.18/ 13.18 GFLOPS | Progress: (4/10) | 2.70 s
[Task 10/25] Current/Best: 18.62/ 18.62 GFLOPS | Progress: (8/10) | 4.39 s
[Task 10/25] Current/Best: 3.27/ 18.62 GFLOPS | Progress: (10/10) | 5.25 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (4/10) | 3.49 s
[Task 11/25] Current/Best: 23.03/ 24.13 GFLOPS | Progress: (8/10) | 5.04 s
[Task 11/25] Current/Best: 16.36/ 24.13 GFLOPS | Progress: (10/10) | 6.45 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 13.36/ 13.37 GFLOPS | Progress: (4/10) | 3.12 s
[Task 12/25] Current/Best: 22.02/ 22.02 GFLOPS | Progress: (8/10) | 6.35 s
[Task 12/25] Current/Best: 19.19/ 22.02 GFLOPS | Progress: (10/10) | 7.55 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 12.23/ 16.86 GFLOPS | Progress: (4/10) | 3.60 s
[Task 13/25] Current/Best: 22.55/ 22.92 GFLOPS | Progress: (8/10) | 6.27 s
[Task 13/25] Current/Best: 14.65/ 22.92 GFLOPS | Progress: (10/10) | 7.20 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 11.74/ 13.75 GFLOPS | Progress: (4/10) | 3.43 s
[Task 14/25] Current/Best: 14.92/ 17.67 GFLOPS | Progress: (8/10) | 5.04 s
[Task 14/25] Current/Best: 10.94/ 17.67 GFLOPS | Progress: (10/10) | 6.29 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 15.85/ 16.19 GFLOPS | Progress: (4/10) | 3.76 s
[Task 15/25] Current/Best: 14.47/ 16.19 GFLOPS | Progress: (8/10) | 8.20 s
[Task 15/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (10/10) | 8.78 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 16/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/10) | 2.63 s
[Task 16/25] Current/Best: 6.18/ 18.31 GFLOPS | Progress: (8/10) | 4.00 s
[Task 16/25] Current/Best: 16.08/ 18.31 GFLOPS | Progress: (10/10) | 4.85 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 23.89/ 23.89 GFLOPS | Progress: (4/10) | 3.10 s
[Task 17/25] Current/Best: 10.93/ 23.89 GFLOPS | Progress: (8/10) | 5.91 s
[Task 17/25] Current/Best: 7.45/ 23.89 GFLOPS | Progress: (10/10) | 7.52 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 15.45/ 15.45 GFLOPS | Progress: (4/10) | 3.30 s
[Task 18/25] Current/Best: 14.87/ 17.35 GFLOPS | Progress: (8/10) | 6.56 s
[Task 18/25] Current/Best: 11.00/ 17.35 GFLOPS | Progress: (10/10) | 7.81 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 9.52/ 21.11 GFLOPS | Progress: (4/10) | 4.42 s
[Task 19/25] Current/Best: 15.79/ 21.29 GFLOPS | Progress: (8/10) | 6.66 s
[Task 19/25] Current/Best: 10.50/ 21.29 GFLOPS | Progress: (10/10) | 7.90 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 7.05/ 18.20 GFLOPS | Progress: (4/10) | 2.40 s
[Task 20/25] Current/Best: 6.91/ 18.20 GFLOPS | Progress: (8/10) | 4.79 s
[Task 20/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (10/10) | 5.77 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/10) | 2.16 s
[Task 21/25] Current/Best: 14.82/ 20.66 GFLOPS | Progress: (8/10) | 4.08 s
[Task 21/25] Current/Best: 12.75/ 20.66 GFLOPS | Progress: (10/10) | 5.10 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 9.04/ 21.23 GFLOPS | Progress: (4/10) | 3.39 s
[Task 22/25] Current/Best: 4.79/ 21.23 GFLOPS | Progress: (8/10) | 6.27 s
[Task 22/25] Current/Best: 18.97/ 21.23 GFLOPS | Progress: (10/10) | 6.87
s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 13.85/ 20.80 GFLOPS | Progress: (4/10) | 3.13 s
[Task 23/25] Current/Best: 11.05/ 21.27 GFLOPS | Progress: (8/10) | 7.07 s
[Task 23/25] Current/Best: 16.97/ 21.27 GFLOPS | Progress: (10/10) | 8.20 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 7.66/ 9.91 GFLOPS | Progress: (4/10) | 12.09 s
[Task 24/25] Current/Best: 8.23/ 9.91 GFLOPS | Progress: (8/10) | 21.89 s
[Task 24/25] Current/Best: 3.62/ 9.91 GFLOPS | Progress: (10/10) | 22.96 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 16/25] Current/Best: 14.13/ 21.17 GFLOPS | Progress: (4/10) | 2.27 s
[Task 16/25] Current/Best: 6.05/ 21.17 GFLOPS | Progress: (8/10) | 3.86 s
[Task 16/25] Current/Best: 7.26/ 21.17 GFLOPS | Progress: (10/10) | 4.98 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 11.03/ 12.27 GFLOPS | Progress: (4/10) | 4.68 s
[Task 17/25] Current/Best: 11.55/ 15.78 GFLOPS | Progress: (8/10) | 8.52 s
[Task 17/25] Current/Best: 14.75/ 21.19 GFLOPS | Progress: (10/10) | 9.51 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 8.52/ 15.17 GFLOPS | Progress: (4/10) | 8.17 s
[Task 18/25] Current/Best: 18.59/ 18.59 GFLOPS | Progress: (8/10) | 11.52 s
[Task 18/25] Current/Best: 12.71/ 18.59 GFLOPS | Progress: (10/10) | 12.70 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 16.23/ 16.23 GFLOPS | Progress: (4/10) | 5.00 s
[Task 19/25] Current/Best: 5.38/ 16.23 GFLOPS | Progress: (8/10) | 8.88 s
[Task 19/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (10/10) | 9.76 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 10.63/ 21.94 GFLOPS | Progress: (4/10) | 2.45 s
[Task 20/25] Current/Best: 15.75/ 21.94 GFLOPS | Progress: (8/10) | 4.92 s
[Task 20/25] Current/Best: 14.74/ 21.94 GFLOPS | Progress: (10/10) | 5.71 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 13.16/ 16.45 GFLOPS | Progress: (4/10) | 2.96 s
[Task 21/25] Current/Best: 17.32/ 17.95 GFLOPS | Progress: (8/10) | 4.64 s
[Task 21/25] Current/Best: 17.11/ 17.95 GFLOPS | Progress: (10/10) | 6.12 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 2.24/ 18.74 GFLOPS | Progress: (4/10) | 2.71 s
[Task 22/25] Current/Best: 6.44/ 21.19 GFLOPS | Progress: (8/10) | 4.18 s
[Task 22/25] Current/Best: 11.69/ 21.19 GFLOPS | Progress: (10/10) | 5.00 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 9.01/ 17.98 GFLOPS | Progress: (4/10) | 5.55 s
[Task 23/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/10) | 7.50 s
[Task 23/25] Current/Best: 12.98/ 19.99 GFLOPS | Progress: (10/10) | 8.53 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 0.98/ 3.13 GFLOPS | Progress: (4/10) | 13.76 s
[Task 24/25] Current/Best: 7.28/ 8.51 GFLOPS | Progress: (8/10) | 29.63 s
[Task 24/25] Current/Best: 4.40/ 8.51 GFLOPS | Progress: (10/10) | 41.41 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
- Done.
-
[Task 25/25] Current/Best: 1.55/ 9.00 GFLOPS | Progress: (4/10) | 6.18 s
[Task 25/25] Current/Best: 5.58/ 9.00 GFLOPS | Progress: (8/10) | 8.67 s
[Task 25/25] Current/Best: 1.55/ 9.00 GFLOPS | Progress: (10/10) | 10.52 s Done.
-
+
[Task 25/25] Current/Best: 5.54/ 9.14 GFLOPS | Progress: (4/10) | 14.79 s
[Task 25/25] Current/Best: 2.93/ 9.14 GFLOPS | Progress: (8/10) | 20.12 s
[Task 25/25] Current/Best: 9.07/ 9.14 GFLOPS | Progress: (10/10) | 47.83 s
The output from this tuning process will look something like this:
@@ -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=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
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': 441.33022453000194, 'median': 441.502400600001, 'std': 1.0752810855332575}
- unoptimized: {'mean': 493.9763870700006, 'median': 493.863586949999, 'std': 0.6900472424638796}
+ optimized: {'mean': 430.242951299997, 'median': 430.6716918999882, 'std': 1.105825627012529}
+ unoptimized: {'mean': 497.1574179799994, 'median': 496.9821459000002, 'std': 1.1958401633421292}
@@ -670,7 +677,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 36.976 seconds)
+ **Total running time of the script:** ( 7 minutes 43.631 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 3c01e31b6..db2183e86 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
- 1.27e-07 secs/op
+ 1.263e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index ed0a15b00..c29a4c63c 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, 0xf1d4070)), stage(b, placeholder(b, 0x1ad25990)), 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, 0xd6c4b60)), stage(b, placeholder(b, 0x22295ea0)), 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 374ecef85..05d55d649 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
=================
-**09:15.323** total execution time for **tutorial** files:
+**11:08.218** total execution time for **tutorial** files:
-- **06:36.976**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **00:59.670**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:47.697**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.955**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:21.848**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.092**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.720**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.216**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.046**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.036**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.034**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.034**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **07:43.631**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:24.223**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:59.421**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:32.385**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:26.316**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:01.135**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.724**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.201**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.049**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.045**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.044**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.044**: :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 ba3e6db3a..7c6d0a39b 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -243,8 +243,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000007
+ Numpy running time: 0.000009
+ naive: 0.000006
@@ -335,7 +335,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000006
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.902440000862043e-06 1.0
- naive 6.5595e-06 0.8300600826180841
- parallel 6.8814e-06 0.8707943368439796
- vector 2.47215e-05 3.1283375764071906
+ numpy 9.080570000605803e-06 1.0
+ naive 5.8536999999999995e-06 0.6446401491987259
+ parallel 6.1858999999999995e-06 0.6812237557319983
+ vector 2.4592800000000003e-05 2.708288135916502
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018726
+ Numpy running time: 0.018744
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.304589
+ none: 3.260776
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.307722
+ blocking: 0.312385
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.345361
+ vectorization: 0.349270
@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: 0.118181
+ loop permutation: 0.123660
@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: 0.109134
+ array packing: 0.109355
@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: 0.110648
+ block caching: 0.111397
@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: 0.144247
+ parallelization: 0.145172
@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 3.3045888673 1.0
- blocking 0.30772193059999997 0.09311958096966623
- vectorization 0.34536051590000005 0.10450937462068477
- loop permutation 0.11818090830000001 0.03576266611239879
- array packing 0.10913402759999999 0.03302499402570688
- block caching 0.11064754350000001 0.03348299832239165
- parallelization 0.14424729139999998 0.043650601388685484
+ none 3.2607762086000003 1.0
+ blocking 0.31238460989999994 0.0958006897486905
+ vectorization 0.3492703231 0.10711263231706344
+ loop permutation 0.1236603495 0.037923592908294994
+ array packing 0.10935490769999998 0.03353646515562349
+ block caching 0.11139655620000002 0.03416258862113927
+ parallelization 0.1451716146 0.0445205697395372
diff --git a/docs/commit_hash b/docs/commit_hash
