You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/06/17 01:24:13 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@333994d45fab729dfebcfeb2f1f9c211818b693e)
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 2a87db6f1 deploying docs (apache/tvm@333994d45fab729dfebcfeb2f1f9c211818b693e)
2a87db6f1 is described below
commit 2a87db6f13e30a730dcb41352eb34a00f70be714
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 17 01:24:07 2022 +0000
deploying docs (apache/tvm@333994d45fab729dfebcfeb2f1f9c211818b693e)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 -
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 270 ++++++++++++---------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 76 ++++--
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 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 | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 ++---
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 ++--
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 70 +++---
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 21 +-
docs/how_to/compile_models/from_tensorflow.html | 1 -
docs/how_to/compile_models/sg_execution_times.html | 30 +--
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 30 +--
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +--
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 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 | 270 ++++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 76 ++++--
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +--
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +--
docs/reference/api/typedoc/classes/memory.html | 34 +--
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +--
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++++-----
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++++++++++----------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +--
docs/tutorial/tensor_expr_get_started.html | 41 ++--
121 files changed, 1272 insertions(+), 1115 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 826b8daa6..5af6b0ec2 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip298ce64c-f7e0-4a08-88b6-fb84f5f0557e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa9698854-8cf5-4db7-b6de-141f43b40404 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 a8dddc1ca..053519a04 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:10, 88.6kB/s]
0%| | 48.0k/41.5M [00:00<05:09, 140kB/s]
0%| | 96.0k/41.5M [00:00<03:40, 197kB/s]
0%| | 192k/41.5M [00:00<02:12, 328kB/s]
1%| | 376k/41.5M [00:00<01:14, 575kB/s]
2%|1 | 704k/41.5M [00:01<00:43, 994kB/s]
3%|3 | 1.39M/41.5M [00:01<00:21, 1.97MB/s]
7%|6 | 2.71M/41.5M [00:01<00:10, 3.71MB/s]
10%|# | 4.23M/41.5M [00:01<00:07, 5.23MB/s]
14%|#3 | 5.76M/41.5M [00:01<00:05, 6.27MB/s]
18%|#7 | 7.29M/41.5M [00:02<00:05, 6.99MB/s]
21%|##1 | 8.80M/41.5M [00:02<00:04, 7.47MB/s]
25%|##4 | 10.3M/41.5M [00:02<00:04, 7.79MB/s]
29%|##8 | 11.8M/41.5M [00:02<00:03, 8.03MB/s]
32%|###2 | 13.4M/41.5M [00:02<00:03, 8.21MB/s]
36%|###5 | 14.9M/41.5M [00:02<00:03, 8.33MB/s]
40%|###9 | 16.4M/41.5M [00:03<00
:03, 8.41MB/s]
43%|####3 | 17.9M/41.5M [00:03<00:02, 8.46MB/s]
47%|####6 | 19.5M/41.5M [00:03<00:02, 9.55MB/s]
51%|##### | 21.0M/41.5M [00:03<00:02, 9.24MB/s]
54%|#####4 | 22.5M/41.5M [00:03<00:01, 10.1MB/s]
57%|#####6 | 23.5M/41.5M [00:03<00:02, 9.41MB/s]
59%|#####8 | 24.4M/41.5M [00:04<00:02, 8.04MB/s]
62%|######1 | 25.6M/41.5M [00:04<00:02, 7.51MB/s]
65%|######5 | 27.1M/41.5M [00:04<00:01, 7.86MB/s]
69%|######8 | 28.6M/41.5M [00:04<00:01, 8.09MB/s]
73%|#######2 | 30.1M/41.5M [00:04<00:01, 8.25MB/s]
76%|#######6 | 31.6M/41.5M [00:05<00:01, 8.34MB/s]
80%|#######9 | 33.2M/41.5M [00:05<00:01, 8.42MB/s]
84%|########3 | 34.7M/41.5M [00:05<00:00, 8.47MB/s]
87%|########7 | 36.2M/41.5M [00:05<00:00, 8.52MB/s]
91%|######### | 37.7M/41.5M [00:05<00:00, 8.54MB/s]
95%|#########4| 39.3M/41.5M [00:05<00:00, 8.54MB/s]
98%|#########8| 40.8M/41.5M [00:06<00:00, 8.56MB/s]
100%|####
######| 41.5M/41.5M [00:06<00:00, 7.08MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:33, 95.9kB/s]
0%| | 40.0k/41.5M [00:00<05:51, 124kB/s]
0%| | 96.0k/41.5M [00:00<03:17, 220kB/s]
0%| | 160k/41.5M [00:00<02:32, 283kB/s]
1%| | 280k/41.5M [00:00<01:38, 439kB/s]
1%|1 | 576k/41.5M [00:01<00:48, 890kB/s]
3%|2 | 1.13M/41.5M [00:01<00:24, 1.74MB/s]
5%|5 | 2.27M/41.5M [00:01<00:12, 3.40MB/s]
9%|9 | 3.74M/41.5M [00:01<00:07, 5.14MB/s]
13%|#2 | 5.20M/41.5M [00:01<00:06, 6.30MB/s]
16%|#6 | 6.67M/41.5M [00:01<00:05, 7.11MB/s]
20%|#9 | 8.14M/41.5M [00:02<00:04, 7.67MB/s]
23%|##3 | 9.61M/41.5M [00:02<00:04, 8.06MB/s]
27%|##6 | 11.1M/41.5M [00:02<00:03, 8.33MB/s]
30%|### | 12.5M/41.5M [00:02<00:03, 8.52MB/s]
34%|###3 | 14.0M/41.5M [00:02<00:03, 8.65MB/s]
37%|###7 | 15.5M/41.5M [00:02<00
:03, 8.76MB/s]
41%|#### | 17.0M/41.5M [00:03<00:02, 8.81MB/s]
44%|####4 | 18.4M/41.5M [00:03<00:02, 8.86MB/s]
48%|####7 | 19.9M/41.5M [00:03<00:02, 8.88MB/s]
51%|#####1 | 21.4M/41.5M [00:03<00:02, 8.91MB/s]
55%|#####5 | 22.8M/41.5M [00:03<00:02, 8.92MB/s]
59%|#####8 | 24.3M/41.5M [00:03<00:02, 8.93MB/s]
62%|######2 | 25.8M/41.5M [00:04<00:01, 8.95MB/s]
66%|######5 | 27.2M/41.5M [00:04<00:01, 8.95MB/s]
69%|######9 | 28.7M/41.5M [00:04<00:01, 8.95MB/s]
73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.94MB/s]
76%|#######6 | 31.6M/41.5M [00:04<00:01, 8.93MB/s]
80%|#######9 | 33.1M/41.5M [00:04<00:00, 8.94MB/s]
83%|########3 | 34.6M/41.5M [00:05<00:00, 8.95MB/s]
87%|########6 | 36.0M/41.5M [00:05<00:00, 8.95MB/s]
90%|######### | 37.5M/41.5M [00:05<00:00, 8.95MB/s]
94%|#########3| 39.0M/41.5M [00:05<00:00, 8.93MB/s]
97%|#########7| 40.4M/41.5M [00:05<00:00, 8.93MB/s]
100%|####
######| 41.5M/41.5M [00:05<00:00, 7.43MB/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 d2e36ed75..be0a03a10 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.065 seconds)
+ **Total running time of the script:** ( 1 minutes 6.650 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 768e67df8..091a95c34 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
9%|8 | 4.00M/44.7M [00:00<00:01, 34.6MB/s]
16%|#6 | 7.30M/44.7M [00:00<00:01, 27.7MB/s]
24%|##3 | 10.6M/44.7M [00:00<00:01, 30.0MB/s]
30%|### | 13.5M/44.7M [00:00<00:01, 23.3MB/s]
37%|###6 | 16.4M/44.7M [00:00<00:01, 25.3MB/s]
42%|####2 | 19.0M/44.7M [00:00<00:01, 20.8MB/s]
47%|####7 | 21.2M/44.7M [00:00<00:01, 20.1MB/s]
54%|#####4 | 24.3M/44.7M [00:01<00:00, 23.1MB/s]
62%|######2 | 27.9M/44.7M [00:01<00:00, 26.9MB/s]
69%|######9 | 31.0M/44.7M [00:01<00:00, 26.5MB/s]
75%|#######5 | 33.7M/44.7M [00:01<00:00, 22.4MB/s]
81%|######## | 36.0M/44.7M [00:01<00:00, 17.3MB/s]
85%|########4 | 37.9M/44.7M [00:01<00:00, 13.1MB/s]
88%|########8 | 39.4M/44.7M [00:02<00:00, 13.1MB/s]
92%|#########2| 41.3M/44.7M [00:02<00:00, 14.2MB/s]
96%|#########5| 42.8M/44.7M [00:02<00:00, 11.9MB/s]
99%|#########8| 44.1M/44.7M [00
:02<00:00, 10.1MB/s]
100%|##########| 44.7M/44.7M [00:02<00:00, 17.6MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
40%|#### | 17.9M/44.7M [00:00<00:00, 188MB/s]
94%|#########4| 42.1M/44.7M [00:00<00:00, 227MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 222MB/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 e26445ae8..e6f3342e0 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -420,11 +420,6 @@ Run the corresponding model on tensorflow
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 3.326 seconds)
-
-
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
.. only:: html
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 4ae30cf5b..4f80ae571 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:29.900** total execution time for **how_to_compile_models** files:
+**05:27.984** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:07.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:06.650 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.310 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:58.560 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:55.912 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.582 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:36.198 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.455 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.878 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.838 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.759 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:20.745 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.863 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.545 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.286 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.673 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.314 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 7c917aed1..49144f69b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -440,7 +440,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2469 16.2381 16.2843 16.2137 0.0230
+ 15.3654 15.3765 15.5716 15.2326 0.1008
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 850264c37..d4c9ea568 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.71M/170M [00:00<00:04, 37.4MB/s]
8%|7 | 13.5M/170M [00:00<00:02, 74.8MB/s]
14%|#3 | 23.1M/170M [00:00<00:01, 86.6MB/s]
20%|#9 | 33.8M/170M [00:00<00:01, 96.9MB/s]
27%|##7 | 46.3M/170M [00:00<00:01, 109MB/s]
34%|###4 | 57.8M/170M [00:00<00:01, 113MB/s]
41%|#### | 69.6M/170M [00:00<00:00, 116MB/s]
48%|####7 | 81.4M/170M [00:00<00:00, 118MB/s]
55%|#####4 | 93.2M/170M [00:00<00:00, 120MB/s]
62%|######1 | 105M/170M [00:01<00:00, 121MB/s]
69%|######8 | 117M/170M [00:01<00:00, 122MB/s]
76%|#######5 | 128M/170M [00:01<00:00, 113MB/s]
82%|########2 | 140M/170M [00:01<00:00, 116MB/s]
89%|########9 | 152M/170M [00:01<00:00, 118MB/s]
96%|#########6| 163M/170M [00:01<00:00, 119MB/s]
100%|##########| 170M/170M [00:01<00:00, 112MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
6%|5 | 9.44M/170M [00:00<00:01, 98.9MB/s]
15%|#5 | 25.7M/170M [00:00<00:01, 141MB/s]
24%|##3 | 40.4M/170M [00:00<00:00, 144MB/s]
33%|###2 | 56.0M/170M [00:00<00:00, 152MB/s]
42%|####2 | 71.6M/170M [00:00<00:00, 155MB/s]
51%|##### | 86.4M/170M [00:00<00:00, 153MB/s]
60%|###### | 103M/170M [00:00<00:00, 158MB/s]
70%|######9 | 119M/170M [00:00<00:00, 161MB/s]
79%|#######9 | 135M/170M [00:00<00:00, 164MB/s]
89%|########8 | 151M/170M [00:01<00:00, 165MB/s]
98%|#########8| 167M/170M [00:01<00:00, 166MB/s]
100%|##########| 170M/170M [00:01<00:00, 158MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.674 seconds)
+ **Total running time of the script:** ( 2 minutes 46.388 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 e0e92754a..9e9e538a5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 169MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/s]
@@ -399,7 +399,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.7523 90.4243 98.8380 90.2408 1.1992
+ 89.0394 88.9430 90.4560 88.7244 0.2790
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.706 seconds)
+ **Total running time of the script:** ( 1 minutes 4.396 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 7efbc823c..ecd4061a6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -426,7 +426,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.5697 120.5087 123.3701 119.5512 0.4639
+ 117.0881 117.0740 123.2218 115.0804 0.8260
@@ -463,7 +463,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 3.954 seconds)
+ **Total running time of the script:** ( 1 minutes 56.761 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 d852a603d..a0e1a160b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.379 seconds)
+ **Total running time of the script:** ( 1 minutes 13.111 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 dffa6be82..b6b632b64 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -157,7 +157,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5939/132723 [00:00<00:02, 59368.82KB/s]
11%|# | 14438/132723 [00:00<00:01, 74432.40KB/s]
17%|#7 | 22874/132723 [00:00<00:01, 78957.48KB/s]
24%|##3 | 31336/132723 [00:00<00:01, 81189.81KB/s]
30%|### | 39817/132723 [00:00<00:01, 82493.75KB/s]
36%|###6 | 48290/132723 [00:00<00:01, 83252.15KB/s]
43%|####2 | 56782/132723 [00:00<00:00, 83795.64KB/s]
49%|####9 | 65272/132723 [00:00<00:00, 84145.37KB/s]
56%|#####5 | 73823/132723 [00:00<00:00, 84570.40KB/s]
62%|######2 | 82345/132723 [00:01<00:00, 84765.72KB/s]
68%|######8 | 90833/132723 [00:01<00:00, 84790.88KB/s]
75%|#######4 | 99313/132723 [00:01<00:00, 84671.85KB/s]
81%|########1 | 107811/132723 [00:01<00:00, 84761.88KB/s]
88%|########7 | 116288/132723 [00:01<00:00, 79635.75KB/s]
94%|#########4| 124840/132723 [00:01<00:00, 81327.68KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82134.24KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 4682/132723 [00:00<00:02, 46815.13KB/s]
10%|9 | 12748/132723 [00:00<00:01, 66719.23KB/s]
16%|#5 | 20983/132723 [00:00<00:01, 73855.09KB/s]
22%|##2 | 29375/132723 [00:00<00:01, 77827.37KB/s]
28%|##8 | 37613/132723 [00:00<00:01, 79465.02KB/s]
34%|###4 | 45699/132723 [00:00<00:01, 79938.21KB/s]
40%|#### | 53693/132723 [00:00<00:00, 79906.37KB/s]
47%|####6 | 61796/132723 [00:00<00:00, 80238.85KB/s]
53%|#####2 | 69820/132723 [00:00<00:00, 80194.96KB/s]
59%|#####8 | 77840/132723 [00:01<00:00, 80029.77KB/s]
65%|######4 | 85865/132723 [00:01<00:00, 80091.70KB/s]
71%|####### | 94108/132723 [00:01<00:00, 80799.15KB/s]
77%|#######7 | 102489/132723 [00:01<00:00, 81709.07KB/s]
83%|########3 | 110747/132723 [00:01<00:00, 81970.68KB/s]
90%|########9 | 118945/132723 [00:01<00:00, 81286.80KB/s]
96%|########
#5| 127188/132723 [00:01<00:00, 81626.11KB/s]
100%|##########| 132723/132723 [00:01<00:00, 79408.41KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 23.126 seconds)
+ **Total running time of the script:** ( 2 minutes 13.281 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 f56d34b18..11592699b 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**10:46.061** total execution time for **how_to_deploy_models** files:
+**10:03.712** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:46.388 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:23.126 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:13.281 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:03.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:56.761 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:19.379 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:13.111 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.706 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.396 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.590 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:27.920 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.626 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.850 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 40298fd28..25c75fd44 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9c2605ab-614a-4f26-a81e-5b6c941f2c9a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5fe841da-889f-4fc2-8a7f-b8bb1fd68b1f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -577,7 +577,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm 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 a0b4d6eb7..b4a450f12 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:41.121** total execution time for **how_to_extend_tvm** files:
+**00:38.134** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:35.143 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.100 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.956 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.885 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.006 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 848a2387c..7532da96d 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -215,10 +215,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7161us [7161us] (46.03%; 46.03%)
- FoldScaleAxis: 8396us [7us] (53.97%; 53.97%)
- FoldConstant: 8389us [1642us] (53.92%; 99.91%)
- InferType: 6747us [6747us] (43.37%; 80.42%)
+ InferType: 6415us [6415us] (45.46%; 45.46%)
+ FoldScaleAxis: 7695us [5us] (54.54%; 54.54%)
+ FoldConstant: 7690us [1611us] (54.50%; 99.93%)
+ InferType: 6079us [6079us] (43.08%; 79.06%)
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6693us [6693us] (44.98%; 44.98%)
- FoldScaleAxis: 8189us [5us] (55.02%; 55.02%)
- FoldConstant: 8183us [1691us] (54.99%; 99.93%)
- InferType: 6492us [6492us] (43.63%; 79.34%)
+ InferType: 6085us [6085us] (44.46%; 44.46%)
+ FoldScaleAxis: 7603us [4us] (55.54%; 55.54%)
+ FoldConstant: 7599us [1604us] (55.51%; 99.94%)
+ InferType: 5994us [5994us] (43.79%; 78.88%)
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 ef67da034..a5e576401 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -327,7 +327,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.181943 ms
+ Convolution: 54.202330 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 4e76b2c86..6e9dfb698 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -658,7 +658,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 8.551538 ms
+ conv2d with tensor core: 8.556827 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 f8f047dcb..7fa9a9eba 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019226
- Baseline: 3.265900
+ Numpy running time: 0.017729
+ Baseline: 3.392386
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.313961
+ Opt1: 0.296617
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.349103
+ Opt2: 0.335684
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120882
+ Opt3: 0.112770
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111118
+ Opt4: 0.106931
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111351
+ Opt5: 0.109232
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145423
+ Opt6: 0.142027
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 dedad1243..ac3378310 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.553** total execution time for **how_to_optimize_operators** files:
+**00:33.922** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.693 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.284 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.228 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.001 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 71581ac35..6c179ba91 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:14.552** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:07.575** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:33.971 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:33.706 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:18.381 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:41.676 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.454 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.208 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.664 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.151 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index df030a9db..14d85597a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,12 +239,12 @@ 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" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -254,68 +254,83 @@ cooperative fetching, unrolling and operator fusion.
for (rc.outer.outer: int32, 0, 32) {
let cse_var_1: int32 = (rc.outer.outer*784)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 336), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 93), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 124), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 155), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 672), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 186), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 217), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 248), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1120), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 310), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 17), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 341), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ if @tir.likely((threadIdx.x_1 < 400), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 86), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 24) {
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- let cse_var_2: int32 = floordiv(ax0.ax1.fused.ax2.fused.ax3.fused.inner.s, 3)
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[((threadIdx.x_2*24) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 6)*8) + cse_var_2), 3)*9)) + (floormod(((threadIdx.x_2*2) + cse_var_2), 3)*3)) + floormod(ax0.ax1.fused.ax2.fused.ax3.fused.inner.s, 3))]
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*9)] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9))]
+ kernel.shared_1[((threadIdx.x_2*9) + 1)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 1)]
+ kernel.shared_1[((threadIdx.x_2*9) + 2)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 2)]
+ kernel.shared_1[((threadIdx.x_2*9) + 3)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 3)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 4)]
+ kernel.shared_1[((threadIdx.x_2*9) + 5)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 5)]
+ kernel.shared_1[((threadIdx.x_2*9) + 6)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 6)]
+ kernel.shared_1[((threadIdx.x_2*9) + 7)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 7)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 8)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ kernel.shared_1[((threadIdx.x_2*9) + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129024)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4033)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129025)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4034)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129026)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4035)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129027)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4036)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129028)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4037)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129029)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4038)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129030)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4039)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129031)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4040)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129032)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*9) + 8064)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258048)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8065)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258049)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8066)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258050)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8067)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258051)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8068)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258052)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8069)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258053)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8070)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258054)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8071)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258055)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8072)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258056)]
}
- for (rc.outer.inner: int32, 0, 8) {
+ for (rc.outer.inner: int32, 0, 2) {
for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ for (xx.outer.inner: int32, 0, 7) {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 65)]))
}
}
}
}
}
- compute[(((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
@@ -369,7 +384,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.229 ms
+ Execution time of this operator: 0.363 ms
@@ -419,34 +434,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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)
@@ -464,16 +479,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=448)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=448)
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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -491,10 +506,10 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(448) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
__shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -505,53 +520,74 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 400) {
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 24; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 24) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) % 3) * 3)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s % 3))];
- }
+ kernel_shared[(((int)threadIdx.x) * 9)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9))];
+ kernel_shared[((((int)threadIdx.x) * 9) + 1)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 2)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 3)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 3)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 4)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 5)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 5)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 6)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 6)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 7)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 7)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 8)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129024)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4033)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129025)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4034)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129026)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4035)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129027)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4036)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129028)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4037)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129029)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4038)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129030)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4039)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129031)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4040)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129032)];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((((int)threadIdx.x) * 9) + 8064)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258048)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8065)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258049)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8066)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258050)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8067)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258051)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8068)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258052)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8069)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258053)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8070)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258054)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8071)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258055)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8072)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258056)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3))]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 65)]));
}
}
}
}
- compute[(((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
@@ -612,7 +648,7 @@ 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 33.971 seconds)
+ **Total running time of the script:** ( 2 minutes 33.706 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 7718895fd..559383090 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -646,7 +646,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.0408 10.0276 10.0759 10.0188 0.0251
+ 9.8250 9.8258 9.8729 9.7764 0.0394
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 6d439d178..7990c47df 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -665,7 +665,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.1155 758.7847 760.1542 758.4076 0.7504
+ 746.6928 746.6570 747.0672 746.3541 0.2922
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.243 seconds)
+ **Total running time of the script:** ( 1 minutes 18.381 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 2f6ffc97b..8b5dac1ea 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -396,30 +396,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_4: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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))
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -475,7 +523,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.494 ms
+ Execution time of this operator: 1.845 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 1354f15b1..22ccc30ff 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
=================
-**00:43.075** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.204** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.172 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 0c8064f56..32a1f739d 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -879,8 +879,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.33/42.33 result: MeasureResult(costs=(0.00546865052631579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6242687702178955, timestamp=1655424491.0523908) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.32/110.32 result: MeasureResult(costs=(0.0020985360625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8206052780151367, timestamp=1655426847.6840272) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,7 +1003,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,7 +1126,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,7 +1249,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1267,7 +1267,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1390,7 +1390,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1513,7 +1513,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1636,7 +1636,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1759,7 +1759,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1882,7 +1882,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2005,7 +2005,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2128,7 +2128,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2251,7 +2251,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f5036f29fa2
+ 12: 0x00007f88f58acfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 142.95/142.95 result: MeasureResult(costs=(0.0016194267096774195,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1618273258209229, timestamp=1655424517.3447928) [('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: 144.24/144.24 result: MeasureResult(costs=(0.00160498168,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3826005458831787, timestamp=1655426873.9520867) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2461,7 +2461,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
- Time cost of this operator: 0.001978
+ Time cost of this operator: 0.002007
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 2dcadfb6b..75d376d4f 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -328,10 +328,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.7 98.745 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.964 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.928 0.291 (1, 1, 10, 10, 3) 1 1
- Total_time - 318.701 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.733 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.088 0.981 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.286 (1, 1, 10, 10, 3) 1 1
+ Total_time - 314.889 - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 250.1 98.828 (1, 1, 10, 10, 6) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.049 0.81 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.917 0.362 (1, 1, 10, 10, 3) 1 1
- Total_time - 253.066 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 77.8 96.637 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.777 2.207 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 1.156 (1, 1, 10, 10, 3) 1 1
+ Total_time - 80.508 - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 1c386d446..0e740e4c1 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -224,7 +224,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpqv6kzq4w/images/random'
+ '/tmp/tmp_nl5au9x/images/random'
@@ -324,8 +324,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpqv6kzq4w/images/target contains 8144 images
- /tmp/tmpqv6kzq4w/images/random contains 5000 images
+ /tmp/tmp_nl5au9x/images/target contains 8144 images
+ /tmp/tmp_nl5au9x/images/random contains 5000 images
@@ -500,13 +500,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2526 - accuracy: 0.9173 - val_loss: 0.1534 - val_accuracy: 0.9547
+ 328/328 - 54s - loss: 0.2286 - accuracy: 0.9204 - val_loss: 0.1375 - val_accuracy: 0.9547
Epoch 2/3
- 328/328 - 53s - loss: 0.1045 - accuracy: 0.9606 - val_loss: 0.1262 - val_accuracy: 0.9626
+ 328/328 - 51s - loss: 0.1002 - accuracy: 0.9610 - val_loss: 0.1194 - val_accuracy: 0.9634
Epoch 3/3
- 328/328 - 53s - loss: 0.0715 - accuracy: 0.9733 - val_loss: 0.1529 - val_accuracy: 0.9524
+ 328/328 - 51s - loss: 0.0656 - accuracy: 0.9746 - val_loss: 0.1162 - val_accuracy: 0.9634
- <keras.callbacks.History object at 0x7fb7692f0a90>
+ <keras.callbacks.History object at 0x7f8dd561b910>
@@ -863,7 +863,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 24.134 seconds)
+ **Total running time of the script:** ( 4 minutes 32.727 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 129a08b6c..490ee6b48 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**06:11.061** total execution time for **how_to_work_with_microtvm** files:
+**05:17.329** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:24.134 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:32.727 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.266 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.211 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.391 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 8d631c84b..80c590cb6 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:12.405** total execution time for **how_to_work_with_relay** files:
+**00:11.243** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.621 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.819 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.778 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.419 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index cf6683fbc..90e85abc3 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fb6e61df680>
+ <function my_cuda_math_rule at 0x7f8d3c341ef0>
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 ae6d558a5..b89f6bdc9 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.161** total execution time for **how_to_work_with_schedules** files:
+**00:04.001** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.923 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.861 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.953 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.536 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.519 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.522 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.501 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.096 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.012 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index de1901de8..f7fc7b882 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpw7n0cedl/input0.cc'\nsource_filename = \"/tmp/tmpw7n0cedl/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/tmpv3z4tcoe/input0.cc'\nsource_filename = \"/tmp/tmpv3z4tcoe/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 e629a5218..b394d3047 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:20.979** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:19.879** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.972 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:19.873 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 67e557387..467cbab48 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 24.11s!