index c137847d8..6284ef94b 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fb32997369ddebad7aa8104c4bbba8f4a29d1c23
+98aa41e329c20a5b8b34a34387fcc9067db5f22a
diff --git a/docs/genindex.html b/docs/genindex.html
index c9e1549e8..6246a0942 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -1471,6 +1471,8 @@
<li><a href="reference/api/python/relay/transform.html#tvm.relay.transform.FlattenAtrousConv">FlattenAtrousConv() (in module tvm.relay.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.FlattenBuffer">FlattenBuffer() (in module tvm.tir.transform)</a>
+</li>
+ <li><a href="reference/api/python/relay/transform.html#tvm.relay.transform.FlexibleShapeDispatch">FlexibleShapeDispatch (class in tvm.relay.transform)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.FloatImm">FloatImm (class in tvm.tir)</a>
</li>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 68a94e7ab..8feddd275 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.zip16a551bd-dfd6-4755-89de-01f306aa40c5 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.zip7b2c8157-3e66-49a7-8ef6-d3d761608d4d 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 72a9b7999..a6231c44f 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,60 +406,47 @@ 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<10:27, 69.3kB/s]
- 0%| | 48.0k/41.5M [00:00<06:10, 117kB/s]
- 0%| | 96.0k/41.5M [00:00<04:11, 172kB/s]
- 0%| | 160k/41.5M [00:01<06:00, 120kB/s]
- 1%| | 272k/41.5M [00:01<03:17, 219kB/s]
- 1%|1 | 488k/41.5M [00:01<01:42, 418kB/s]
- 2%|1 | 768k/41.5M [00:02<01:06, 641kB/s]
- 3%|2 | 1.05M/41.5M [00:02<00:48, 869kB/s]
- 3%|3 | 1.34M/41.5M [00:02<00:40, 1.04MB/s]
- 4%|4 | 1.66M/41.5M [00:02<00:35, 1.18MB/s]
- 5%|4 | 1.99M/41.5M [00:02<00:32, 1.26MB/s]
- 6%|5 | 2.34M/41.5M [00:03<00:29, 1.41MB/s]
- 7%|6 | 2.71M/41.5M [00:03<00:26, 1.55MB/s]
- 7%|7 | 3.10M/41.5M [00:03<00:24, 1.63MB/s]
- 8%|8 | 3.51M/41.5M [00:03<00:23, 1.68MB/s]
- 9%|9 | 3.93M/41.5M [00:03<00:21, 1.80MB/s]
- 11%|# | 4.38M/41.5M [00:04<00:19, 1.95MB/s]
- 12%|#1 | 4.85M/41.5M [00:04<00:18, 2.03MB/s]
- 13%|#2 | 5.34M/41.5M [00:04<00:18, 2.08MB/s]
- 14%|#4 | 5.86M/41.5M [00:04<00:16, 2.22MB/s]
- 15%|#5 | 6.40M/41.5M [00:05<00:15, 2.38MB/s]
- 17%|#6 | 6.97M/41.5M [00:05<00:14, 2.46MB/s]
- 18%|#8 | 7.56M/41.5M [00:05<00:14, 2.52MB/s]
- 20%|#9 | 8.19M/41.5M [00:05<00:12, 2.71MB/s]
- 21%|##1 | 8.84M/41.5M [00:05<00:11, 2.88MB/s]
- 23%|##2 | 9.52M/41.5M [00:06<00:11, 2.98MB/s]
- 25%|##4 | 10.2M/41.5M [00:06<00:10, 3.05MB/s]
- 27%|##6 | 11.0M/41.5M [00:06<00:09, 3.29MB/s]
- 28%|##8 | 11.8M/41.5M [00:06<00:09, 3.46MB/s]
- 30%|### | 12.6M/41.5M [00:07<00:08, 3.53MB/s]
- 32%|###2 | 13.4M/41.5M [00:07<00:08, 3.57MB/s]
- 34%|###4 | 14.2M/41.5M [00:07<00:07, 3.81MB/s]
- 37%|###6 | 15.2M/41.5M [00:07<00:06, 4.04MB/s]
- 39%|###8 | 16.1M/41.5M [00:07<00:06, 4.16MB/s]
- 41%|####1 | 17.1M/41.5M [00:08<00:05, 4.26MB/s]
- 44%|####3 | 18.2M/41.5M [00:08<00:05, 4.61MB/s]
- 47%|####6 | 19.3M/41.5M [00:08<00:04, 4.89MB/s]
- 49%|####9 | 20.5M/41.5M [00:08<00:04, 5.03MB/s]
- 52%|#####2 | 21.7M/41.5M [00:08<00:04, 5.15MB/s]
- 55%|#####5 | 23.0M/41.5M [00:09<00:03, 5.57MB/s]
- 59%|#####8 | 24.3M/41.5M [00:09<00:03, 5.93MB/s]
- 62%|######1 | 25.7M/41.5M [00:09<00:02, 6.10MB/s]
- 66%|######5 | 27.2M/41.5M [00:09<00:02, 6.23MB/s]
- 69%|######9 | 28.7M/41.5M [00:10<00:02, 6.62MB/s]
- 73%|#######2 | 30.2M/41.5M [00:10<00:01, 6.90MB/s]
- 76%|#######6 | 31.6M/41.5M [00:10<00:01, 8.25MB/s]
- 78%|#######8 | 32.5M/41.5M [00:10<00:01, 7.97MB/s]
- 80%|######## | 33.3M/41.5M [00:10<00:01, 6.37MB/s]
- 83%|########3 | 34.6M/41.5M [00:10<00:01, 6.45MB/s]
- 87%|########6 | 36.1M/41.5M [00:11<00:00, 6.83MB/s]
- 91%|######### | 37.6M/41.5M [00:11<00:00, 6.83MB/s]
- 94%|#########4| 39.0M/41.5M [00:11<00:00, 6.73MB/s]
- 98%|#########7| 40.5M/41.5M [00:11<00:00, 7.00MB/s]
-100%|##########| 41.5M/41.5M [00:11<00:00, 3.68MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:50, 92.4kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:57, 146kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:31, 205kB/s]
+ 0%| | 168k/41.5M [00:00<02:30, 288kB/s]
+ 1%| | 344k/41.5M [00:00<01:18, 548kB/s]
+ 1%|1 | 536k/41.5M [00:01<00:58, 737kB/s]
+ 3%|2 | 1.06M/41.5M [00:01<00:27, 1.53MB/s]
+ 5%|5 | 2.09M/41.5M [00:01<00:13, 2.96MB/s]
+ 9%|8 | 3.57M/41.5M [00:01<00:08, 4.76MB/s]
+ 12%|#2 | 5.05M/41.5M [00:01<00:06, 5.97MB/s]
+ 16%|#5 | 6.53M/41.5M [00:01<00:05, 6.81MB/s]
+ 19%|#9 | 8.02M/41.5M [00:02<00:04, 7.40MB/s]
+ 23%|##2 | 9.48M/41.5M [00:02<00:04, 7.77MB/s]
+ 26%|##6 | 11.0M/41.5M [00:02<00:03, 8.05MB/s]
+ 30%|##9 | 12.4M/41.5M [00:02<00:03, 8.25MB/s]
+ 34%|###3 | 13.9M/41.5M [00:02<00:03, 8.39MB/s]
+ 37%|###7 | 15.4M/41.5M [00:03<00:03, 8.49MB/s]
+ 41%|#### | 16.9M/41.5M [00:03<00:03, 8.55MB/s]
+ 44%|####4 | 18.4M/41.5M [00:03<00:02, 8.60MB/s]
+ 48%|####7 | 19.9M/41.5M [00:03<00:02, 9.74MB/s]
+ 51%|##### | 21.0M/41.5M [00:03<00:02, 10.2MB/s]
+ 53%|#####3 | 22.0M/41.5M [00:03<00:02, 9.21MB/s]
+ 55%|#####5 | 22.9M/41.5M [00:03<00:02, 7.98MB/s]
+ 59%|#####8 | 24.3M/41.5M [00:04<00:01, 9.26MB/s]
+ 61%|###### | 25.2M/41.5M [00:04<00:01, 9.39MB/s]
+ 63%|######3 | 26.2M/41.5M [00:04<00:01, 8.38MB/s]
+ 66%|######5 | 27.3M/41.5M [00:04<00:01, 8.90MB/s]
+ 69%|######8 | 28.5M/41.5M [00:04<00:01, 9.88MB/s]
+ 71%|#######1 | 29.5M/41.5M [00:04<00:01, 8.79MB/s]
+ 73%|#######3 | 30.4M/41.5M [00:04<00:01, 7.55MB/s]
+ 76%|#######6 | 31.7M/41.5M [00:04<00:01, 8.95MB/s]
+ 79%|#######8 | 32.6M/41.5M [00:05<00:01, 9.12MB/s]
+ 81%|######## | 33.5M/41.5M [00:05<00:01, 8.12MB/s]
+ 83%|########3 | 34.6M/41.5M [00:05<00:00, 8.82MB/s]
+ 86%|########6 | 35.8M/41.5M [00:05<00:00, 9.73MB/s]
+ 89%|########8 | 36.8M/41.5M [00:05<00:00, 8.66MB/s]
+ 91%|######### | 37.7M/41.5M [00:05<00:00, 7.45MB/s]
+ 94%|#########4| 39.0M/41.5M [00:05<00:00, 8.99MB/s]
+ 96%|#########6| 40.0M/41.5M [00:05<00:00, 9.13MB/s]
+ 99%|#########8| 40.9M/41.5M [00:06<00:00, 8.12MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 7.14MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 4f3c6a80f..93fd5f526 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 12.515 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.899 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 2a7676790..cfced0ae2 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,10 +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]
- 31%|### | 13.7M/44.7M [00:00<00:00, 142MB/s]
- 61%|######1 | 27.3M/44.7M [00:00<00:00, 107MB/s]
- 89%|########9 | 39.8M/44.7M [00:00<00:00, 115MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 122MB/s]
+ 39%|###8 | 17.2M/44.7M [00:00<00:00, 180MB/s]
+ 77%|#######6 | 34.4M/44.7M [00:00<00:00, 149MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 157MB/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 625069900..77bb5048f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.805 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.401 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 95a405e0f..a4f87952b 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:30.804</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:22.520</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:12.515</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>01:00.805</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:57.171</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:36.437</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>00:26.046</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>00:21.613</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:21.357</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:19.680</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>00:12.515</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>00:02.665</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>01:06.899</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>01:04.401</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>00:57.651</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>00:30.145</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>00:25.110</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>00:21.744</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>00:21.411</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:18.941</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>00:13.701</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>00:02.516</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 135268434..95269aae5 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1265 16.0957 16.4350 16.0224 0.1131
+ 16.2510 15.8680 17.0769 15.7228 0.5397
</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 09cad7fa4..4fe4ab33e 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,55 +409,22 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|3 | 5.31M/170M [00:00<00:03, 55.5MB/s]
- 6%|6 | 10.6M/170M [00:00<00:03, 43.3MB/s]
- 9%|8 | 15.1M/170M [00:00<00:03, 44.3MB/s]
- 11%|#1 | 19.4M/170M [00:00<00:04, 39.0MB/s]
- 14%|#3 | 23.3M/170M [00:00<00:04, 34.6MB/s]
- 16%|#5 | 26.7M/170M [00:00<00:05, 28.3MB/s]
- 17%|#7 | 29.5M/170M [00:00<00:05, 25.8MB/s]
- 19%|#8 | 32.1M/170M [00:01<00:05, 25.9MB/s]
- 20%|## | 34.7M/170M [00:01<00:05, 24.5MB/s]
- 22%|##2 | 37.5M/170M [00:01<00:05, 25.6MB/s]
- 25%|##4 | 42.0M/170M [00:01<00:04, 31.2MB/s]
- 27%|##6 | 45.0M/170M [00:01<00:04, 31.0MB/s]
- 28%|##8 | 48.1M/170M [00:01<00:04, 29.4MB/s]
- 30%|### | 51.1M/170M [00:01<00:04, 30.0MB/s]
- 33%|###3 | 56.2M/170M [00:01<00:03, 34.5MB/s]
- 36%|###6 | 61.4M/170M [00:01<00:02, 39.9MB/s]
- 39%|###8 | 65.9M/170M [00:02<00:02, 41.9MB/s]
- 41%|####1 | 70.3M/170M [00:02<00:02, 43.0MB/s]
- 44%|####3 | 74.4M/170M [00:02<00:02, 37.4MB/s]
- 46%|####6 | 78.3M/170M [00:02<00:02, 38.3MB/s]
- 48%|####8 | 82.1M/170M [00:02<00:02, 31.5MB/s]
- 50%|##### | 85.4M/170M [00:02<00:02, 30.8MB/s]
- 52%|#####2 | 88.5M/170M [00:02<00:03, 26.8MB/s]
- 54%|#####3 | 91.2M/170M [00:02<00:03, 27.1MB/s]
- 56%|#####5 | 94.4M/170M [00:03<00:02, 28.5MB/s]
- 58%|#####7 | 97.7M/170M [00:03<00:02, 30.1MB/s]
- 59%|#####9 | 101M/170M [00:03<00:02, 26.9MB/s]
- 61%|###### | 103M/170M [00:03<00:02, 23.4MB/s]
- 62%|######2 | 106M/170M [00:03<00:02, 23.3MB/s]
- 64%|######3 | 108M/170M [00:03<00:02, 23.8MB/s]
- 65%|######5 | 110M/170M [00:03<00:02, 22.6MB/s]
- 66%|######6 | 113M/170M [00:03<00:02, 20.4MB/s]
- 68%|######7 | 115M/170M [00:04<00:02, 21.5MB/s]
- 69%|######9 | 118M/170M [00:04<00:02, 22.5MB/s]
- 71%|####### | 120M/170M [00:04<00:02, 23.6MB/s]
- 73%|#######2 | 124M/170M [00:04<00:01, 27.3MB/s]
- 75%|#######4 | 127M/170M [00:04<00:01, 25.8MB/s]
- 76%|#######5 | 129M/170M [00:04<00:01, 24.8MB/s]
- 79%|#######8 | 134M/170M [00:04<00:01, 31.8MB/s]
- 81%|######## | 137M/170M [00:04<00:01, 32.6MB/s]
- 83%|########2 | 140M/170M [00:04<00:01, 30.8MB/s]
- 84%|########4 | 143M/170M [00:05<00:00, 29.3MB/s]
- 86%|########6 | 146M/170M [00:05<00:00, 29.3MB/s]
- 89%|########9 | 151M/170M [00:05<00:00, 35.8MB/s]
- 92%|#########2| 156M/170M [00:05<00:00, 40.2MB/s]
- 94%|#########4| 160M/170M [00:05<00:00, 40.4MB/s]
- 97%|#########6| 164M/170M [00:05<00:00, 30.3MB/s]
- 99%|#########9| 168M/170M [00:05<00:00, 33.2MB/s]
-100%|##########| 170M/170M [00:05<00:00, 30.6MB/s]
+ 3%|3 | 5.16M/170M [00:00<00:03, 54.0MB/s]
+ 9%|9 | 15.7M/170M [00:00<00:01, 84.9MB/s]
+ 14%|#3 | 23.8M/170M [00:00<00:02, 67.0MB/s]
+ 20%|#9 | 33.5M/170M [00:00<00:01, 78.9MB/s]
+ 27%|##6 | 45.2M/170M [00:00<00:01, 92.8MB/s]
+ 33%|###3 | 56.8M/170M [00:00<00:01, 102MB/s]
+ 40%|#### | 68.5M/170M [00:00<00:00, 108MB/s]
+ 47%|####6 | 79.1M/170M [00:00<00:01, 92.6MB/s]
+ 54%|#####4 | 91.9M/170M [00:01<00:00, 104MB/s]
+ 61%|######1 | 104M/170M [00:01<00:00, 110MB/s]