+ resnet18_v1 inference graph built in 21.33s!
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 924f7bbd4..002b27de8 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.17s!
+ yolov3-tiny inference graph built in 15.18s!
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 aec5d8b7a..f771f8413 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:32.740** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.025** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.265 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:46.767 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.475 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:41.259 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 15b894983..ec34b3424 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.211** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.185** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.820 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.795 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.390 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index b97ef781b..8a81053ae 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.731** total execution time for **topic_vta_tutorials** files:
+**00:00.709** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.373 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.349 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.337 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index c3c3d7db9..5ad0964ed 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -208,12 +208,12 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
*E
+
.. GENERATED FROM PYTHON SOURCE LINES 134-140
Inspecting the Optimized Schedule
@@ -334,7 +334,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.420 ms
+ Execution time of this operator: 91.876 ms
@@ -434,7 +434,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ .T
@@ -450,6 +450,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 11.720 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index a14ee7d21..a95716b7c 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.67/9.67 result: MeasureResult(costs=(0.0277716648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.587357759475708, timestamp=1655423338.7361605) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.69/9.67 result: MeasureResult(costs=(0.09961413659999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.75498366355896, timestamp=1655423340.495578) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022760171399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5715122222900391, timestamp=1655423341.5399616) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.58/11.79 result: MeasureResult(costs=(0.1695307248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.836313009262085, timestamp=1655423344.927747) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.64/11.79 result: MeasureResult(costs=(0.0738259992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3164796829223633, timestamp=1655423346.3689651) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.70/11.79 result: MeasureResult(costs=(0.1575823816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.687743902206421, timestamp=1655423349.0927753) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.85/11.79 result: MeasureResult(costs=(0.3175632158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.194802522659302, timestamp=1655423354.8374522) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.24/11.79 result: MeasureResult(costs=(0.0262087616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5642800331115723, timestamp=1655423355.4232423) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.64/11.79 result: MeasureResult(costs=(0.16367640719999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.717639923095703, timestamp=1655423358.2610846) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.17/11.79 result: MeasureResult(costs=(0.12369548859999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.083334445953369, timestamp=1655423360.4037995) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.98/10.98 result: MeasureResult(costs=(0.024449573199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.521331787109375, timestamp=1655425724.245574) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.96/10.98 result: MeasureResult(costs=(0.0908326226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5962371826171875, timestamp=1655425726.342798) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 12.01/12.01 result: MeasureResult(costs=(0.022354579000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5843491554260254, timestamp=1655425726.9030123) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.87/12.01 result: MeasureResult(costs=(0.1435340632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4219417572021484, timestamp=1655425729.8526187) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.75/12.01 result: MeasureResult(costs=(0.0715465934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2833199501037598, timestamp=1655425731.267437) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.78/12.01 result: MeasureResult(costs=(0.1506930936,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.524484872817993, timestamp=1655425734.3145797) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/12.01 result: MeasureResult(costs=(0.3080363614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.03804612159729, timestamp=1655425739.4033012) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.90/12.01 result: MeasureResult(costs=(0.0246313948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5323412418365479, timestamp=1655425739.9579465) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.94/12.01 result: MeasureResult(costs=(0.13847948240000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3109400272369385, timestamp=1655425742.3885188) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.81/12.01 result: MeasureResult(costs=(0.095644071,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.629319190979004, timestamp=1655425744.0790825) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 53b660e9c..560f20602 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.3567338799112, 'median': 496.84443964979437, 'std': 1.5960987762688807}
+ {'mean': 489.15848393004126, 'median': 488.8971324000522, 'std': 1.4240269798007845}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (4/20) | 5.67 s
[Task 1/25] Current/Best: 6.17/ 17.43 GFLOPS | Progress: (8/20) | 9.06 s
[Task 1/25] Current/Best: 11.51/ 22.64 GFLOPS | Progress: (12/20) | 11.55 s
[Task 1/25] Current/Best: 16.78/ 22.74 GFLOPS | Progress: (16/20) | 13.23 s
[Task 1/25] Current/Best: 11.54/ 23.75 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.19/ 12.85 GFLOPS | Progress: (4/20) | 3.73 s
[Task 2/25] Current/Best: 14.29/ 18.63 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (12/20) | 6.34 s
[Task 2/25] Current/Best: 12.25/ 20.99 GFLOPS | Progress: (16/20) | 7.60 s
[Task 2/25] Current/Best: 19.07/ 20.99 GFLOPS | Progress: (20/20) | 9.22 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.79 s
[Task 3/25] Current/Best: 15.59/ 16.92 GFLOPS | Progress: (8/20) | 7.70 s
[Task 3/25] Current/Best: 14.87/ 16.92 GFLOPS | Progress: (12/20) | 9.40 s
[Task 3/25] Current/Best: 7.21/ 23.83 GFLOPS | Progress: (16/20) | 11.29 s
[Task 3/25] Current/Best: 12.09/ 23.83 GFLOPS | Progress: (20/20) | 15.87 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.59/ 20.43 GFLOPS | Progress: (4/20) | 2.33 s
[Task 4/25] Current/Best: 6.86/ 20.43 GFLOPS | Progress: (8/20) | 6.98 s
[Task 4/25] Current/Best: 22.07/ 22.07 GFLOPS | Progress: (12/20) | 11.90 s
[Task 4/25] Current/Best: 16.99/ 22.07 GFLOPS | Progress: (16/20) | 14.32 s
[Task 4/25] Current/Best: 12.69/ 22.07 GFLOPS | Progress: (20/20) | 16.42 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.71/ 10.37 GFLOPS | Progress: (4/20) | 2.52 s
[Task 5/25] Current/Best: 11.75/ 12.74 GFLOPS | Progress: (8/20) | 4.59 s
[Task 5/25] Current/Best: 11.72/ 18.16 GFLOPS | Progress: (12/20) | 7.77 s
[Task 5/25] Current/Best: 11.86/ 22.89 GFLOPS | Progress: (16/20) | 9.18 s
[Task 5/25] Current/Best: 12.06/ 22.89 GFLOPS | Progress: (20/20) | 11.05 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.26/ 20.72 GFLOPS | Progress: (4/20) | 4.05 s
[Task 6/25] Current/Best: 18.86/ 20.72 GFLOPS | Progress: (8/20) | 5.83 s
[Task 6/25] Current/Best: 13.28/ 20.72 GFLOPS | Progress: (12/20) | 7.77 s
[Task 6/25] Current/Best: 19.76/ 20.72 GFLOPS | Progress: (16/20) | 10.03 s
[Task 6/25] Current/Best: 3.75/ 20.72 GFLOPS | Progress: (20/20) | 12.58 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.25/ 12.72 GFLOPS | Progress: (4/20) | 3.54 s
[Task 7/25] Current/Best: 19.93/ 21.09 GFLOPS | Progress: (8/20) | 5.03 s
[Task 7/25] Current/Best: 16.09/ 21.09 GFLOPS | Progress: (12/20) | 6.95 s
[Task 7/25] Current/Best: 12.23/ 21.09 GFLOPS | Progress: (16/20) | 9.00 s
[Task 7/25] Current/Best: 6.45/ 21.69 GFLOPS | Progress: (20/20) | 11.46 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.25/ 14.57 GFLOPS | Progress: (4/20) | 2.86 s
[Task 8/25] Current/Best: 9.46/ 14.57 GFLOPS | Progress: (8/20) | 8.00 s
[Task 8/25] Current/Best: 13.39/ 14.57 GFLOPS | Progress: (12/20) | 14.41 s
[Task 8/25] Current/Best: 18.59/ 18.59 GFLOPS | Progress: (16/20) | 16.48 s
[Task 8/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (20/20) | 23.49 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.78 GFLOPS | Progress: (4/20) | 11.89 s
[Task 9/25] Current/Best: 23.57/ 23.57 GFLOPS | Progress: (8/20) | 13.64 s
[Task 9/25] Current/Best: 8.27/ 23.57 GFLOPS | Progress: (12/20) | 16.15 s
[Task 9/25] Current/Best: 18.01/ 23.57 GFLOPS | Progress: (16/20) | 19.00 s
[Task 9/25] Current/Best: 9.03/ 23.57 GFLOPS | Progress: (20/20) | 27.46 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (4/20) | 2.49 s
[Task 10/25] Current/Best: 15.52/ 18.16 GFLOPS | Progress: (8/20) | 4.14 s
[Task 10/25] Current/Best: 12.76/ 18.92 GFLOPS | Progress: (12/20) | 5.67 s
[Task 10/25] Current/Best: 19.14/ 20.40 GFLOPS | Progress: (16/20) | 6.78 s
[Task 10/25] Current/Best: 8.90/ 20.40 GFLOPS | Progress: (20/20
) | 8.29 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.28/ 18.07 GFLOPS | Progress: (4/20) | 3.29 s
[Task 11/25] Current/Best: 16.82/ 18.07 GFLOPS | Progress: (8/20) | 6.09 s
[Task 11/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (12/20) | 8.12 s
[Task 11/25] Current/Best: 12.39/ 21.16 GFLOPS | Progress: (16/20) | 11.07 s
[Task 11/25] Current/Best: 19.43/ 21.45 GFLOPS | Progress: (20/20) | 13.16 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.79/ 18.18 GFLOPS | Progress: (4/20) | 5.63 s
[Task 12/25] Current/Best: 5.27/ 18.18 GFLOPS | Progress: (8/20) | 9.59 s
[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 11.59 s
[Task 12/25] Current/Best: 13.38/ 18.95 GFLOPS | Progress: (16/20) | 14.54 s
[Task 12/25] Current/Best: 15.13/ 18.95 GFLOPS | Progress: (20/20) | 16.48 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.71/ 17.14 GFLOPS | Progress: (4/20) | 3.73 s
[Task 13/25] Current/Best: 15.55/ 20.76 GFLOPS | Progress: (8/20) | 6.33 s
[Task 13/25] Current/Best: 19.42/ 21.40 GFLOPS | Progress: (12/20) | 9.39 s
[Task 13/25] Current/Best: 12.22/ 21.40 GFLOPS | Progress: (16/20) | 12.84 s
[Task 13/25] Current/Best: 18.59/ 21.40 GFLOPS | Progress: (20/20) | 15.16 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.50/ 13.50 GFLOPS | Progress: (4/20) | 3.27 s
[Task 14/25] Current/Best: 6.07/ 13.50 GFLOPS | Progress: (8/20) | 5.47 s
[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 8.18 s
[Task 14/25] Current/Best: 15.59/ 20.32 GFLOPS | Progress: (16/20) | 9.90 s Done.