+ 69%|######8 | 116M/170M [00:01<00:00, 116MB/s]
+ 75%|#######5 | 128M/170M [00:01<00:00, 95.9MB/s]
+ 82%|########1 | 139M/170M [00:01<00:00, 101MB/s]
+ 88%|########7 | 149M/170M [00:01<00:00, 95.5MB/s]
+ 95%|#########4| 161M/170M [00:01<00:00, 102MB/s]
+100%|##########| 170M/170M [00:01<00:00, 94.4MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -550,7 +517,7 @@ 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 14.754 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.218 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 1a69d0860..43fe12391 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,8 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 35%|###4 | 4.70M/13.6M [00:00<00:00, 49.2MB/s]
- 74%|#######3 | 10.0M/13.6M [00:00<00:00, 52.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 53.8MB/s]
+ 32%|###1 | 4.30M/13.6M [00:00<00:00, 45.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 78.3MB/s]
</pre></div>
</div>
</div>
@@ -541,7 +540,7 @@ 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)
- 90.4861 90.3578 95.5018 90.1938 0.5526
+ 90.6081 90.4701 93.1976 90.2701 0.3699
</pre></div>
</div>
<div class="admonition note">
@@ -580,7 +579,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.712 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.115 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 195477120..c3daf39d4 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)
- 120.3253 120.2978 124.9795 119.7389 0.5480
+ 120.2118 120.1631 123.9041 119.4701 0.5162
</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 58.020 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.331 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 04a54afa5..f9efdbd2e 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 11.942 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 57.106 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 adf488617..02227a389 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,24 +415,24 @@ 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]
- 2%|2 | 3174/132723 [00:00<00:04, 31735.26KB/s]
- 7%|7 | 9932/132723 [00:00<00:02, 52815.43KB/s]
- 13%|#3 | 17892/132723 [00:00<00:01, 65042.08KB/s]
- 20%|#9 | 26053/132723 [00:00<00:01, 71578.44KB/s]
- 26%|##5 | 34267/132723 [00:00<00:01, 75384.53KB/s]
- 32%|###1 | 42422/132723 [00:00<00:01, 77478.41KB/s]
- 38%|###8 | 50566/132723 [00:00<00:01, 78772.32KB/s]
- 44%|####4 | 58737/132723 [00:00<00:00, 79702.00KB/s]
- 50%|##### | 66886/132723 [00:00<00:00, 80258.54KB/s]
- 57%|#####6 | 75034/132723 [00:01<00:00, 80630.94KB/s]
- 63%|######2 | 83173/132723 [00:01<00:00, 80860.00KB/s]
- 69%|######8 | 91329/132723 [00:01<00:00, 81069.31KB/s]
- 75%|#######4 | 99436/132723 [00:01<00:00, 81031.62KB/s]
- 81%|########1 | 107587/132723 [00:01<00:00, 81174.91KB/s]
- 87%|########7 | 115725/132723 [00:01<00:00, 81232.71KB/s]
- 93%|#########3| 123892/132723 [00:01<00:00, 81363.16KB/s]
-100%|#########9| 132131/132723 [00:01<00:00, 81666.28KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77652.34KB/s]
+ 2%|2 | 2679/132723 [00:00<00:04, 26786.64KB/s]
+ 6%|6 | 8269/132723 [00:00<00:02, 43907.22KB/s]
+ 12%|#2 | 16374/132723 [00:00<00:01, 60123.44KB/s]
+ 17%|#6 | 22546/132723 [00:00<00:01, 60746.74KB/s]
+ 23%|##3 | 31054/132723 [00:00<00:01, 69477.15KB/s]
+ 30%|##9 | 39323/132723 [00:00<00:01, 73952.96KB/s]
+ 36%|###6 | 47803/132723 [00:00<00:01, 77489.43KB/s]
+ 42%|####2 | 56396/132723 [00:00<00:00, 80169.15KB/s]
+ 49%|####8 | 64959/132723 [00:00<00:00, 81872.80KB/s]
+ 55%|#####5 | 73625/132723 [00:01<00:00, 83346.13KB/s]
+ 62%|######1 | 82285/132723 [00:01<00:00, 84338.82KB/s]
+ 68%|######8 | 90890/132723 [00:01<00:00, 84857.90KB/s]
+ 75%|#######4 | 99376/132723 [00:01<00:00, 82695.87KB/s]
+ 81%|########1 | 108022/132723 [00:01<00:00, 83810.75KB/s]
+ 88%|########7 | 116414/132723 [00:01<00:00, 66191.21KB/s]
+ 93%|#########3| 123611/132723 [00:01<00:00, 63721.97KB/s]
+ 99%|#########8| 131062/132723 [00:01<00:00, 66446.63KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 71864.16KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -472,7 +472,7 @@ 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 26.356 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.685 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 1bbae4a3e..8a429452b 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,15 +300,15 @@
<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>10:48.435</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:26.792</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:14.754</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>02:26.356</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>01:58.020</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>01:11.942</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>01:06.712</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:28.678</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>00:21.764</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>03:11.218</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>02:26.685</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>01:57.106</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>01:53.331</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>01:07.115</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>00:29.368</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>00:21.760</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>00:00.209</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 2ec55a7c0..97a593872 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.zip463a2a1d-3b7b-4837-a02d-b86d5f887657 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.zipb6163e60-6cc7-441f-8e4f-531b7765a8e9 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 c9304cbf8..2ca4f5193 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:38.160</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.790</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.696</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>00:02.214</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>00:01.039</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.211</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:35.215</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>00:02.273</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>00:01.092</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>00:00.210</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 081376f62..08a08cc92 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: 5877us [5877us] (44.50%; 44.50%)
-FoldScaleAxis: 7331us [2us] (55.50%; 55.50%)
- FoldConstant: 7329us [1552us] (55.49%; 99.97%)
- InferType: 5777us [5777us] (43.74%; 78.83%)
+InferType: 6149us [6149us] (45.45%; 45.45%)
+FoldScaleAxis: 7381us [2us] (54.55%; 54.55%)
+ FoldConstant: 7379us [1525us] (54.54%; 99.97%)
+ InferType: 5854us [5854us] (43.26%; 79.33%)
</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: 5707us [5707us] (44.76%; 44.76%)
-FoldScaleAxis: 7044us [2us] (55.24%; 55.24%)
- FoldConstant: 7042us [1495us] (55.23%; 99.97%)
- InferType: 5548us [5548us] (43.51%; 78.78%)
+InferType: 5905us [5905us] (44.61%; 44.61%)
+FoldScaleAxis: 7333us [2us] (55.39%; 55.39%)
+ FoldConstant: 7331us [1526us] (55.38%; 99.97%)
+ InferType: 5805us [5805us] (43.85%; 79.19%)
</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 6cb3cbb8a..9528c0a2c 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: 54.116121 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.021404 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 47fb5d505..6a9aa3203 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: 6.246579 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.449030 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 54f7028d3..2414ffd7f 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: 0.019112
-Baseline: 3.265317
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019271
+Baseline: 3.169802
</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: 0.315681
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.309262
</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: 0.349897
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.343368
</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: 0.116375
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122711
</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: 0.111497
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111697
</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: 0.111295
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112147
</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: 0.145145
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144950
</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 627de6794..096d33e8d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.069</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.851</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.366</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>00:01.434</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>00:01.269</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>00:32.161</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>00:01.439</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>00:01.250</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 59d9e0f32..73bd5839e 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>04:57.938</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:56.803</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:23.093</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>01:20.069</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>00:41.024</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>00:16.261</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>00:08.868</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>00:08.623</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>02:21.494</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>01:20.656</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>00:40.438</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>00:16.546</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>00:09.065</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>00:08.605</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 2e0c761c6..4ed3af514 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
@@ -470,12 +470,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=64)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -489,76 +489,501 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- conv2d_nchw_1[14] = 0f32
- conv2d_nchw_1[15] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[(threadIdx.x_1*3)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 3))), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 1)] = @tir.if_then_else(((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 7)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*3) + 2)] = @tir.if_then_else((((1 <= (floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 21), 3) + ry.outer.outer) < 8)) && (floormod(threadIdx.x_1, 3) < 2)), data[(((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 3)*7)) + (ry.outer.outer*7)) + (floormod(threadIdx.x_1, 3)*3)) - 6)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 70), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*3) + 294)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 6), 9))) && (floormod(((threadIdx.x_1*3) + 6), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 6), [...]