-
[Task 14/25] Current/Best: 17.07/ 20.32 GFLOPS | Progress: (20/20) | 11.63 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.13/ 17.54 GFLOPS | Progress: (4/20) | 2.69 s
[Task 15/25] Current/Best: 14.14/ 17.91 GFLOPS | Progress: (8/20) | 4.05 s
[Task 15/25] Current/Best: 10.37/ 21.83 GFLOPS | Progress: (12/20) | 6.29 s
[Task 15/25] Current/Best: 20.38/ 21.83 GFLOPS | Progress: (16/20) | 9.57 s
[Task 15/25] Current/Best: 9.68/ 21.83 GFLOPS | Progress: (20/20) | 10.59 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (4/20) | 2.92 s
[Task 16/25] Current/Best: 3.04/ 20.35 GFLOPS | Progress: (8/20) | 4.56 s
[Task 16/25] Current/Best: 19.25/ 20.35 GFLOPS | Progress: (12/20) | 5.79 s
[Task 16/25] Current/Best: 17.76/ 20.35 GFLOPS | Progress: (16/20) |
7.19 s
[Task 16/25] Current/Best: 9.99/ 22.29 GFLOPS | Progress: (20/20) | 9.36 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.87/ 18.81 GFLOPS | Progress: (4/20) | 4.79 s
[Task 17/25] Current/Best: 14.40/ 22.62 GFLOPS | Progress: (8/20) | 7.72 s
[Task 17/25] Current/Best: 17.25/ 22.62 GFLOPS | Progress: (12/20) | 9.82 s
[Task 17/25] Current/Best: 16.41/ 22.62 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 10.01/ 22.62 GFLOPS | Progress: (20/20) | 14.20 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.07/ 17.88 GFLOPS | Progress: (4/20) | 3.82 s
[Task 18/25] Current/Best: 10.59/ 19.12 GFLOPS | Progress: (8/20) | 7.55 s
[Task 18/25] Current/Best: 19.47/ 19.47 GFLOPS | Progress: (12/20) | 9.48 s
[Task 18/25] Current/Best: 9.90/ 19.47 GFLOPS | Progress: (16/20) | 13.40 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.93 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.98/ 20.05 GFLOPS | Progress: (4/20) | 6.10 s
[Task 19/25] Current/Best: 2.60/ 20.05 GFLOPS | Progress: (8/20) | 9.46 s
[Task 19/25] Current/Best: 19.67/ 21.84 GFLOPS | Progress: (12/20) | 12.38 s
[Task 19/25] Current/Best: 14.91/ 21.88 GFLOPS | Progress: (16/20) | 15.33 s
[Task 19/25] Current/Best: 2.70/ 23.58 GFLOPS | Progress: (20/20) | 18.12 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.13/ 15.43 GFLOPS | Progress: (4/20) | 3.22 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.74/ 17.74 GFLOPS | Progress: (4/20) | 6.40 s
[Task 1/25] Current/Best: 6.25/ 17.74 GFLOPS | Progress: (8/20) | 8.75 s
[Task 1/25] Current/Best: 11.65/ 23.13 GFLOPS | Progress: (12/20) | 11.18 s
[Task 1/25] Current/Best: 17.09/ 23.13 GFLOPS | Progress: (16/20) | 12.84 s
[Task 1/25] Current/Best: 11.76/ 24.28 GFLOPS | Progress: (20/20) | 14.55 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.43/ 13.41 GFLOPS | Progress: (4/20) | 3.69 s
[Task 2/25] Current/Best: 14.21/ 17.94 GFLOPS | Progress: (8/20) | 4.97 s
[Task 2/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 6.30 s
[Task 2/25] Current/Best: 13.02/ 21.28 GFLOPS | Progress: (16/20) | 7.58 s
[Task 2/25] Current/Best: 20.30/ 21.28 GFLOPS | Progress: (20/20) | 9.17 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.65/ 10.65 GFLOPS | Progress: (4/20) | 5.74 s
[Task 3/25] Current/Best: 15.90/ 17.17 GFLOPS | Progress: (8/20) | 7.66 s
[Task 3/25] Current/Best: 15.13/ 17.17 GFLOPS | Progress: (12/20) | 9.34 s
[Task 3/25] Current/Best: 7.29/ 24.17 GFLOPS | Progress: (16/20) | 11.26 s
[Task 3/25] Current/Best: 11.31/ 24.17 GFLOPS | Progress: (20/20) | 15.77 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.65/ 20.67 GFLOPS | Progress: (4/20) | 2.33 s
[Task 4/25] Current/Best: 6.93/ 20.67 GFLOPS | Progress: (8/20) | 6.95 s
[Task 4/25] Current/Best: 22.74/ 22.74 GFLOPS | Progress: (12/20) | 11.89 s
[Task 4/25] Current/Best: 17.81/ 22.74 GFLOPS | Progress: (16/20) | 14.23 s
[Task 4/25] Current/Best: 13.77/ 22.74 GFLOPS | Progress: (20/20) | 16.28 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.55/ 10.41 GFLOPS | Progress: (4/20) | 2.49 s
[Task 5/25] Current/Best: 11.80/ 12.67 GFLOPS | Progress: (8/20) | 4.54 s
[Task 5/25] Current/Best: 11.56/ 18.31 GFLOPS | Progress: (12/20) | 7.67 s
[Task 5/25] Current/Best: 11.89/ 22.47 GFLOPS | Progress: (16/20) | 9.07 s
[Task 5/25] Current/Best: 12.15/ 22.47 GFLOPS | Progress: (20/20) | 10.97 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.38/ 20.98 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 19.24/ 20.98 GFLOPS | Progress: (8/20) | 5.69 s
[Task 6/25] Current/Best: 13.52/ 20.98 GFLOPS | Progress: (12/20) | 7.61 s
[Task 6/25] Current/Best: 20.34/ 20.98 GFLOPS | Progress: (16/20) | 9.82 s
[Task 6/25] Current/Best: 3.74/ 20.98 GFLOPS | Progress: (20/20) | 12.29 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.33/ 12.41 GFLOPS | Progress: (4/20) | 3.50 s
[Task 7/25] Current/Best: 20.61/ 21.35 GFLOPS | Progress: (8/20) | 5.00 s
[Task 7/25] Current/Best: 16.46/ 21.35 GFLOPS | Progress: (12/20) | 6.87 s
[Task 7/25] Current/Best: 12.45/ 21.35 GFLOPS | Progress: (16/20) | 8.88 s
[Task 7/25] Current/Best: 6.38/ 22.17 GFLOPS | Progress: (20/20) | 11.30 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.95/ 13.98 GFLOPS | Progress: (4/20) | 2.80 s
[Task 8/25] Current/Best: 9.24/ 13.98 GFLOPS | Progress: (8/20) | 7.74 s
[Task 8/25] Current/Best: 12.38/ 13.98 GFLOPS | Progress: (12/20) | 14.14 s
[Task 8/25] Current/Best: 19.11/ 19.11 GFLOPS | Progress: (16/20) | 16.23 s
[Task 8/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (20/20) | 23.21 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.56/ 16.03 GFLOPS | Progress: (4/20) | 11.84 s
[Task 9/25] Current/Best: 23.82/ 23.82 GFLOPS | Progress: (8/20) | 13.56 s
[Task 9/25] Current/Best: 8.38/ 23.82 GFLOPS | Progress: (12/20) | 16.02 s
[Task 9/25] Current/Best: 18.33/ 23.82 GFLOPS | Progress: (16/20) | 18.84 s
[Task 9/25] Current/Best: 9.11/ 23.82 GFLOPS | Progress: (20/20) | 27.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (4/20) | 2.49 s
[Task 10/25] Current/Best: 15.54/ 18.53 GFLOPS | Progress: (8/20) | 4.11 s
[Task 10/25] Current/Best: 12.62/ 19.28 GFLOPS | Progress: (12/20) | 5.65 s
[Task 10/25] Current/Best: 19.44/ 20.50 GFLOPS | Progress: (16/20) | 6.75 s
[Task 10/25] Current/Best: 8.98/ 20.50 GFLOPS | Progress: (20/20
) | 8.26 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.48/ 18.45 GFLOPS | Progress: (4/20) | 3.29 s
[Task 11/25] Current/Best: 17.05/ 18.45 GFLOPS | Progress: (8/20) | 6.08 s
[Task 11/25] Current/Best: 18.45/ 18.45 GFLOPS | Progress: (12/20) | 8.09 s
[Task 11/25] Current/Best: 13.67/ 21.43 GFLOPS | Progress: (16/20) | 11.02 s
[Task 11/25] Current/Best: 19.69/ 21.86 GFLOPS | Progress: (20/20) | 13.07 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.95/ 18.21 GFLOPS | Progress: (4/20) | 5.58 s
[Task 12/25] Current/Best: 5.22/ 18.21 GFLOPS | Progress: (8/20) | 9.45 s
[Task 12/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 11.40 s
[Task 12/25] Current/Best: 15.45/ 19.21 GFLOPS | Progress: (16/20) | 14.25 s
[Task 12/25] Current/Best: 15.35/ 19.21 GFLOPS | Progress: (20/20) | 16.16 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.80/ 17.56 GFLOPS | Progress: (4/20) | 3.67 s
[Task 13/25] Current/Best: 16.40/ 21.19 GFLOPS | Progress: (8/20) | 6.23 s
[Task 13/25] Current/Best: 19.84/ 21.66 GFLOPS | Progress: (12/20) | 9.22 s
[Task 13/25] Current/Best: 12.50/ 21.66 GFLOPS | Progress: (16/20) | 12.59 s
[Task 13/25] Current/Best: 19.02/ 21.66 GFLOPS | Progress: (20/20) | 14.85 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.84/ 13.84 GFLOPS | Progress: (4/20) | 3.31 s
[Task 14/25] Current/Best: 6.20/ 13.84 GFLOPS | Progress: (8/20) | 5.44 s
[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 8.04 s
[Task 14/25] Current/Best: 18.38/ 20.49 GFLOPS | Progress: (16/20) | 9.66 s Done.
+
[Task 14/25] Current/Best: 17.44/ 20.49 GFLOPS | Progress: (20/20) | 11.32 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.48/ 17.88 GFLOPS | Progress: (4/20) | 2.56 s
[Task 15/25] Current/Best: 14.68/ 18.41 GFLOPS | Progress: (8/20) | 3.89 s
[Task 15/25] Current/Best: 10.50/ 22.63 GFLOPS | Progress: (12/20) | 6.07 s
[Task 15/25] Current/Best: 20.59/ 22.63 GFLOPS | Progress: (16/20) | 9.05 s
[Task 15/25] Current/Best: 9.86/ 22.63 GFLOPS | Progress: (20/20) | 10.01 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (4/20) | 2.79 s
[Task 16/25] Current/Best: 3.06/ 20.87 GFLOPS | Progress: (8/20) | 4.38 s
[Task 16/25] Current/Best: 19.78/ 20.87 GFLOPS | Progress: (12/20) | 5.58 s
[Task 16/25] Current/Best: 18.06/ 20.87 GFLOPS | Progress: (16/20) |
6.91 s
[Task 16/25] Current/Best: 10.22/ 22.92 GFLOPS | Progress: (20/20) | 9.01 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.94/ 19.17 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 14.48/ 23.72 GFLOPS | Progress: (8/20) | 7.50 s
[Task 17/25] Current/Best: 17.21/ 23.72 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 16.77/ 23.72 GFLOPS | Progress: (16/20) | 11.72 s
[Task 17/25] Current/Best: 10.20/ 23.72 GFLOPS | Progress: (20/20) | 13.82 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.43/ 18.53 GFLOPS | Progress: (4/20) | 3.66 s
[Task 18/25] Current/Best: 10.69/ 20.08 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 19.71/ 20.08 GFLOPS | Progress: (12/20) | 9.13 s
[Task 18/25] Current/Best: 10.20/ 20.08 GFLOPS | Progress: (16/20) | 12.91 s
[Task 18/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (20/20) | 14.40 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.29/ 20.90 GFLOPS | Progress: (4/20) | 5.94 s
[Task 19/25] Current/Best: 2.65/ 20.90 GFLOPS | Progress: (8/20) | 9.27 s
[Task 19/25] Current/Best: 20.47/ 22.27 GFLOPS | Progress: (12/20) | 12.19 s
[Task 19/25] Current/Best: 14.40/ 22.27 GFLOPS | Progress: (16/20) | 15.16 s
[Task 19/25] Current/Best: 2.74/ 24.29 GFLOPS | Progress: (20/20) | 17.95 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.63/ 15.05 GFLOPS | Progress: (4/20) | 3.25 s Done.
Done.
-
[Task 20/25] Current/Best: 9.66/ 15.43 GFLOPS | Progress: (8/20) | 6.60 s
[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.52 s
[Task 20/25] Current/Best: 12.47/ 16.60 GFLOPS | Progress: (16/20) | 14.43 s
[Task 20/25] Current/Best: 12.13/ 22.02 GFLOPS | Progress: (20/20) | 16.53 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.66 GFLOPS | Progress: (4/20) | 3.20 s
[Task 21/25] Current/Best: 14.66/ 17.66 GFLOPS | Progress: (8/20) | 4.78 s
[Task 21/25] Current/Best: 1.61/ 17.66 GFLOPS | Progress: (12/20) | 6.88 s
[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.39 s
[Task 21/25] Current/Best: 4.45/ 17.91 GFLOPS | Progress: (20/20) | 17.58 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.71/ 16.81 GFLOPS | Progress: (4/20
) | 2.60 s
[Task 22/25] Current/Best: 8.89/ 21.92 GFLOPS | Progress: (8/20) | 4.63 s
[Task 22/25] Current/Best: 20.03/ 21.92 GFLOPS | Progress: (12/20) | 6.98 s
[Task 22/25] Current/Best: 15.37/ 21.92 GFLOPS | Progress: (16/20) | 9.07 s
[Task 22/25] Current/Best: 14.21/ 21.92 GFLOPS | Progress: (20/20) | 10.73 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.70/ 20.93 GFLOPS | Progress: (4/20) | 3.12 s
[Task 23/25] Current/Best: 14.23/ 20.93 GFLOPS | Progress: (8/20) | 6.56 s
[Task 23/25] Current/Best: 21.03/ 21.94 GFLOPS | Progress: (12/20) | 8.36 s
[Task 23/25] Current/Best: 6.34/ 21.94 GFLOPS | Progress: (16/20) | 15.62 s
[Task 23/25] Current/Best: 7.56/ 21.94 GFLOPS | Progress: (20/20) | 19.91 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.44/ 8.44 GFLOPS | Progress: (4/20) | 11.77 s
[Task 24/25] Current/Best: 1.89/ 8.44 GFLOPS | Progress: (8/20) | 22.77 s
[Task 24/25] Current/Best: 4.39/ 8.44 GFLOPS | Progress: (12/20) | 34.29 s Done.
+
[Task 20/25] Current/Best: 9.75/ 15.05 GFLOPS | Progress: (8/20) | 6.75 s
[Task 20/25] Current/Best: 2.36/ 16.65 GFLOPS | Progress: (12/20) | 10.83 s
[Task 20/25] Current/Best: 12.49/ 16.65 GFLOPS | Progress: (16/20) | 14.50 s
[Task 20/25] Current/Best: 12.25/ 22.67 GFLOPS | Progress: (20/20) | 16.56 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.52/ 18.01 GFLOPS | Progress: (4/20) | 3.14 s
[Task 21/25] Current/Best: 14.91/ 18.01 GFLOPS | Progress: (8/20) | 4.69 s
[Task 21/25] Current/Best: 1.64/ 18.01 GFLOPS | Progress: (12/20) | 6.78 s
[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.20 s
[Task 21/25] Current/Best: 4.54/ 18.05 GFLOPS | Progress: (20/20) | 17.33 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.74/ 17.27 GFLOPS | Progress: (4/20
) | 2.56 s
[Task 22/25] Current/Best: 8.80/ 22.37 GFLOPS | Progress: (8/20) | 4.60 s
[Task 22/25] Current/Best: 20.25/ 22.37 GFLOPS | Progress: (12/20) | 6.96 s
[Task 22/25] Current/Best: 15.67/ 22.37 GFLOPS | Progress: (16/20) | 9.05 s
[Task 22/25] Current/Best: 14.30/ 22.37 GFLOPS | Progress: (20/20) | 10.69 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.90/ 21.15 GFLOPS | Progress: (4/20) | 3.12 s
[Task 23/25] Current/Best: 14.44/ 21.15 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 21.33/ 22.27 GFLOPS | Progress: (12/20) | 8.31 s
[Task 23/25] Current/Best: 6.46/ 22.27 GFLOPS | Progress: (16/20) | 15.16 s
[Task 23/25] Current/Best: 7.97/ 22.27 GFLOPS | Progress: (20/20) | 19.28 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.34/ 8.34 GFLOPS | Progress: (4/20) | 11.71 s
[Task 24/25] Current/Best: 2.06/ 8.34 GFLOPS | Progress: (8/20) | 22.67 s
[Task 24/25] Current/Best: 4.28/ 8.34 GFLOPS | Progress: (12/20) | 34.14 s Done.
Done.
-
[Task 24/25] Current/Best: 6.81/ 8.60 GFLOPS | Progress: (16/20) | 40.22 s
[Task 24/25] Current/Best: 3.23/ 8.85 GFLOPS | Progress: (20/20) | 46.34 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.91 GFLOPS | Progress: (4/20) | 11.60 s
[Task 25/25] Current/Best: 5.80/ 7.85 GFLOPS | Progress: (8/20) | 22.88 s
[Task 25/25] Current/Best: 5.97/ 7.85 GFLOPS | Progress: (12/20) | 34.14 s
[Task 25/25] Current/Best: 5.82/ 8.67 GFLOPS | Progress: (16/20) | 35.95 s
[Task 25/25] Current/Best: 2.83/ 8.67 GFLOPS | Progress: (20/20) | 46.68 s
+
[Task 24/25] Current/Best: 6.11/ 9.17 GFLOPS | Progress: (16/20) | 39.73 s
[Task 24/25] Current/Best: 3.47/ 9.17 GFLOPS | Progress: (20/20) | 45.64 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.57/ 2.80 GFLOPS | Progress: (4/20) | 11.51 s
[Task 25/25] Current/Best: 6.24/ 8.25 GFLOPS | Progress: (8/20) | 22.72 s
[Task 25/25] Current/Best: 6.13/ 8.25 GFLOPS | Progress: (12/20) | 33.94 s
[Task 25/25] Current/Best: 6.07/ 9.11 GFLOPS | Progress: (16/20) | 35.63 s
[Task 25/25] Current/Best: 2.92/ 9.25 GFLOPS | Progress: (20/20) | 46.33 s
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 413.3635271499952, 'median': 412.78412854990165, 'std': 2.080394213480733}
- unoptimized: {'mean': 496.3567338799112, 'median': 496.84443964979437, 'std': 1.5960987762688807}
+ optimized: {'mean': 396.4592194200668, 'median': 395.67348075015616, 'std': 1.9716355693665089}
+ unoptimized: {'mean': 489.15848393004126, 'median': 488.8971324000522, 'std': 1.4240269798007845}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 27.969 seconds)
+ **Total running time of the script:** ( 10 minutes 9.590 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 8afad7d75..5075cee12 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.264e-07 secs/op
+ 1.268e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index c4f5874cb..28f9713f9 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x20212070)), stage(b, placeholder(b, 0x21a99110)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x2025d900)), stage(b, placeholder(b, 0x21df3b10)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index fe35680ae..1d6483064 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:12.143** total execution time for **tutorial** files:
+**13:13.543** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:27.969 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:09.590 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.791 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:11.720 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.364 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.636 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.341 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.260 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.094 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.063 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.769 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.651 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.668 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.487 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.147 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.137 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 30b199e2a..d75ec8242 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -447,7 +447,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000025
+ vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.190530024876352e-06 1.0
- naive 5.853599999999999e-06 0.7146790234846087
- parallel 6.1469e-06 0.7504886718357151
- vector 2.4507e-05 2.9921140543490004
+ numpy 7.506799993279856e-06 1.0
+ naive 5.7591000000000005e-06 0.7671844201464793
+ parallel 5.8953999999999995e-06 0.7853412912662661
+ vector 2.38423e-05 3.1760936779112017
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019471
+ Numpy running time: 0.016072
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.270069
+ none: 3.441797
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.326683
+ blocking: 0.292769
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.351616
+ vectorization: 0.328208
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.120809
+ loop permutation: 0.113438
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.111510
+ array packing: 0.106714
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111313
+ block caching: 0.108925
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.143911
+ parallelization: 0.142040
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.270069246 1.0
- blocking 0.3266827326 0.09990086081498228
- vectorization 0.3516162646 0.10752563268502725
- loop permutation 0.1208091131 0.03694390057573723
- array packing 0.11150971219999999 0.034100107310082325
- block caching 0.11131297340000001 0.03403994381347117
- parallelization 0.14391054509999998 0.044008409080643664
+ none 3.4417968634999996 1.0
+ blocking 0.2927686107 0.08506272226719402
+ vectorization 0.3282077072 0.09535940679144035
+ loop permutation 0.11343817870000002 0.03295899880176064
+ array packing 0.1067137891 0.031005254909635085
+ block caching 0.10892510979999999 0.0316477450936
+ parallelization 0.14204011889999998 0.04126917553046924
@@ -1673,6 +1673,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.636 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index e349898ec..9a8f9c6e4 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b4a77ac7f4ed9c639a28468133b22d9b03c69bf7