- pad_temp.shared_1[((threadIdx.x_1*3) + 295)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 7), 9))) && (floormod(((threadIdx.x_1*3) + 7), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 7), [...]
- pad_temp.shared_1[((threadIdx.x_1*3) + 296)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 98), 21), 3) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*3) + 8), 9))) && (floormod(((threadIdx.x_1*3) + 8), 9) < 8)), data[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 98), 3)*7)) + (ry.outer.outer*7)) + floormod(((threadIdx.x_1*3) + 8), [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 49), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 98), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 98), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 196), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 147), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 196), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 392), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 245), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 490), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 294), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 8)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 82), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 2) + 343), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 686), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_6: int32 = (ff.outer.inner*4)
- let cse_var_5: int32 = (cse_var_6 + 3)
- let cse_var_4: int32 = (cse_var_6 + 2)
- let cse_var_3: int32 = (cse_var_6 + 1)
- {
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 75)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 78)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*252) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*384) + (ff.outer.inner*96)) + (rc.outer.inner*12)) + rx.outer.inner) + 81)]))
- }
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 10), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 80), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 128), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 3)*7)) + floormod(blockIdx.x, 7)) + fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 144)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 9), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 144), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 3), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 160), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 160), 27), 3)*7)) + floormod(blockIdx.x, 7)) + fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 176)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 176), 27)) && (floormod((threadIdx.x_1 + 14), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 176), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 176), 27), 3)*7)) + floormod(blockIdx.x, 7)) + fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 8), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 208)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 19), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 208), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 208), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 16))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 32))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 48))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 10), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 22), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 26), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 30), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 34), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 38), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 46), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 50), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 58), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 62), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 66), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 74), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 78), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 82), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 86), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 94), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 102), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 106), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 110), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 114), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 118), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 122), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 130), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 134), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 138), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 142), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1168)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 146), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1200)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 150), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1264)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 158), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1296)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1328)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 166), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1360)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 170), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1392)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 174), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1424)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 178), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1488)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 186), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1520)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 190), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1552)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 194), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1584)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1616)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 202), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1648)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 206), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 210), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1712)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 214), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1744)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 218), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1776)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 222), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1808)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 226), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1840)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 230), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1872)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 238), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1936)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 242), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1968)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 246), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2000)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 250), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2032)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 254), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2064)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 258), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2096)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 262), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 266), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 274), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 278), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (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" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 282), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 2288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 286), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ for (rc.outer.inner: int32, 0, 8) {
+ let cse_var_29: int32 = (rc.outer.inner*27)
+ let cse_var_28: int32 = (cse_var_29 + 1)
+ let cse_var_27: int32 = (cse_var_29 + 10)
+ let cse_var_26: int32 = (cse_var_29 + 11)
+ let cse_var_25: int32 = (cse_var_29 + 12)
+ let cse_var_24: int32 = (cse_var_29 + 13)
+ let cse_var_23: int32 = (cse_var_29 + 15)
+ let cse_var_22: int32 = (cse_var_29 + 16)
+ let cse_var_21: int32 = (cse_var_29 + 17)
+ let cse_var_20: int32 = (cse_var_29 + 18)
+ let cse_var_19: int32 = (cse_var_29 + 19)
+ let cse_var_18: int32 = (cse_var_29 + 2)
+ let cse_var_17: int32 = (cse_var_29 + 20)
+ let cse_var_16: int32 = (cse_var_29 + 21)
+ let cse_var_15: int32 = (cse_var_29 + 9)
+ let cse_var_14: int32 = (cse_var_29 + 8)
+ let cse_var_13: int32 = (cse_var_29 + 7)
+ let cse_var_12: int32 = (cse_var_29 + 6)
+ let cse_var_11: int32 = (cse_var_29 + 14)
+ let cse_var_10: int32 = (cse_var_29 + 5)
+ let cse_var_9: int32 = (cse_var_29 + 4)
+ let cse_var_8: int32 = (cse_var_29 + 3)
+ let cse_var_7: int32 = (cse_var_29 + 26)
+ let cse_var_6: int32 = (cse_var_29 + 25)
+ let cse_var_5: int32 = (cse_var_29 + 24)
+ let cse_var_4: int32 = (cse_var_29 + 23)
+ let cse_var_3: int32 = (cse_var_29 + 22)
+ {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[((threadIdx.x*72) + (rc.outer.inner*9))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_29]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_28]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_18]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_8]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_9]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_10]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_12]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_15]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_25]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_23]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_20]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_16]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_5]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_13]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_27]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_24]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_22]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_19]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_3]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_6]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[cse_var_14]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[cse_var_26]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[cse_var_11]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[cse_var_21]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[cse_var_17]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[cse_var_4]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[cse_var_7]*kernel.shared_1[(((threadIdx.x*72) + (rc.outer.inner*9)) + 1160)]))
}
}
}
}
- for (i1.inner: int32, 0, 16) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*784)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*16)) + i1.inner)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 784)] = max((conv2d_nchw_1[7] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 791)] = max((conv2d_nchw_1[8] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 798)] = max((conv2d_nchw_1[9] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 805)] = max((conv2d_nchw_1[10] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 812)] = max((conv2d_nchw_1[11] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 819)] = max((conv2d_nchw_1[12] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 826)] = max((conv2d_nchw_1[13] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
}
}
</pre></div>
@@ -595,7 +1020,7 @@ 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: 0.367 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.303 ms
</pre></div>
</div>
</div>
@@ -625,36 +1050,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_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=16)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_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=16)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_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=16)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -674,14 +1099,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=3)
+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=98)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=16)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -699,10 +1124,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[768];
+extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -717,57 +1142,312 @@ extern "C" __global__ void __launch_bounds__(98) default_function_kern
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 3)] = ((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 3))) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 1)] = (((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 7)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 2)] = ((((1 <= (((((int)threadIdx.x) % 21) / 3) + ry_outer_outer)) && ((((((int)threadIdx.x) % 21) / 3) + ry_outer_outer) < 8)) && ((((int)threadIdx.x) % 3) < 2)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) % 3) * 3)) - 6)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 70) {
- pad_temp_shared[((((int)threadIdx.x) * 3) + 294)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 6) % 9))) && ((((((int)threadIdx.x) * 3) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 295)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 7) % 9))) && ((((((int)threadIdx.x) * 3) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 3) + 296)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 3) + 8) % 9))) && ((((((int)threadIdx.x) * 3) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 98) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 3) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 98) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 2) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 294) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 2) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 490) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 10) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 4) & 7) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- if (((int)threadIdx.x) < 82) {
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 686) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 14) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 24)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 48)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 72)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 3)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 27)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 51)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 75)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 6)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 30)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 54)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 78)]));
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 9)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 33)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 57)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 252) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 384) + (ff_outer_inner * 96)) + (rc_outer_inner * 12)) + rx_outer_inner) + 81)]));
- }
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 27) * 49)) + ((((((int)threadIdx.x) + 4) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 144)] = ((((((int)threadIdx.x) < 15) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 144) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 176)] = (((((3 <= ((((int)threadIdx.x) + 14) % 27)) && (((((int)threadIdx.x) + 14) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 176) / 27) * 49)) + ((((((int)threadIdx.x) + 14) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 1) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 8) {
+ pad_temp_shared[(((int)threadIdx.x) + 208)] = ((((((int)threadIdx.x) < 5) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 208) / 27) * 49)) + ((((((int)threadIdx.x) + 19) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 16)];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32)];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1168) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1200)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1232) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1264)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1264) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1296)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1328)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1360)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1392)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1424)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1456) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1488)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1520)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1520) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1552)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1552) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1584)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1616)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1648)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1712)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1744) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1776)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1808)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1808) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1840)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1840) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 1872)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 1936)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1968)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2000)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2032) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2064)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2096)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2096) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[(((int)threadIdx.x) + 2160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 48))];