+333994d45fab729dfebcfeb2f1f9c211818b693e
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 8c978c59c..67e631c6b 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -403,7 +403,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip298ce64c-f7e0-4a08-88b6-fb84f5f0557e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa9698854-8cf5-4db7-b6de-141f43b40404 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 41218e526..20ba34534 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -408,41 +408,41 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<08:10, 88.6kB/s]
- 0%| | 48.0k/41.5M [00:00<05:09, 140kB/s]
- 0%| | 96.0k/41.5M [00:00<03:40, 197kB/s]
- 0%| | 192k/41.5M [00:00<02:12, 328kB/s]
- 1%| | 376k/41.5M [00:00<01:14, 575kB/s]
- 2%|1 | 704k/41.5M [00:01<00:43, 994kB/s]
- 3%|3 | 1.39M/41.5M [00:01<00:21, 1.97MB/s]
- 7%|6 | 2.71M/41.5M [00:01<00:10, 3.71MB/s]
- 10%|# | 4.23M/41.5M [00:01<00:07, 5.23MB/s]
- 14%|#3 | 5.76M/41.5M [00:01<00:05, 6.27MB/s]
- 18%|#7 | 7.29M/41.5M [00:02<00:05, 6.99MB/s]
- 21%|##1 | 8.80M/41.5M [00:02<00:04, 7.47MB/s]
- 25%|##4 | 10.3M/41.5M [00:02<00:04, 7.79MB/s]
- 29%|##8 | 11.8M/41.5M [00:02<00:03, 8.03MB/s]
- 32%|###2 | 13.4M/41.5M [00:02<00:03, 8.21MB/s]
- 36%|###5 | 14.9M/41.5M [00:02<00:03, 8.33MB/s]
- 40%|###9 | 16.4M/41.5M [00:03<00:03, 8.41MB/s]
- 43%|####3 | 17.9M/41.5M [00:03<00:02, 8.46MB/s]
- 47%|####6 | 19.5M/41.5M [00:03<00:02, 9.55MB/s]
- 51%|##### | 21.0M/41.5M [00:03<00:02, 9.24MB/s]
- 54%|#####4 | 22.5M/41.5M [00:03<00:01, 10.1MB/s]
- 57%|#####6 | 23.5M/41.5M [00:03<00:02, 9.41MB/s]
- 59%|#####8 | 24.4M/41.5M [00:04<00:02, 8.04MB/s]
- 62%|######1 | 25.6M/41.5M [00:04<00:02, 7.51MB/s]
- 65%|######5 | 27.1M/41.5M [00:04<00:01, 7.86MB/s]
- 69%|######8 | 28.6M/41.5M [00:04<00:01, 8.09MB/s]
- 73%|#######2 | 30.1M/41.5M [00:04<00:01, 8.25MB/s]
- 76%|#######6 | 31.6M/41.5M [00:05<00:01, 8.34MB/s]
- 80%|#######9 | 33.2M/41.5M [00:05<00:01, 8.42MB/s]
- 84%|########3 | 34.7M/41.5M [00:05<00:00, 8.47MB/s]
- 87%|########7 | 36.2M/41.5M [00:05<00:00, 8.52MB/s]
- 91%|######### | 37.7M/41.5M [00:05<00:00, 8.54MB/s]
- 95%|#########4| 39.3M/41.5M [00:05<00:00, 8.54MB/s]
- 98%|#########8| 40.8M/41.5M [00:06<00:00, 8.56MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 7.08MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:33, 95.9kB/s]
+ 0%| | 40.0k/41.5M [00:00<05:51, 124kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:17, 220kB/s]
+ 0%| | 160k/41.5M [00:00<02:32, 283kB/s]
+ 1%| | 280k/41.5M [00:00<01:38, 439kB/s]
+ 1%|1 | 576k/41.5M [00:01<00:48, 890kB/s]
+ 3%|2 | 1.13M/41.5M [00:01<00:24, 1.74MB/s]
+ 5%|5 | 2.27M/41.5M [00:01<00:12, 3.40MB/s]
+ 9%|9 | 3.74M/41.5M [00:01<00:07, 5.14MB/s]
+ 13%|#2 | 5.20M/41.5M [00:01<00:06, 6.30MB/s]
+ 16%|#6 | 6.67M/41.5M [00:01<00:05, 7.11MB/s]
+ 20%|#9 | 8.14M/41.5M [00:02<00:04, 7.67MB/s]
+ 23%|##3 | 9.61M/41.5M [00:02<00:04, 8.06MB/s]
+ 27%|##6 | 11.1M/41.5M [00:02<00:03, 8.33MB/s]
+ 30%|### | 12.5M/41.5M [00:02<00:03, 8.52MB/s]
+ 34%|###3 | 14.0M/41.5M [00:02<00:03, 8.65MB/s]
+ 37%|###7 | 15.5M/41.5M [00:02<00:03, 8.76MB/s]
+ 41%|#### | 17.0M/41.5M [00:03<00:02, 8.81MB/s]
+ 44%|####4 | 18.4M/41.5M [00:03<00:02, 8.86MB/s]
+ 48%|####7 | 19.9M/41.5M [00:03<00:02, 8.88MB/s]
+ 51%|#####1 | 21.4M/41.5M [00:03<00:02, 8.91MB/s]
+ 55%|#####5 | 22.8M/41.5M [00:03<00:02, 8.92MB/s]
+ 59%|#####8 | 24.3M/41.5M [00:03<00:02, 8.93MB/s]
+ 62%|######2 | 25.8M/41.5M [00:04<00:01, 8.95MB/s]
+ 66%|######5 | 27.2M/41.5M [00:04<00:01, 8.95MB/s]
+ 69%|######9 | 28.7M/41.5M [00:04<00:01, 8.95MB/s]
+ 73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.94MB/s]
+ 76%|#######6 | 31.6M/41.5M [00:04<00:01, 8.93MB/s]
+ 80%|#######9 | 33.1M/41.5M [00:04<00:00, 8.94MB/s]
+ 83%|########3 | 34.6M/41.5M [00:05<00:00, 8.95MB/s]
+ 87%|########6 | 36.0M/41.5M [00:05<00:00, 8.95MB/s]
+ 90%|######### | 37.5M/41.5M [00:05<00:00, 8.95MB/s]
+ 94%|#########3| 39.0M/41.5M [00:05<00:00, 8.93MB/s]
+ 97%|#########7| 40.4M/41.5M [00:05<00:00, 8.93MB/s]
+100%|##########| 41.5M/41.5M [00:05<00:00, 7.43MB/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 7be6cd292..7cd4bf102 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.065 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.650 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index a27a9aedb..39ea5b24a 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -390,24 +390,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 9%|8 | 4.00M/44.7M [00:00<00:01, 34.6MB/s]
- 16%|#6 | 7.30M/44.7M [00:00<00:01, 27.7MB/s]
- 24%|##3 | 10.6M/44.7M [00:00<00:01, 30.0MB/s]
- 30%|### | 13.5M/44.7M [00:00<00:01, 23.3MB/s]
- 37%|###6 | 16.4M/44.7M [00:00<00:01, 25.3MB/s]
- 42%|####2 | 19.0M/44.7M [00:00<00:01, 20.8MB/s]
- 47%|####7 | 21.2M/44.7M [00:00<00:01, 20.1MB/s]
- 54%|#####4 | 24.3M/44.7M [00:01<00:00, 23.1MB/s]
- 62%|######2 | 27.9M/44.7M [00:01<00:00, 26.9MB/s]
- 69%|######9 | 31.0M/44.7M [00:01<00:00, 26.5MB/s]
- 75%|#######5 | 33.7M/44.7M [00:01<00:00, 22.4MB/s]
- 81%|######## | 36.0M/44.7M [00:01<00:00, 17.3MB/s]
- 85%|########4 | 37.9M/44.7M [00:01<00:00, 13.1MB/s]
- 88%|########8 | 39.4M/44.7M [00:02<00:00, 13.1MB/s]
- 92%|#########2| 41.3M/44.7M [00:02<00:00, 14.2MB/s]
- 96%|#########5| 42.8M/44.7M [00:02<00:00, 11.9MB/s]
- 99%|#########8| 44.1M/44.7M [00:02<00:00, 10.1MB/s]
-100%|##########| 44.7M/44.7M [00:02<00:00, 17.6MB/s]
+ 40%|#### | 17.9M/44.7M [00:00<00:00, 188MB/s]
+ 94%|#########4| 42.1M/44.7M [00:00<00:00, 227MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 222MB/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 72c4d7300..874c7e960 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,6 @@ 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 3.326 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index e1be1cd2a..030e0b803 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:29.900</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:27.984</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,43 +312,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>01:07.065</p></td>
+<td><p>01:06.650</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:03.326</p></td>
+<td><p>00:59.310</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>00:58.560</p></td>
+<td><p>00:55.912</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.582</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:36.198</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.455</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
+<td><p>00:31.878</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:22.838</p></td>
+<td><p>00:22.759</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.573</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:20.745</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.863</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
+<td><p>00:18.545</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:14.286</p></td>
+<td><p>00:13.673</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.353</p></td>
+<td><p>00:02.314</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index e989840b5..8a4df9693 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -629,7 +629,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2469 16.2381 16.2843 16.2137 0.0230
+ 15.3654 15.3765 15.5716 15.2326 0.1008
</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 6a5a3551d..109b2f0a7 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -412,22 +412,18 @@ 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]
- 2%|2 | 3.71M/170M [00:00<00:04, 37.4MB/s]
- 8%|7 | 13.5M/170M [00:00<00:02, 74.8MB/s]
- 14%|#3 | 23.1M/170M [00:00<00:01, 86.6MB/s]
- 20%|#9 | 33.8M/170M [00:00<00:01, 96.9MB/s]
- 27%|##7 | 46.3M/170M [00:00<00:01, 109MB/s]
- 34%|###4 | 57.8M/170M [00:00<00:01, 113MB/s]
- 41%|#### | 69.6M/170M [00:00<00:00, 116MB/s]
- 48%|####7 | 81.4M/170M [00:00<00:00, 118MB/s]
- 55%|#####4 | 93.2M/170M [00:00<00:00, 120MB/s]
- 62%|######1 | 105M/170M [00:01<00:00, 121MB/s]
- 69%|######8 | 117M/170M [00:01<00:00, 122MB/s]
- 76%|#######5 | 128M/170M [00:01<00:00, 113MB/s]
- 82%|########2 | 140M/170M [00:01<00:00, 116MB/s]
- 89%|########9 | 152M/170M [00:01<00:00, 118MB/s]
- 96%|#########6| 163M/170M [00:01<00:00, 119MB/s]
-100%|##########| 170M/170M [00:01<00:00, 112MB/s]
+ 6%|5 | 9.44M/170M [00:00<00:01, 98.9MB/s]
+ 15%|#5 | 25.7M/170M [00:00<00:01, 141MB/s]
+ 24%|##3 | 40.4M/170M [00:00<00:00, 144MB/s]
+ 33%|###2 | 56.0M/170M [00:00<00:00, 152MB/s]
+ 42%|####2 | 71.6M/170M [00:00<00:00, 155MB/s]
+ 51%|##### | 86.4M/170M [00:00<00:00, 153MB/s]
+ 60%|###### | 103M/170M [00:00<00:00, 158MB/s]
+ 70%|######9 | 119M/170M [00:00<00:00, 161MB/s]
+ 79%|#######9 | 135M/170M [00:00<00:00, 164MB/s]
+ 89%|########8 | 151M/170M [00:01<00:00, 165MB/s]
+ 98%|#########8| 167M/170M [00:01<00:00, 166MB/s]
+100%|##########| 170M/170M [00:01<00:00, 158MB/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').