+ kernel_shared[(((int)threadIdx.x) + 2224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rc_outer_inner * 27)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[((((int)threadIdx.x) * 72) + (rc_outer_inner * 9))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(rc_outer_inner * 27)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 1)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 2)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 3)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 4)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 5)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 6)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 9)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 12)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 15)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 18)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 21)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 24)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 7)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 10)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 13)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 16)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 19)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 22)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 25)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 27) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 27) + 8)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((rc_outer_inner * 27) + 11)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((rc_outer_inner * 27) + 14)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((rc_outer_inner * 27) + 17)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((rc_outer_inner * 27) + 20)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((rc_outer_inner * 27) + 23)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((rc_outer_inner * 27) + 26)] * kernel_shared[(((((int)threadIdx.x) * 72) + (rc_outer_inner * 9)) + 1160)]));
}
}
- for (int i1_inner = 0; i1_inner < 16; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 784)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 16)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 784)] = max((conv2d_nchw[7] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 791)] = max((conv2d_nchw[8] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 798)] = max((conv2d_nchw[9] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 805)] = max((conv2d_nchw[10] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 812)] = max((conv2d_nchw[11] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 819)] = max((conv2d_nchw[12] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 826)] = max((conv2d_nchw[13] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -804,7 +1484,7 @@ 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 23.093 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.494 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 bc5229520..e2f01bb3e 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)
- 9.7522 9.7732 9.7778 9.7055 0.0331
+ 9.8366 9.8759 9.8844 9.7495 0.0617
</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 d0575cd1c..32f6ce697 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)
- 757.3604 758.7667 759.3807 753.9339 2.4359
+ 758.4326 760.0705 760.1377 755.0895 2.3641
</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 20.069 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.656 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 89ae5b561..a82f9ac67 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,215 +600,29 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_1: int32 = (i.outer.inner*64)
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 16)] = 0f32
- compute_5[(cse_var_1 + 17)] = 0f32
- compute_5[(cse_var_1 + 18)] = 0f32
- compute_5[(cse_var_1 + 19)] = 0f32
- compute_5[(cse_var_1 + 20)] = 0f32
- compute_5[(cse_var_1 + 21)] = 0f32
- compute_5[(cse_var_1 + 22)] = 0f32
- compute_5[(cse_var_1 + 23)] = 0f32
- compute_5[(cse_var_1 + 24)] = 0f32
- compute_5[(cse_var_1 + 25)] = 0f32
- compute_5[(cse_var_1 + 26)] = 0f32
- compute_5[(cse_var_1 + 27)] = 0f32
- compute_5[(cse_var_1 + 28)] = 0f32
- compute_5[(cse_var_1 + 29)] = 0f32
- compute_5[(cse_var_1 + 30)] = 0f32
- compute_5[(cse_var_1 + 31)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 48)] = 0f32
- compute_5[(cse_var_1 + 49)] = 0f32
- compute_5[(cse_var_1 + 50)] = 0f32
- compute_5[(cse_var_1 + 51)] = 0f32
- compute_5[(cse_var_1 + 52)] = 0f32
- compute_5[(cse_var_1 + 53)] = 0f32
- compute_5[(cse_var_1 + 54)] = 0f32
- compute_5[(cse_var_1 + 55)] = 0f32
- compute_5[(cse_var_1 + 56)] = 0f32
- compute_5[(cse_var_1 + 57)] = 0f32
- compute_5[(cse_var_1 + 58)] = 0f32
- compute_5[(cse_var_1 + 59)] = 0f32
- compute_5[(cse_var_1 + 60)] = 0f32
- compute_5[(cse_var_1 + 61)] = 0f32
- compute_5[(cse_var_1 + 62)] = 0f32
- compute_5[(cse_var_1 + 63)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (cse_var_1 + 37)
- let cse_var_66: int32 = (cse_var_1 + 36)
- let cse_var_65: int32 = (cse_var_1 + 35)
- let cse_var_64: int32 = (cse_var_1 + 34)
- let cse_var_63: int32 = (cse_var_1 + 33)
- let cse_var_62: int32 = (cse_var_1 + 32)
- let cse_var_61: int32 = (cse_var_1 + 31)
- let cse_var_60: int32 = (cse_var_1 + 30)
- let cse_var_59: int32 = (cse_var_1 + 3)
- let cse_var_58: int32 = (cse_var_1 + 29)
- let cse_var_57: int32 = (cse_var_1 + 28)
- let cse_var_56: int32 = (cse_var_1 + 27)
- let cse_var_55: int32 = (cse_var_1 + 26)
- let cse_var_54: int32 = (cse_var_1 + 25)
- let cse_var_53: int32 = (cse_var_1 + 24)
- let cse_var_52: int32 = (cse_var_1 + 39)
- let cse_var_51: int32 = (cse_var_1 + 22)
- let cse_var_50: int32 = (cse_var_1 + 21)
- let cse_var_49: int32 = (cse_var_1 + 20)
- let cse_var_48: int32 = (cse_var_1 + 2)
- let cse_var_47: int32 = (cse_var_1 + 19)
- let cse_var_46: int32 = (cse_var_1 + 18)
- let cse_var_45: int32 = (cse_var_1 + 17)
- let cse_var_44: int32 = (cse_var_1 + 16)
- let cse_var_43: int32 = (cse_var_1 + 15)
- let cse_var_42: int32 = (cse_var_1 + 14)
- let cse_var_41: int32 = (cse_var_1 + 13)
- let cse_var_40: int32 = (cse_var_1 + 12)
- let cse_var_39: int32 = (cse_var_1 + 11)
- let cse_var_38: int32 = (cse_var_1 + 10)
- let cse_var_37: int32 = (cse_var_1 + 1)
- let cse_var_36: int32 = (cse_var_1 + 23)
- let cse_var_35: int32 = (elem_idx*16)
- let cse_var_34: int32 = (cse_var_1 + 9)
- let cse_var_33: int32 = (cse_var_1 + 8)
- let cse_var_32: int32 = (cse_var_1 + 7)
- let cse_var_31: int32 = (cse_var_1 + 63)
- let cse_var_30: int32 = (cse_var_1 + 62)
- let cse_var_29: int32 = (cse_var_1 + 61)
- let cse_var_28: int32 = (cse_var_1 + 60)
- let cse_var_27: int32 = (cse_var_1 + 6)
- let cse_var_26: int32 = (cse_var_1 + 59)
- let cse_var_25: int32 = (cse_var_1 + 58)
- let cse_var_24: int32 = (cse_var_1 + 57)
- let cse_var_23: int32 = (cse_var_1 + 56)
- let cse_var_22: int32 = (cse_var_1 + 55)
- let cse_var_21: int32 = (cse_var_1 + 54)
- let cse_var_20: int32 = (cse_var_1 + 38)
- let cse_var_19: int32 = (cse_var_1 + 4)
- let cse_var_18: int32 = (cse_var_1 + 40)
- let cse_var_17: int32 = (cse_var_1 + 41)
- let cse_var_16: int32 = (cse_var_1 + 42)
- let cse_var_15: int32 = (cse_var_1 + 43)
- let cse_var_14: int32 = (cse_var_1 + 44)
- let cse_var_13: int32 = (cse_var_1 + 45)
- let cse_var_12: int32 = (cse_var_1 + 46)
- let cse_var_11: int32 = (cse_var_1 + 47)
- let cse_var_10: int32 = (cse_var_1 + 48)
- let cse_var_9: int32 = (cse_var_1 + 49)
- let cse_var_8: int32 = (cse_var_1 + 5)
- let cse_var_7: int32 = (cse_var_1 + 50)
- let cse_var_6: int32 = (cse_var_1 + 51)
- let cse_var_5: int32 = (cse_var_1 + 53)
- let cse_var_4: int32 = (cse_var_1 + 52)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*1024))
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_35)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_35) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*512) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_68: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_68, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_68, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 2) {
+ let cse_var_4: int32 = (((i0.outer*1024) + (i0.inner*512)) + (i1.outer*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -847,7 +661,7 @@ 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: 3.040 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.870 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 323c0f9de..fb8eed977 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>00:44.426</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.529</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.500</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>00:00.243</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>00:00.229</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>00:00.228</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>00:00.226</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>00:43.605</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>00:00.246</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>00:00.230</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>00:00.227</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:00.221</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
</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 698cfafdb..7b9924629 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: 67.42/67.42 result: MeasureResult(costs=(0.0034337007,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.743032693862915, timestamp=1651853234.041699) [('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: 0.00/67.42 result: Traceback (most recent call last):
+No: 6 GFLOPS: 108.25/108.25 result: MeasureResult(costs=(0.002138649875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6317508220672607, timestamp=1651868046.1444492) [('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: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/108.25 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: 0.00/67.42 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/108.25 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: 0.00/67.42 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/108.25 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: 0x00007fa069b0afa2
+ 12: 0x00007f45fdf53fa2
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: 145.08/145.08 result: MeasureResult(costs=(0.0015956777,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.425276279449463, timestamp=1651853260.5548215) [('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: 144.36/144.36 result: MeasureResult(costs=(0.00160366258,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.434868574142456, timestamp=1651868072.608344) [('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: 0.001954
+Time cost of this operator: 0.002050
</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 bb3e4b8b0..7c91a6184 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 313.8 98.75 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.966 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.284 (1, 1, 10, 10, 3) 1 1
-Total_time - 317.771 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.621 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.242 1.021 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.137 0.358 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.579 - - - -
</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 136.8 98.072 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.255 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.939 0.673 (1, 1, 10, 10, 3) 1 1
-Total_time - 139.489 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.6 96.854 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.077 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.069 (1, 1, 10, 10, 3) 1 1
+Total_time - 84.251 - - - -
</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 6d2f78ba9..2a51130cc 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>00:44.391</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:44.528</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.305</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>00:03.473</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>00:40.440</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>00:03.463</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>00:00.217</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>00:00.206</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.204</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>00:00.203</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>00:00.202</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</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 1733ffea7..21da4d01a 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>00:09.429</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.299</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:07.359</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>00:01.843</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.227</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:07.122</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>00:01.947</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>00:00.230</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 352f26bff..50c75cf33 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>00:05.821</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.880</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.117</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>00:01.176</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>00:02.138</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>00:01.187</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>00:00.749</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>00:00.731</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.320</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.252</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
-<li><p><strong>00:00.247</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>00:00.230</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>00:00.737</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
+<li><p><strong>00:00.324</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>00:00.254</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>00:00.252</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>00:00.240</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 5fbd7e813..c33071f24 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/tmpsszsjdw0/input0.cc'\nsource_filename = \"/tmp/tmpsszsjdw0/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/tmpig9au86g/input0.cc'\nsource_filename = \"/tmp/tmpig9au86g/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/objects.inv b/docs/objects.inv
index f3493d6e2..7883c460d 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 290549af0..5f76cd7bd 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -961,9 +961,11 @@ from the upper contexts.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em> or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.auto_scheduler.MeasureInput" title="tvm.auto_scheduler.measure.MeasureInput"><em>auto_scheduler.measure.MeasureInput</em></a><em>, </em><a class="reference internal" href="#tvm.auto_scheduler.MeasureResult" tit [...]
+<li><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>list of str</em><em>, or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.auto_scheduler.MeasureInput" title="tvm.auto_scheduler.measure.MeasureInput"><em>auto_scheduler.measure.MeasureInput</em></a><em>, </em><a class="reference internal [...]
If is str, then it should be the filename of a records log file.
-Each row of this file is an encoded record pair. Otherwise, it is an iterator.</p></li>
+Each row of this file is an encoded record pair. If it is an iterator,
+it can either be a set of str filenames which will be applied jointly,
+or a set of (input, result) tuples.</p></li>
<li><p><strong>n_lines</strong> (<em>Optional</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>) – if it is not None, only load the first <cite>n_lines</cite> lines of log.</p></li>
<li><p><strong>include_compatible</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a>) – When set to True, compatible records will also be considered.</p></li>
</ul>
@@ -1713,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1750,7 +1752,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/python/autotvm.html b/docs/reference/api/python/autotvm.html
index cdd3c8fd6..dbe87c9fe 100644
--- a/docs/reference/api/python/autotvm.html
+++ b/docs/reference/api/python/autotvm.html
@@ -358,9 +358,10 @@
<dd><p>Apply the history best config</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em> or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference internal" href="#tvm.autotvm.measure.MeasureResult" title="tvm.autotvm.measure.Mea [...]
+<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>list of str</em><em>, or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference int [...]
If is str, then it should be the filename of a records log file.
-Each row of this file is an encoded record pair. Otherwise, it is an iterator.</p>
+Each row of this file is an encoded record pair. If it is a list, it can either be
+a list of paths to log files that will be loaded jointly or an iterator or records.</p>
</dd>
</dl>
</dd></dl>
@@ -2169,9 +2170,10 @@ One can construct a new <cite>ConfigEntity</cite> if this is not the case.</p>
<dd><p>Apply the history best config</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em> or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference internal" href="#tvm.autotvm.measure.MeasureResult" title="tvm.autotvm.measure.Mea [...]