@@ -522,7 +518,7 @@ 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 1.674 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 46.388 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 394143397..adaaab8de 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -453,7 +453,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 169MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 165MB/s]
</pre></div>
</div>
</div>
@@ -542,7 +542,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.7523 90.4243 98.8380 90.2408 1.1992
+ 89.0394 88.9430 90.4560 88.7244 0.2790
</pre></div>
</div>
<div class="admonition note">
@@ -581,7 +581,7 @@ 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 6.706 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.396 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 307b834ba..acca77f17 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -546,7 +546,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.5697 120.5087 123.3701 119.5512 0.4639
+ 117.0881 117.0740 123.2218 115.0804 0.8260
</pre></div>
</div>
<div class="admonition note">
@@ -574,7 +574,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 3.954 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 56.761 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 1a90dcc7e..e59e41ac3 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -485,7 +485,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.379 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.111 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index cf8f70329..b315685e5 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -417,22 +417,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5939/132723 [00:00<00:02, 59368.82KB/s]
- 11%|# | 14438/132723 [00:00<00:01, 74432.40KB/s]
- 17%|#7 | 22874/132723 [00:00<00:01, 78957.48KB/s]
- 24%|##3 | 31336/132723 [00:00<00:01, 81189.81KB/s]
- 30%|### | 39817/132723 [00:00<00:01, 82493.75KB/s]
- 36%|###6 | 48290/132723 [00:00<00:01, 83252.15KB/s]
- 43%|####2 | 56782/132723 [00:00<00:00, 83795.64KB/s]
- 49%|####9 | 65272/132723 [00:00<00:00, 84145.37KB/s]
- 56%|#####5 | 73823/132723 [00:00<00:00, 84570.40KB/s]
- 62%|######2 | 82345/132723 [00:01<00:00, 84765.72KB/s]
- 68%|######8 | 90833/132723 [00:01<00:00, 84790.88KB/s]
- 75%|#######4 | 99313/132723 [00:01<00:00, 84671.85KB/s]
- 81%|########1 | 107811/132723 [00:01<00:00, 84761.88KB/s]
- 88%|########7 | 116288/132723 [00:01<00:00, 79635.75KB/s]
- 94%|#########4| 124840/132723 [00:01<00:00, 81327.68KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 82134.24KB/s]
+ 4%|3 | 4682/132723 [00:00<00:02, 46815.13KB/s]
+ 10%|9 | 12748/132723 [00:00<00:01, 66719.23KB/s]
+ 16%|#5 | 20983/132723 [00:00<00:01, 73855.09KB/s]
+ 22%|##2 | 29375/132723 [00:00<00:01, 77827.37KB/s]
+ 28%|##8 | 37613/132723 [00:00<00:01, 79465.02KB/s]
+ 34%|###4 | 45699/132723 [00:00<00:01, 79938.21KB/s]
+ 40%|#### | 53693/132723 [00:00<00:00, 79906.37KB/s]
+ 47%|####6 | 61796/132723 [00:00<00:00, 80238.85KB/s]
+ 53%|#####2 | 69820/132723 [00:00<00:00, 80194.96KB/s]
+ 59%|#####8 | 77840/132723 [00:01<00:00, 80029.77KB/s]
+ 65%|######4 | 85865/132723 [00:01<00:00, 80091.70KB/s]
+ 71%|####### | 94108/132723 [00:01<00:00, 80799.15KB/s]
+ 77%|#######7 | 102489/132723 [00:01<00:00, 81709.07KB/s]
+ 83%|########3 | 110747/132723 [00:01<00:00, 81970.68KB/s]
+ 90%|########9 | 118945/132723 [00:01<00:00, 81286.80KB/s]
+ 96%|#########5| 127188/132723 [00:01<00:00, 81626.11KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 79408.41KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -475,7 +476,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.126 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 13.281 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 283eb5bc1..1ca01f7f7 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:46.061</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:03.712</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -312,35 +312,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:01.674</p></td>
+<td><p>02:46.388</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:23.126</p></td>
+<td><p>02:13.281</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:03.954</p></td>
+<td><p>01:56.761</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:19.379</p></td>
+<td><p>01:13.111</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.706</p></td>
+<td><p>01:04.396</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:28.590</p></td>
+<td><p>00:27.920</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.626</p></td>
+<td><p>00:21.850</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 8dd1ff741..a24450002 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -585,7 +585,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9c2605ab-614a-4f26-a81e-5b6c941f2c9a 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.zip5fe841da-889f-4fc2-8a7f-b8bb1fd68b1f 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>
@@ -649,7 +649,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm 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 registered 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 a9afca57f..6ab91217d 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.121</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.134</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,19 +312,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.852</p></td>
+<td><p>00:35.143</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.306</p></td>
+<td><p>00:02.100</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.956</p></td>
+<td><p>00:00.885</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 70a8c15b8..ca4bc13b9 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -488,10 +488,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7161us [7161us] (46.03%; 46.03%)
-FoldScaleAxis: 8396us [7us] (53.97%; 53.97%)
- FoldConstant: 8389us [1642us] (53.92%; 99.91%)
- InferType: 6747us [6747us] (43.37%; 80.42%)
+InferType: 6415us [6415us] (45.46%; 45.46%)
+FoldScaleAxis: 7695us [5us] (54.54%; 54.54%)
+ FoldConstant: 7690us [1611us] (54.50%; 99.93%)
+ InferType: 6079us [6079us] (43.08%; 79.06%)
</pre></div>
</div>
</div>
@@ -513,10 +513,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6693us [6693us] (44.98%; 44.98%)
-FoldScaleAxis: 8189us [5us] (55.02%; 55.02%)
- FoldConstant: 8183us [1691us] (54.99%; 99.93%)
- InferType: 6492us [6492us] (43.63%; 79.34%)
+InferType: 6085us [6085us] (44.46%; 44.46%)
+FoldScaleAxis: 7603us [4us] (55.54%; 55.54%)
+ FoldConstant: 7599us [1604us] (55.51%; 99.94%)
+ InferType: 5994us [5994us] (43.79%; 78.88%)
</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 156ab65f7..0cbedd96d 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -537,7 +537,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.181943 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.202330 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 129a77512..9feb5037b 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -879,7 +879,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.551538 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.556827 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 7b2c665c1..d55523b8f 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -434,8 +434,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019226
-Baseline: 3.265900
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017729
+Baseline: 3.392386
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -495,7 +495,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.313961
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296617
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -562,7 +562,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349103
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335684
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120882
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.112770
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -706,7 +706,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111118
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.106931
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -792,7 +792,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111351
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.109232
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -882,7 +882,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145423
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.142027
</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 d9c9a8fc5..1849ae302 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.553</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:33.922</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.242</p></td>
+<td><p>00:31.693</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.284</p></td>
+<td><p>00:01.228</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.027</p></td>
+<td><p>00:01.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 366b8dac1..448287e18 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:14.552</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:07.575</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>02:33.971</p></td>
+<td><p>02:33.706</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.243</p></td>
+<td><p>01:18.381</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:43.758</p></td>
+<td><p>00:41.676</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:18.210</p></td>
+<td><p>00:17.454</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.707</p></td>
+<td><p>00:08.208</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.664</p></td>
+<td><p>00:08.151</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index c0956dbda..bf1fc2941 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
@@ -467,12 +467,12 @@ 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" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -482,68 +482,83 @@ cooperative fetching, unrolling and operator fusion.</p>
for (rc.outer.outer: int32, 0, 32) {
let cse_var_1: int32 = (rc.outer.outer*784)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 336), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 93), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 124), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 155), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 672), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 186), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 217), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 248), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1120), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 310), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 17), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 341), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ if @tir.likely((threadIdx.x_1 < 400), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 896), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 86), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 24) {
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- let cse_var_2: int32 = floordiv(ax0.ax1.fused.ax2.fused.ax3.fused.inner.s, 3)
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[((threadIdx.x_2*24) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 6)*8) + cse_var_2), 3)*9)) + (floormod(((threadIdx.x_2*2) + cse_var_2), 3)*3)) + floormod(ax0.ax1.fused.ax2.fused.ax3.fused.inner.s, 3))]
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*9)] = kernel[((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9))]
+ kernel.shared_1[((threadIdx.x_2*9) + 1)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 1)]
+ kernel.shared_1[((threadIdx.x_2*9) + 2)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 2)]
+ kernel.shared_1[((threadIdx.x_2*9) + 3)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 3)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 4)]
+ kernel.shared_1[((threadIdx.x_2*9) + 5)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 5)]
+ kernel.shared_1[((threadIdx.x_2*9) + 6)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 6)]
+ kernel.shared_1[((threadIdx.x_2*9) + 7)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 7)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 8)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448 {
+ kernel.shared_1[((threadIdx.x_2*9) + 4032)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129024)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4033)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129025)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4034)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129026)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4035)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129027)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4036)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129028)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4037)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129029)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4038)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129030)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4039)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129031)]
+ kernel.shared_1[((threadIdx.x_2*9) + 4040)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 129032)]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 448;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*9) + 8064)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258048)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8065)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258049)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8066)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258050)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8067)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258051)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8068)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258052)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8069)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258053)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8070)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258054)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8071)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258055)]
+ kernel.shared_1[((threadIdx.x_2*9) + 8072)] = kernel[(((((blockIdx.x*294912) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + 258056)]
}
- for (rc.outer.inner: int32, 0, 8) {
+ for (rc.outer.inner: int32, 0, 2) {
for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ for (xx.outer.inner: int32, 0, 7) {
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[xx.outer.inner] = (conv2d_nchw_1[xx.outer.inner] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*72)) + (ry.outer.inner*3)) + 65)]))
}
}
}
}
}
- compute[(((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute[(((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
+ }
}
}
</pre></div>
@@ -579,7 +594,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.229 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.363 ms
</pre></div>
</div>
</div>
@@ -610,34 +625,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=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)
@@ -655,16 +670,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=9)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=448)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=448)
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", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -682,10 +697,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(448) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
__shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -696,53 +711,74 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 400) {
+ pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 24; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 24) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) % 3) * 3)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s % 3))];
- }
+ kernel_shared[(((int)threadIdx.x) * 9)] = kernel[((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9))];
+ kernel_shared[((((int)threadIdx.x) * 9) + 1)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 1)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 2)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 2)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 3)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 3)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 4)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 5)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 5)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 6)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 6)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 7)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 7)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 8)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4032)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129024)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4033)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129025)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4034)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129026)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4035)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129027)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4036)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129028)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4037)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129029)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4038)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129030)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4039)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129031)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 4040)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 129032)];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[((((int)threadIdx.x) * 9) + 8064)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258048)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8065)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258049)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8066)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258050)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8067)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258051)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8068)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258052)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8069)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258053)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8070)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258054)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8071)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258055)];
+ kernel_shared[((((int)threadIdx.x) * 9) + 8072)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + 258056)];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ for (int xx_outer_inner = 0; xx_outer_inner < 7; ++xx_outer_inner) {
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3))]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[xx_outer_inner] = (conv2d_nchw[xx_outer_inner] + (pad_temp_shared[(((((rc_outer_inner * 648) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 72)) + (ry_outer_inner * 3)) + 65)]));
}
}
}
}
- compute[(((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
</pre></div>
</div>
@@ -778,7 +814,7 @@ 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 33.971 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.706 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 7028bd79b..98ca10992 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -882,7 +882,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.0408 10.0276 10.0759 10.0188 0.0251
+ 9.8250 9.8258 9.8729 9.7764 0.0394
</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 d5e4e16eb..f8854ff70 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.1155 758.7847 760.1542 758.4076 0.7504
+ 746.6928 746.6570 747.0672 746.3541 0.2922
</pre></div>
</div>
</div>
@@ -923,7 +923,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.243 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.381 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 7ffb85ce5..d4bea9b2b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -601,30 +601,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 16) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_4: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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))
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -662,7 +710,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.494 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.845 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 3933f729d..185644800 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.075</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.204</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,7 +312,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.041</p></td>
+<td><p>00:43.172</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