+<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>list of str</em><em>, or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference int [...]
If is str, then it should be the filename of a records log file.
-Each row of this file is an encoded record pair. Otherwise, it is an iterator.</p>
+Each row of this file is an encoded record pair. If it is a list, it can either be
+a list of paths to log files that will be loaded jointly or an iterator or records.</p>
</dd>
</dl>
<dl class="py method">
@@ -2180,9 +2182,11 @@ Each row of this file is an encoded record pair. Otherwise, it is an iterator.</
<dd><p>Load records to this dispatch context</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em> or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference internal" href="#tvm.autotvm.measure.MeasureResult" title="tvm.autotvm.measure.Mea [...]
+<dd class="field-odd"><p><strong>records</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>list of str</em><em>, or </em><em>iterator of</em><em> (</em><a class="reference internal" href="#tvm.autotvm.measure.MeasureInput" title="tvm.autotvm.measure.MeasureInput"><em>autotvm.measure.MeasureInput</em></a><em>, </em><a class="reference [...]
If is str, then it should be the filename of a records log file.
-Each row of this file is an encoded record pair. Otherwise, it is an iterator.</p>
+Each row of this file is an encoded record pair. If it is a list
+it can either be a list of paths to logs that will loaded jointly or
+an iterator of measurement results.</p>
</dd>
</dl>
</dd></dl>
diff --git a/docs/reference/api/python/relay/transform.html b/docs/reference/api/python/relay/transform.html
index 32488fd44..5b9d16d71 100644
--- a/docs/reference/api/python/relay/transform.html
+++ b/docs/reference/api/python/relay/transform.html
@@ -535,13 +535,16 @@
<col style="width: 90%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.relay.transform.ChangeBatch" title="tvm.relay.transform.ChangeBatch"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ChangeBatch</span></code></a>(data[, batch_size])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.relay.transform.FlexibleShapeDispatch" title="tvm.relay.transform.FlexibleShapeDispatch"><code class="xref py py-obj docutils literal notranslate"><span class="pre">FlexibleShapeDispatch</span></code></a>(buckets[, axis, ...])</p></td>
+<td><p>Enable inference of multiple shaped inputs in one module.</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.relay.transform.ChangeBatch" title="tvm.relay.transform.ChangeBatch"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ChangeBatch</span></code></a>(data[, batch_size])</p></td>
<td><p>Change the batch size.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.relay.transform.FunctionPass" title="tvm.relay.transform.FunctionPass"><code class="xref py py-obj docutils literal notranslate"><span class="pre">FunctionPass</span></code></a></p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.relay.transform.FunctionPass" title="tvm.relay.transform.FunctionPass"><code class="xref py py-obj docutils literal notranslate"><span class="pre">FunctionPass</span></code></a></p></td>
<td><p>A pass that works on each tvm.relay.Function in a module.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.relay.transform.LayoutConfig" title="tvm.relay.transform.LayoutConfig"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LayoutConfig</span></code></a>([skip_layers])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.relay.transform.LayoutConfig" title="tvm.relay.transform.LayoutConfig"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LayoutConfig</span></code></a>([skip_layers])</p></td>
<td><p>A structure for customizing the ConvertLayout pass.</p></td>
</tr>
</tbody>
@@ -580,6 +583,57 @@ allowed and indicate starting at the last layer.</p></li>
</dl>
</dd></dl>
+<dl class="py class">
+<dt class="sig sig-object py" id="tvm.relay.transform.FlexibleShapeDispatch">
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.relay.transform.</span></span><span class="sig-name descname"><span class="pre">FlexibleShapeDispatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buckets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">axis</span></span><span class="o"><span class="pre">=</span></span><span class="defaul [...]
+<dd><p>Enable inference of multiple shaped inputs in one module.</p>
+<p>This transformation adds a handler around a module that
+checks input shapes and dispatches to a subgraph specialized
+to handle the specific shapes of that input. If no exactly matching
+subgraph is available, the input will be run using full dynamism.
+For best performance, specify all the sizes the module will
+be likely to see using the buckets argument.</p>
+<p>By default, this pass will dispatch shapes that exactly match one
+of the buckets to a corresponding subgraph. All non-matching shapes
+use the same fully dynamic fallback. This can be detrimental to performance
+for those non-matching shapes. Setting auto_pad to True causes this
+pass to round-up the shape of non-matching inputs to the closest
+bucket. This allows them to use the tuned kernels of bucket shapes
+which can improve performance.</p>
+<p>Models that have multiple inputs sharing a dynamic axis, which
+is common for batch size or sequence length dynamism, are supported
+through the input_indices argument.</p>
+<p>Many types of dynamism such as batching affect both the input and output
+shape, however this is not always the case. If the output shape
+is independent of the input, the affects_output argument of this
+pass must be set to False.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>buckets</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a><em>]</em>) – The sizes of the input dimension that should be explicitly handled.
+Each value in buckets will have a corresponding subgraph constructed to
+handle it.</p></li>
+<li><p><strong>axis</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a>) – The dimension of the input that should be made flexible. This will
+most often be used for the batch dimension.</p></li>
+<li><p><strong>auto_pad</strong> (<em>Optional</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>]</em>) – If True, then padding will be inserted to values that don’t match one of
+the provided buckets.</p></li>
+<li><p><strong>pad_value</strong> (<em>Optional</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.10)"><em>float</em></a><em>]</em>) – When auto_pad is true, padding will be done with this value.</p></li>
+<li><p><strong>input_indices</strong> (<em>Optional</em><em>[</em><em>List</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>) – Which inputs should be dispatched dynamically, provided by index. All inputs
+must share the same dynamic axis.</p></li>
+<li><p><strong>affects_output</strong> (<em>Optional</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><em>bool</em></a><em>]</em>) – Whether the change in input shape has a corresponding effect on the output shape.
+Batching for example effects both the input and output whereas changing sequence
+length in an NLP model typically does not.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>ret</strong> – A pass that can be applied to a module to add flexible shape handling.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="#tvm.relay.transform.FlexibleShapeDispatch" title="tvm.relay.transform.FlexibleShapeDispatch">FlexibleShapeDispatch</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<dl class="py function">
<dt class="sig sig-object py" id="tvm.relay.transform.AlterOpLayout">
<span class="sig-prename descclassname"><span class="pre">tvm.relay.transform.</span></span><span class="sig-name descname"><span class="pre">AlterOpLayout</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.relay.transform.AlterOpLayout" title="Permalink to this definition">¶</a></dt>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 27510a02a..9ad4986e2 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/fb3299736/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 effe18182..d0c46ce99 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/fb3299736/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 bb319874d..e69f7973e 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/fb3299736/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 7a3ce9da9..bcf8f900f 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/fb3299736/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 c8cc2888c..39ce56e0d 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/fb3299736/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 ab5b9d5f7..00add4bcf 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/fb3299736/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 a8aaa1484..e1a6f20b3 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/fb3299736/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 3d9ec7127..1a402d14b 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/fb3299736/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 b88c89d4a..9ad200662 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/fb3299736/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 8d8a1cf8f..be40445ee 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/fb3299736/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 9a950bef8..d18f00dc9 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/fb3299736/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 9a4edd16d..e68bf139c 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/fb3299736/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 e5846e9eb..5d343337d 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/fb3299736/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 a3312a5a8..ae3299d1b 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/fb3299736/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 c1e330bb4..a74e0e6e0 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/fb3299736/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 625e59241..612a4b9e0 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/fb3299736/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 8f9f82a18..e5ce07545 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/fb3299736/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 498c2f830..780df13c4 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/fb3299736/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 1258d57ed..fa41f8c8a 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/fb3299736/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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 8163dc3a6..88c91cff7 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/fb3299736/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/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/fb3299736/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index b6443e1b7..fd271090f 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 318c04365..87e529091 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index dad9b7ec1..b7e19e7b0 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 3b64d70bc..422dbe025 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fb3299736/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98aa41e32/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 69fb28022..09d179516 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 8ea11ce5d..029732bed 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.731</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.893</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:20.512</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
-<li><p><strong>00:00.219</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
+<li><p><strong>00:20.676</strong>: <a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></li>
+<li><p><strong>00:00.218</strong>: <a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 2381d35b5..57e44e521 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -539,7 +539,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 21.31s!
+resnet18_v1 inference graph built in 21.98s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 585c50b7f..da376358d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -557,7 +557,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
<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/build_module.py:431: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.15s!
+yolov3-tiny inference graph built in 15.26s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index e068f2474..f0a58e2b6 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:28.675</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:30.532</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:47.298</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
-<li><p><strong>00:41.377</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
+<li><p><strong>00:48.094</strong>: <a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></li>
+<li><p><strong>00:42.439</strong>: <a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 3fe7a90da..f9395a3f4 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.583</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.535</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:03.025</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
-<li><p><strong>00:00.559</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
+<li><p><strong>00:02.972</strong>: <a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></li>
+<li><p><strong>00:00.563</strong>: <a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 272a10fa4..e332c2608 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -300,10 +300,10 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:01.007</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:01.031</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:00.511</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
-<li><p><strong>00:00.496</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
+<li><p><strong>00:00.518</strong>: <a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></li>
+<li><p><strong>00:00.513</strong>: <a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 0609df290..c4fcba364 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -453,7 +453,7 @@ trials, we can load the best schedule from the log file and apply it.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T*E
</pre></div>
</div>
</div>
@@ -545,7 +545,7 @@ 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: 93.825 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.620 ms
</pre></div>
</div>
</div>
@@ -621,6 +621,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.223 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 7cb9802a3..510bec13c 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -513,7 +513,7 @@ standard deviation.</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>{'mean': 493.9763870700006, 'median': 493.863586949999, 'std': 0.6900472424638796}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 497.1574179799994, 'median': 496.9821459000002, 'std': 1.1958401633421292}
</pre></div>
</div>
</div>
@@ -667,129 +667,129 @@ depending on the specifics of the model and the target platform.</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>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 1/25] Current/Best: 5.90/ 22.79 GFLOPS | Progress: (4/10) | 7.50 s
-[Task 1/25] Current/Best: 12.19/ 22.79 GFLOPS | Progress: (8/10) | 9.91 s
-[Task 1/25] Current/Best: 17.96/ 22.79 GFLOPS | Progress: (10/10) | 10.75 s Done.
+[Task 1/25] Current/Best: 14.05/ 19.14 GFLOPS | Progress: (4/10) | 5.19 s
+[Task 1/25] Current/Best: 23.02/ 23.02 GFLOPS | Progress: (8/10) | 7.79 s
+[Task 1/25] Current/Best: 1.93/ 23.02 GFLOPS | Progress: (10/10) | 13.50 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 2/25] Current/Best: 21.07/ 21.07 GFLOPS | Progress: (4/10) | 2.56 s
-[Task 2/25] Current/Best: 14.43/ 21.07 GFLOPS | Progress: (8/10) | 4.20 s
-[Task 2/25] Current/Best: 12.91/ 21.07 GFLOPS | Progress: (10/10) | 5.00 s Done.
+[Task 2/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (4/10) | 2.69 s
+[Task 2/25] Current/Best: 18.30/ 19.71 GFLOPS | Progress: (8/10) | 3.94 s
+[Task 2/25] Current/Best: 12.36/ 19.71 GFLOPS | Progress: (10/10) | 4.92 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 3/25] Current/Best: 17.16/ 17.16 GFLOPS | Progress: (4/10) | 2.91 s
-[Task 3/25] Current/Best: 15.28/ 17.16 GFLOPS | Progress: (8/10) | 4.75 s
-[Task 3/25] Current/Best: 1.61/ 17.59 GFLOPS | Progress: (10/10) | 6.93 s Done.
+[Task 3/25] Current/Best: 14.98/ 22.43 GFLOPS | Progress: (4/10) | 2.73 s
+[Task 3/25] Current/Best: 1.63/ 23.30 GFLOPS | Progress: (8/10) | 5.75 s
+[Task 3/25] Current/Best: 20.58/ 23.30 GFLOPS | Progress: (10/10) | 6.51 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 4/25] Current/Best: 12.29/ 16.00 GFLOPS | Progress: (4/10) | 3.57 s
-[Task 4/25] Current/Best: 12.27/ 16.67 GFLOPS | Progress: (8/10) | 10.05 s
-[Task 4/25] Current/Best: 8.78/ 21.85 GFLOPS | Progress: (10/10) | 10.72 s Done.
+[Task 4/25] Current/Best: 16.58/ 17.21 GFLOPS | Progress: (4/10) | 3.34 s
+[Task 4/25] Current/Best: 16.83/ 20.23 GFLOPS | Progress: (8/10) | 4.79 s
+[Task 4/25] Current/Best: 12.13/ 20.23 GFLOPS | Progress: (10/10) | 6.56 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 5/25] Current/Best: 6.33/ 18.31 GFLOPS | Progress: (4/10) | 2.45 s
-[Task 5/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (8/10) | 4.74 s
-[Task 5/25] Current/Best: 13.29/ 20.48 GFLOPS | Progress: (10/10) | 5.67 s Done.
+[Task 5/25] Current/Best: 10.05/ 11.63 GFLOPS | Progress: (4/10) | 2.58 s
+[Task 5/25] Current/Best: 11.60/ 14.03 GFLOPS | Progress: (8/10) | 5.86 s
+[Task 5/25] Current/Best: 7.87/ 14.03 GFLOPS | Progress: (10/10) | 7.69 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 6/25] Current/Best: 1.69/ 17.58 GFLOPS | Progress: (4/10) | 3.79 s
-[Task 6/25] Current/Best: 20.96/ 20.96 GFLOPS | Progress: (8/10) | 7.10 s
-[Task 6/25] Current/Best: 3.40/ 20.96 GFLOPS | Progress: (10/10) | 8.67 s Done.
+[Task 6/25] Current/Best: 4.29/ 15.11 GFLOPS | Progress: (4/10) | 3.37 s
+[Task 6/25] Current/Best: 4.82/ 15.26 GFLOPS | Progress: (8/10) | 6.41 s
+[Task 6/25] Current/Best: 10.29/ 19.62 GFLOPS | Progress: (10/10) | 7.48 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 7/25] Current/Best: 16.10/ 17.49 GFLOPS | Progress: (4/10) | 2.65 s
-[Task 7/25] Current/Best: 3.12/ 17.49 GFLOPS | Progress: (8/10) | 5.49 s
-[Task 7/25] Current/Best: 21.99/ 21.99 GFLOPS | Progress: (10/10) | 6.51 s Done.
+[Task 7/25] Current/Best: 12.91/ 18.80 GFLOPS | Progress: (4/10) | 3.17 s
+[Task 7/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (8/10) | 5.10 s
+[Task 7/25] Current/Best: 19.07/ 20.63 GFLOPS | Progress: (10/10) | 5.91 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 8/25] Current/Best: 16.93/ 16.93 GFLOPS | Progress: (4/10) | 4.78 s
-[Task 8/25] Current/Best: 7.34/ 16.93 GFLOPS | Progress: (8/10) | 7.26 s
-[Task 8/25] Current/Best: 4.05/ 16.93 GFLOPS | Progress: (10/10) | 13.96 s Done.
+[Task 8/25] Current/Best: 13.75/ 15.17 GFLOPS | Progress: (4/10) | 3.81 s
+[Task 8/25] Current/Best: 10.49/ 15.17 GFLOPS | Progress: (8/10) | 9.88 s
+[Task 8/25] Current/Best: 8.45/ 15.17 GFLOPS | Progress: (10/10) | 15.52 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 9/25] Current/Best: 12.11/ 18.84 GFLOPS | Progress: (4/10) | 3.03 s
-[Task 9/25] Current/Best: 7.52/ 18.84 GFLOPS | Progress: (8/10) | 4.77 s
-[Task 9/25] Current/Best: 10.43/ 18.84 GFLOPS | Progress: (10/10) | 5.55 s Done.
+[Task 9/25] Current/Best: 7.21/ 16.19 GFLOPS | Progress: (4/10) | 5.94 s
+[Task 9/25] Current/Best: 15.87/ 16.19 GFLOPS | Progress: (8/10) | 8.76 s
+[Task 9/25] Current/Best: 18.77/ 18.77 GFLOPS | Progress: (10/10) | 9.42 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 10/25] Current/Best: 15.08/ 15.08 GFLOPS | Progress: (4/10) | 3.09 s
-[Task 10/25] Current/Best: 5.95/ 16.83 GFLOPS | Progress: (8/10) | 4.49 s
-[Task 10/25] Current/Best: 11.10/ 16.83 GFLOPS | Progress: (10/10) | 5.11 s Done.
+[Task 10/25] Current/Best: 13.18/ 13.18 GFLOPS | Progress: (4/10) | 2.70 s
+[Task 10/25] Current/Best: 18.62/ 18.62 GFLOPS | Progress: (8/10) | 4.39 s
+[Task 10/25] Current/Best: 3.27/ 18.62 GFLOPS | Progress: (10/10) | 5.25 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 11/25] Current/Best: 14.83/ 20.68 GFLOPS | Progress: (4/10) | 3.21 s
-[Task 11/25] Current/Best: 17.86/ 20.68 GFLOPS | Progress: (8/10) | 5.49 s
-[Task 11/25] Current/Best: 3.12/ 20.68 GFLOPS | Progress: (10/10) | 6.99 s Done.
+[Task 11/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (4/10) | 3.49 s
+[Task 11/25] Current/Best: 23.03/ 24.13 GFLOPS | Progress: (8/10) | 5.04 s
+[Task 11/25] Current/Best: 16.36/ 24.13 GFLOPS | Progress: (10/10) | 6.45 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 12/25] Current/Best: 5.56/ 12.30 GFLOPS | Progress: (4/10) | 3.74 s
-[Task 12/25] Current/Best: 12.93/ 16.33 GFLOPS | Progress: (8/10) | 5.60 s
-[Task 12/25] Current/Best: 19.80/ 19.80 GFLOPS | Progress: (10/10) | 8.36 s Done.
+[Task 12/25] Current/Best: 13.36/ 13.37 GFLOPS | Progress: (4/10) | 3.12 s
+[Task 12/25] Current/Best: 22.02/ 22.02 GFLOPS | Progress: (8/10) | 6.35 s
+[Task 12/25] Current/Best: 19.19/ 22.02 GFLOPS | Progress: (10/10) | 7.55 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 13/25] Current/Best: 9.06/ 10.77 GFLOPS | Progress: (4/10) | 4.16 s
-[Task 13/25] Current/Best: 6.22/ 13.53 GFLOPS | Progress: (8/10) | 7.64 s
-[Task 13/25] Current/Best: 7.51/ 13.53 GFLOPS | Progress: (10/10) | 9.83 s Done.
+[Task 13/25] Current/Best: 12.23/ 16.86 GFLOPS | Progress: (4/10) | 3.60 s
+[Task 13/25] Current/Best: 22.55/ 22.92 GFLOPS | Progress: (8/10) | 6.27 s
+[Task 13/25] Current/Best: 14.65/ 22.92 GFLOPS | Progress: (10/10) | 7.20 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 14/25] Current/Best: 3.72/ 17.74 GFLOPS | Progress: (4/10) | 4.32 s
-[Task 14/25] Current/Best: 15.88/ 17.74 GFLOPS | Progress: (8/10) | 6.75 s
-[Task 14/25] Current/Best: 14.18/ 21.73 GFLOPS | Progress: (10/10) | 7.55 s
+[Task 14/25] Current/Best: 11.74/ 13.75 GFLOPS | Progress: (4/10) | 3.43 s
+[Task 14/25] Current/Best: 14.92/ 17.67 GFLOPS | Progress: (8/10) | 5.04 s
+[Task 14/25] Current/Best: 10.94/ 17.67 GFLOPS | Progress: (10/10) | 6.29 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 15/25] Current/Best: 4.82/ 21.80 GFLOPS | Progress: (4/10) | 2.90 s
-[Task 15/25] Current/Best: 11.05/ 21.80 GFLOPS | Progress: (8/10) | 4.45 s
-[Task 15/25] Current/Best: 21.31/ 21.80 GFLOPS | Progress: (10/10) | 5.04 s
+[Task 15/25] Current/Best: 15.85/ 16.19 GFLOPS | Progress: (4/10) | 3.76 s
+[Task 15/25] Current/Best: 14.47/ 16.19 GFLOPS | Progress: (8/10) | 8.20 s
+[Task 15/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (10/10) | 8.78 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-[Task 16/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/10) | 2.63 s
-[Task 16/25] Current/Best: 6.18/ 18.31 GFLOPS | Progress: (8/10) | 4.00 s
-[Task 16/25] Current/Best: 16.08/ 18.31 GFLOPS | Progress: (10/10) | 4.85 s Done.
+[Task 16/25] Current/Best: 14.13/ 21.17 GFLOPS | Progress: (4/10) | 2.27 s
+[Task 16/25] Current/Best: 6.05/ 21.17 GFLOPS | Progress: (8/10) | 3.86 s
+[Task 16/25] Current/Best: 7.26/ 21.17 GFLOPS | Progress: (10/10) | 4.98 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 17/25] Current/Best: 23.89/ 23.89 GFLOPS | Progress: (4/10) | 3.10 s
-[Task 17/25] Current/Best: 10.93/ 23.89 GFLOPS | Progress: (8/10) | 5.91 s
-[Task 17/25] Current/Best: 7.45/ 23.89 GFLOPS | Progress: (10/10) | 7.52 s Done.
+[Task 17/25] Current/Best: 11.03/ 12.27 GFLOPS | Progress: (4/10) | 4.68 s
+[Task 17/25] Current/Best: 11.55/ 15.78 GFLOPS | Progress: (8/10) | 8.52 s
+[Task 17/25] Current/Best: 14.75/ 21.19 GFLOPS | Progress: (10/10) | 9.51 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 18/25] Current/Best: 15.45/ 15.45 GFLOPS | Progress: (4/10) | 3.30 s
-[Task 18/25] Current/Best: 14.87/ 17.35 GFLOPS | Progress: (8/10) | 6.56 s
-[Task 18/25] Current/Best: 11.00/ 17.35 GFLOPS | Progress: (10/10) | 7.81 s Done.
+[Task 18/25] Current/Best: 8.52/ 15.17 GFLOPS | Progress: (4/10) | 8.17 s
+[Task 18/25] Current/Best: 18.59/ 18.59 GFLOPS | Progress: (8/10) | 11.52 s
+[Task 18/25] Current/Best: 12.71/ 18.59 GFLOPS | Progress: (10/10) | 12.70 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 19/25] Current/Best: 9.52/ 21.11 GFLOPS | Progress: (4/10) | 4.42 s
-[Task 19/25] Current/Best: 15.79/ 21.29 GFLOPS | Progress: (8/10) | 6.66 s
-[Task 19/25] Current/Best: 10.50/ 21.29 GFLOPS | Progress: (10/10) | 7.90 s Done.
+[Task 19/25] Current/Best: 16.23/ 16.23 GFLOPS | Progress: (4/10) | 5.00 s
+[Task 19/25] Current/Best: 5.38/ 16.23 GFLOPS | Progress: (8/10) | 8.88 s
+[Task 19/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (10/10) | 9.76 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 20/25] Current/Best: 7.05/ 18.20 GFLOPS | Progress: (4/10) | 2.40 s
-[Task 20/25] Current/Best: 6.91/ 18.20 GFLOPS | Progress: (8/10) | 4.79 s
-[Task 20/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (10/10) | 5.77 s
+[Task 20/25] Current/Best: 10.63/ 21.94 GFLOPS | Progress: (4/10) | 2.45 s
+[Task 20/25] Current/Best: 15.75/ 21.94 GFLOPS | Progress: (8/10) | 4.92 s
+[Task 20/25] Current/Best: 14.74/ 21.94 GFLOPS | Progress: (10/10) | 5.71 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 21/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/10) | 2.16 s
-[Task 21/25] Current/Best: 14.82/ 20.66 GFLOPS | Progress: (8/10) | 4.08 s
-[Task 21/25] Current/Best: 12.75/ 20.66 GFLOPS | Progress: (10/10) | 5.10 s
+[Task 21/25] Current/Best: 13.16/ 16.45 GFLOPS | Progress: (4/10) | 2.96 s
+[Task 21/25] Current/Best: 17.32/ 17.95 GFLOPS | Progress: (8/10) | 4.64 s
+[Task 21/25] Current/Best: 17.11/ 17.95 GFLOPS | Progress: (10/10) | 6.12 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 22/25] Current/Best: 9.04/ 21.23 GFLOPS | Progress: (4/10) | 3.39 s
-[Task 22/25] Current/Best: 4.79/ 21.23 GFLOPS | Progress: (8/10) | 6.27 s
-[Task 22/25] Current/Best: 18.97/ 21.23 GFLOPS | Progress: (10/10) | 6.87 s Done.
+[Task 22/25] Current/Best: 2.24/ 18.74 GFLOPS | Progress: (4/10) | 2.71 s
+[Task 22/25] Current/Best: 6.44/ 21.19 GFLOPS | Progress: (8/10) | 4.18 s
+[Task 22/25] Current/Best: 11.69/ 21.19 GFLOPS | Progress: (10/10) | 5.00 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 23/25] Current/Best: 13.85/ 20.80 GFLOPS | Progress: (4/10) | 3.13 s
-[Task 23/25] Current/Best: 11.05/ 21.27 GFLOPS | Progress: (8/10) | 7.07 s
-[Task 23/25] Current/Best: 16.97/ 21.27 GFLOPS | Progress: (10/10) | 8.20 s Done.
+[Task 23/25] Current/Best: 9.01/ 17.98 GFLOPS | Progress: (4/10) | 5.55 s
+[Task 23/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/10) | 7.50 s
+[Task 23/25] Current/Best: 12.98/ 19.99 GFLOPS | Progress: (10/10) | 8.53 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
-[Task 24/25] Current/Best: 7.66/ 9.91 GFLOPS | Progress: (4/10) | 12.09 s
-[Task 24/25] Current/Best: 8.23/ 9.91 GFLOPS | Progress: (8/10) | 21.89 s
-[Task 24/25] Current/Best: 3.62/ 9.91 GFLOPS | Progress: (10/10) | 22.96 s
+[Task 24/25] Current/Best: 0.98/ 3.13 GFLOPS | Progress: (4/10) | 13.76 s
+[Task 24/25] Current/Best: 7.28/ 8.51 GFLOPS | Progress: (8/10) | 29.63 s
+[Task 24/25] Current/Best: 4.40/ 8.51 GFLOPS | Progress: (10/10) | 41.41 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
- Done.
-[Task 25/25] Current/Best: 1.55/ 9.00 GFLOPS | Progress: (4/10) | 6.18 s
-[Task 25/25] Current/Best: 5.58/ 9.00 GFLOPS | Progress: (8/10) | 8.67 s
-[Task 25/25] Current/Best: 1.55/ 9.00 GFLOPS | Progress: (10/10) | 10.52 s Done.
+[Task 25/25] Current/Best: 5.54/ 9.14 GFLOPS | Progress: (4/10) | 14.79 s
+[Task 25/25] Current/Best: 2.93/ 9.14 GFLOPS | Progress: (8/10) | 20.12 s
+[Task 25/25] Current/Best: 9.07/ 9.14 GFLOPS | Progress: (10/10) | 47.83 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -836,6 +836,10 @@ model using optimized operators to speed up our computations.</p>
<span class="n">module</span> <span class="o">=</span> <a href="../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="View documentation for tvm.contrib.graph_executor.GraphModule"><span class="n">graph_executor</span><span class="o">.</span><span class="n">GraphModule</span></a><span class="p">(</span><span class="n">lib</span><span class="p">[</span><span class="s2">"default"</span><span class="p">](</span><span class="n">dev</span><span c [...]
</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>Done.
+</pre></div>
+</div>
<p>Verify that the optimized model runs and produces the same results:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dtype</span> <span class="o">=</span> <span class="s2">"float32"</span>
<span class="n">module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">input_name</span><span class="p">,</span> <span class="n">img_data</span><span class="p">)</span>
@@ -851,8 +855,8 @@ model using optimized operators to speed up our computations.</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>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -890,8 +894,8 @@ improvement in comparing the optimized model to the unoptimized model.</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>optimized: {'mean': 441.33022453000194, 'median': 441.502400600001, 'std': 1.0752810855332575}
-unoptimized: {'mean': 493.9763870700006, 'median': 493.863586949999, 'std': 0.6900472424638796}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 430.242951299997, 'median': 430.6716918999882, 'std': 1.105825627012529}
+unoptimized: {'mean': 497.1574179799994, 'median': 496.9821459000002, 'std': 1.1958401633421292}
</pre></div>
</div>
</div>
@@ -905,7 +909,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 36.976 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 43.631 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_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">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 7dff67981..27b7e1350 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -496,7 +496,7 @@ device and returns the measured cost. Network overhead is excluded.</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>1.27e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.263e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 86fe10c21..eaba23754 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -461,7 +461,7 @@ we can schedule the following series of operations ending with <code class="code
</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>[stage(a, placeholder(a, 0xf1d4070)), stage(b, placeholder(b, 0x1ad25990)), 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=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xd6c4b60)), stage(b, placeholder(b, 0x22295ea0)), 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=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index eefe2d517..21802c228 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -300,20 +300,20 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:15.323</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>11:08.218</strong> total execution time for <strong>tutorial</strong> files:</p>
<ul class="simple">
-<li><p><strong>06:36.976</strong>: <a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:59.670</strong>: <a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></li>
-<li><p><strong>00:47.697</strong>: <a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></li>
-<li><p><strong>00:26.955</strong>: <a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></li>
-<li><p><strong>00:21.848</strong>: <a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></li>
-<li><p><strong>00:01.092</strong>: <a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></li>
-<li><p><strong>00:00.720</strong>: <a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></li>
-<li><p><strong>00:00.216</strong>: <a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></li>
-<li><p><strong>00:00.046</strong>: <a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></li>
-<li><p><strong>00:00.036</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
-<li><p><strong>00:00.034</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
-<li><p><strong>00:00.034</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
+<li><p><strong>07:43.631</strong>: <a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></li>
+<li><p><strong>01:24.223</strong>: <a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></li>
+<li><p><strong>00:59.421</strong>: <a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></li>
+<li><p><strong>00:32.385</strong>: <a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></li>
+<li><p><strong>00:26.316</strong>: <a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></li>
+<li><p><strong>00:01.135</strong>: <a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></li>
+<li><p><strong>00:00.724</strong>: <a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></li>
+<li><p><strong>00:00.201</strong>: <a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></li>
+<li><p><strong>00:00.049</strong>: <a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></li>
+<li><p><strong>00:00.045</strong>: <a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></li>
+<li><p><strong>00:00.044</strong>: <a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></li>
+<li><p><strong>00:00.044</strong>: <a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 233185190..e215a8dc2 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -507,8 +507,8 @@ helper function to run a profile of the TVM generated code.</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>Numpy running time: 0.000008
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000009
+naive: 0.000006
</pre></div>
</div>
</div>
@@ -559,7 +559,7 @@ compile and run this new schedule with the parallel operation applied:</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>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000006
</pre></div>
</div>
</div>
@@ -633,10 +633,10 @@ factor to be the number of threads on your CPU.</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>Operator Timing Performance
- numpy 7.902440000862043e-06 1.0
- naive 6.5595e-06 0.8300600826180841
-parallel 6.8814e-06 0.8707943368439796
- vector 2.47215e-05 3.1283375764071906
+ numpy 9.080570000605803e-06 1.0
+ naive 5.8536999999999995e-06 0.6446401491987259
+parallel 6.1858999999999995e-06 0.6812237557319983
+ vector 2.4592800000000003e-05 2.708288135916502
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -954,7 +954,7 @@ matrix multiplication.</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>Numpy running time: 0.018726
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018744
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -996,7 +996,7 @@ optimizations.</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>none: 3.304589
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.260776
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1063,7 +1063,7 @@ schedule.</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>blocking: 0.307722
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.312385
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1124,7 +1124,7 @@ already cache friendly from our previous optimizations.</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>vectorization: 0.345361
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.349270
@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], []),
@@ -1180,7 +1180,7 @@ 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>loop permutation: 0.118181
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.123660
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1257,7 +1257,7 @@ optimized schedule.</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>array packing: 0.109134
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109355
@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], []),
@@ -1332,7 +1332,7 @@ to `C</cite> 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>block caching: 0.110648
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111397
@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], []),
@@ -1400,7 +1400,7 @@ of thread-level parallelization.</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>parallelization: 0.144247
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145172
@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], []),
@@ -1463,13 +1463,13 @@ working, we can compare the results.</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> Operator Timing Performance
- none 3.3045888673 1.0
- blocking 0.30772193059999997 0.09311958096966623
- vectorization 0.34536051590000005 0.10450937462068477
-loop permutation 0.11818090830000001 0.03576266611239879
- array packing 0.10913402759999999 0.03302499402570688
- block caching 0.11064754350000001 0.03348299832239165
- parallelization 0.14424729139999998 0.043650601388685484
+ none 3.2607762086000003 1.0
+ blocking 0.31238460989999994 0.0958006897486905
+ vectorization 0.3492703231 0.10711263231706344
+loop permutation 0.1236603495 0.037923592908294994
+ array packing 0.10935490769999998 0.03353646515562349
+ block caching 0.11139655620000002 0.03416258862113927
+ parallelization 0.1451716146 0.0445205697395372
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a