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 ea00519ce..ba815e1a4 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1145,8 +1145,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.33/42.33 result: MeasureResult(costs=(0.00546865052631579,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6242687702178955, timestamp=1655424491.0523908) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.32/110.32 result: MeasureResult(costs=(0.0020985360625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8206052780151367, timestamp=1655426847.6840272) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1269,7 +1269,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1392,7 +1392,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1515,7 +1515,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1533,7 +1533,7 @@ No: 10 GFLOPS: 0.00/42.33 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: 0.00/42.33 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1656,7 +1656,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1779,7 +1779,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1902,7 +1902,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2025,7 +2025,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2148,7 +2148,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2271,7 +2271,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2394,7 +2394,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2517,7 +2517,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.33 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.32 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2605,7 +2605,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f5036f29fa2
+ 12: 0x00007f88f58acfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2670,7 +2670,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 142.95/142.95 result: MeasureResult(costs=(0.0016194267096774195,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1618273258209229, timestamp=1655424517.3447928) [('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: 144.24/144.24 result: MeasureResult(costs=(0.00160498168,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3826005458831787, timestamp=1655426873.9520867) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2711,7 +2711,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.001978
+Time cost of this operator: 0.002007
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 59f4ebabb..07ef4b3cb 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -559,10 +559,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.7 98.745 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.964 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.928 0.291 (1, 1, 10, 10, 3) 1 1
-Total_time - 318.701 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.733 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.088 0.981 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.286 (1, 1, 10, 10, 3) 1 1
+Total_time - 314.889 - - - -
</pre></div>
</div>
</div>
@@ -615,10 +615,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 250.1 98.828 (1, 1, 10, 10, 6) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.049 0.81 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.917 0.362 (1, 1, 10, 10, 3) 1 1
-Total_time - 253.066 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 77.8 96.637 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.777 2.207 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 1.156 (1, 1, 10, 10, 3) 1 1
+Total_time - 80.508 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 03a33e7f4..02b67b962 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -490,7 +490,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqv6kzq4w/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp_nl5au9x/images/random'
</pre></div>
</div>
</div>
@@ -550,8 +550,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqv6kzq4w/images/target contains 8144 images
-/tmp/tmpqv6kzq4w/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp_nl5au9x/images/target contains 8144 images
+/tmp/tmp_nl5au9x/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -663,13 +663,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2526 - accuracy: 0.9173 - val_loss: 0.1534 - val_accuracy: 0.9547
+328/328 - 54s - loss: 0.2286 - accuracy: 0.9204 - val_loss: 0.1375 - val_accuracy: 0.9547
Epoch 2/3
-328/328 - 53s - loss: 0.1045 - accuracy: 0.9606 - val_loss: 0.1262 - val_accuracy: 0.9626
+328/328 - 51s - loss: 0.1002 - accuracy: 0.9610 - val_loss: 0.1194 - val_accuracy: 0.9634
Epoch 3/3
-328/328 - 53s - loss: 0.0715 - accuracy: 0.9733 - val_loss: 0.1529 - val_accuracy: 0.9524
+328/328 - 51s - loss: 0.0656 - accuracy: 0.9746 - val_loss: 0.1162 - val_accuracy: 0.9634
-<keras.callbacks.History object at 0x7fb7692f0a90>
+<keras.callbacks.History object at 0x7f8dd561b910>
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.134 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 32.727 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index ab4d5ffc9..642af0781 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:11.061</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:17.329</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:24.134</p></td>
+<td><p>04:32.727</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:43.266</p></td>
+<td><p>00:41.211</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.661</p></td>
+<td><p>00:03.391</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index ce1c2a600..5edd258b6 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:12.405</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.243</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.621</p></td>
+<td><p>00:09.819</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.778</p></td>
+<td><p>00:01.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 48c48735c..37f665b5b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -496,7 +496,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fb6e61df680>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f8d3c341ef0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 3fa4080aa..b43f3ad46 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.161</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.001</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.923</p></td>
+<td><p>00:01.861</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.007</p></td>
+<td><p>00:00.953</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.536</p></td>
+<td><p>00:00.519</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.522</p></td>
+<td><p>00:00.501</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.099</p></td>
+<td><p>00:00.096</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.033</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
@@ -340,7 +340,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.013</p></td>
+<td><p>00:00.012</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 7dfd4d06e..a0e9cc27a 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/tmpw7n0cedl/input0.cc'\nsource_filename = \"/tmp/tmpw7n0cedl/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/tmpv3z4tcoe/input0.cc'\nsource_filename = \"/tmp/tmpv3z4tcoe/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index da5f029b8..5c2a675e2 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1718,7 +1718,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1755,7 +1755,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 6842ac3ed..5b708ee27 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/b4a77ac7f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 4681275e7..6fe1e1e32 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/b4a77ac7f/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 27b581307..e045a0ae1 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/b4a77ac7f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 194a97362..492e2bb3a 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/b4a77ac7f/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 99a74d405..4033c65de 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/b4a77ac7f/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 4e8f64b60..f36cf5022 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/b4a77ac7f/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 34a896ba3..bb1fd59fc 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/b4a77ac7f/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 ac37209ed..918b333f3 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/b4a77ac7f/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 238878d71..4c84db820 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/b4a77ac7f/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 f6ae4dfa0..e46213607 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/b4a77ac7f/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 2dd79f2f4..b470a0478 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/b4a77ac7f/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 ed163147e..20aec88e3 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/b4a77ac7f/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 1baf5b825..599fe5aeb 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/b4a77ac7f/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 2be6fa4a8..e5fc80c05 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/b4a77ac7f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 7e28b33a5..48b60973c 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/b4a77ac7f/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 86b05ac28..1362141d4 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/b4a77ac7f/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 a85b261a1..56a108bf0 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/b4a77ac7f/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 bdcc77849..a99617aac 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/b4a77ac7f/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 2e74d8435..2b601003f 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/b4a77ac7f/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 3b5fb606c..1ef4f5888 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/b4a77ac7f/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 f0e0ad854..acd5faf76 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/b4a77ac7f/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 db6591619..8611610d9 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/b4a77ac7f/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 3dff68d00..2dcaf7820 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/b4a77ac7f/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 dbc69ef6c..b5265a2f2 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/b4a77ac7f/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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/b4a77ac7f/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/333994d45/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 454a198f7..77c8e6841 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 dce503db2..a31ffb49f 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.979</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:19.879</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.972</p></td>
+<td><p>00:19.873</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index d5f5d63e4..a21d0941f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -547,7 +547,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 24.11s!
+resnet18_v1 inference graph built in 21.33s!
</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 0887ecb97..11fb5ce26 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -565,7 +565,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.17s!
+yolov3-tiny inference graph built in 15.18s!
</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 c1bce1759..fb030fcf6 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:32.740</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:28.025</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.265</p></td>
+<td><p>00:46.767</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:44.475</p></td>
+<td><p>00:41.259</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 89bda5bcf..1d2b4b428 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.211</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.185</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.820</p></td>
+<td><p>00:02.795</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.391</p></td>
+<td><p>00:00.390</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 1ccdd5069..af067f402 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.731</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.709</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.382</p></td>
+<td><p>00:00.373</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.349</p></td>
+<td><p>00:00.337</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index a6890dc61..94378ca4e 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -545,7 +545,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.420 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 91.876 ms
</pre></div>
</div>
</div>
@@ -609,6 +609,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+.T
</pre></div>
</div>
</div>
@@ -619,6 +620,7 @@ 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 11.720 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 18227229e..d049c96e7 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -641,16 +641,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.67/9.67 result: MeasureResult(costs=(0.0277716648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.587357759475708, timestamp=1655423338.7361605) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.69/9.67 result: MeasureResult(costs=(0.09961413659999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.75498366355896, timestamp=1655423340.495578) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022760171399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5715122222900391, timestamp=1655423341.5399616) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.58/11.79 result: MeasureResult(costs=(0.1695307248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.836313009262085, timestamp=1655423344.927747) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.64/11.79 result: MeasureResult(costs=(0.0738259992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3164796829223633, timestamp=1655423346.3689651) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.70/11.79 result: MeasureResult(costs=(0.1575823816,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.687743902206421, timestamp=1655423349.0927753) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.85/11.79 result: MeasureResult(costs=(0.3175632158,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.194802522659302, timestamp=1655423354.8374522) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.24/11.79 result: MeasureResult(costs=(0.0262087616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5642800331115723, timestamp=1655423355.4232423) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.64/11.79 result: MeasureResult(costs=(0.16367640719999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.717639923095703, timestamp=1655423358.2610846) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.17/11.79 result: MeasureResult(costs=(0.12369548859999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.083334445953369, timestamp=1655423360.4037995) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.98/10.98 result: MeasureResult(costs=(0.024449573199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.521331787109375, timestamp=1655425724.245574) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.96/10.98 result: MeasureResult(costs=(0.0908326226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5962371826171875, timestamp=1655425726.342798) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 12.01/12.01 result: MeasureResult(costs=(0.022354579000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5843491554260254, timestamp=1655425726.9030123) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.87/12.01 result: MeasureResult(costs=(0.1435340632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4219417572021484, timestamp=1655425729.8526187) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.75/12.01 result: MeasureResult(costs=(0.0715465934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2833199501037598, timestamp=1655425731.267437) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.78/12.01 result: MeasureResult(costs=(0.1506930936,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.524484872817993, timestamp=1655425734.3145797) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/12.01 result: MeasureResult(costs=(0.3080363614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.03804612159729, timestamp=1655425739.4033012) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.90/12.01 result: MeasureResult(costs=(0.0246313948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5323412418365479, timestamp=1655425739.9579465) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.94/12.01 result: MeasureResult(costs=(0.13847948240000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3109400272369385, timestamp=1655425742.3885188) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.81/12.01 result: MeasureResult(costs=(0.095644071,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.629319190979004, timestamp=1655425744.0790825) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 5c437ff79..5d7fe4ee6 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -523,7 +523,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.3567338799112, 'median': 496.84443964979437, 'std': 1.5960987762688807}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 489.15848393004126, 'median': 488.8971324000522, 'std': 1.4240269798007845}
</pre></div>
</div>
</div>
@@ -678,179 +678,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 1/25] Current/Best: 6.17/ 17.43 GFLOPS | Progress: (8/20) | 9.06 s
-[Task 1/25] Current/Best: 11.51/ 22.64 GFLOPS | Progress: (12/20) | 11.55 s
-[Task 1/25] Current/Best: 16.78/ 22.74 GFLOPS | Progress: (16/20) | 13.23 s
-[Task 1/25] Current/Best: 11.54/ 23.75 GFLOPS | Progress: (20/20) | 14.96 s Done.
+[Task 1/25] Current/Best: 17.74/ 17.74 GFLOPS | Progress: (4/20) | 6.40 s
+[Task 1/25] Current/Best: 6.25/ 17.74 GFLOPS | Progress: (8/20) | 8.75 s
+[Task 1/25] Current/Best: 11.65/ 23.13 GFLOPS | Progress: (12/20) | 11.18 s
+[Task 1/25] Current/Best: 17.09/ 23.13 GFLOPS | Progress: (16/20) | 12.84 s
+[Task 1/25] Current/Best: 11.76/ 24.28 GFLOPS | Progress: (20/20) | 14.55 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.19/ 12.85 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 2/25] Current/Best: 14.29/ 18.63 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 20.99/ 20.99 GFLOPS | Progress: (12/20) | 6.34 s
-[Task 2/25] Current/Best: 12.25/ 20.99 GFLOPS | Progress: (16/20) | 7.60 s
-[Task 2/25] Current/Best: 19.07/ 20.99 GFLOPS | Progress: (20/20) | 9.22 s Done.
+[Task 2/25] Current/Best: 12.43/ 13.41 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 2/25] Current/Best: 14.21/ 17.94 GFLOPS | Progress: (8/20) | 4.97 s
+[Task 2/25] Current/Best: 21.28/ 21.28 GFLOPS | Progress: (12/20) | 6.30 s
+[Task 2/25] Current/Best: 13.02/ 21.28 GFLOPS | Progress: (16/20) | 7.58 s
+[Task 2/25] Current/Best: 20.30/ 21.28 GFLOPS | Progress: (20/20) | 9.17 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.79 s
-[Task 3/25] Current/Best: 15.59/ 16.92 GFLOPS | Progress: (8/20) | 7.70 s
-[Task 3/25] Current/Best: 14.87/ 16.92 GFLOPS | Progress: (12/20) | 9.40 s
-[Task 3/25] Current/Best: 7.21/ 23.83 GFLOPS | Progress: (16/20) | 11.29 s
-[Task 3/25] Current/Best: 12.09/ 23.83 GFLOPS | Progress: (20/20) | 15.87 s Done.
+[Task 3/25] Current/Best: 1.65/ 10.65 GFLOPS | Progress: (4/20) | 5.74 s
+[Task 3/25] Current/Best: 15.90/ 17.17 GFLOPS | Progress: (8/20) | 7.66 s
+[Task 3/25] Current/Best: 15.13/ 17.17 GFLOPS | Progress: (12/20) | 9.34 s
+[Task 3/25] Current/Best: 7.29/ 24.17 GFLOPS | Progress: (16/20) | 11.26 s
+[Task 3/25] Current/Best: 11.31/ 24.17 GFLOPS | Progress: (20/20) | 15.77 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.59/ 20.43 GFLOPS | Progress: (4/20) | 2.33 s
-[Task 4/25] Current/Best: 6.86/ 20.43 GFLOPS | Progress: (8/20) | 6.98 s
-[Task 4/25] Current/Best: 22.07/ 22.07 GFLOPS | Progress: (12/20) | 11.90 s
-[Task 4/25] Current/Best: 16.99/ 22.07 GFLOPS | Progress: (16/20) | 14.32 s
-[Task 4/25] Current/Best: 12.69/ 22.07 GFLOPS | Progress: (20/20) | 16.42 s Done.
+[Task 4/25] Current/Best: 9.65/ 20.67 GFLOPS | Progress: (4/20) | 2.33 s
+[Task 4/25] Current/Best: 6.93/ 20.67 GFLOPS | Progress: (8/20) | 6.95 s
+[Task 4/25] Current/Best: 22.74/ 22.74 GFLOPS | Progress: (12/20) | 11.89 s
+[Task 4/25] Current/Best: 17.81/ 22.74 GFLOPS | Progress: (16/20) | 14.23 s
+[Task 4/25] Current/Best: 13.77/ 22.74 GFLOPS | Progress: (20/20) | 16.28 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.71/ 10.37 GFLOPS | Progress: (4/20) | 2.52 s
-[Task 5/25] Current/Best: 11.75/ 12.74 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 5/25] Current/Best: 11.72/ 18.16 GFLOPS | Progress: (12/20) | 7.77 s
-[Task 5/25] Current/Best: 11.86/ 22.89 GFLOPS | Progress: (16/20) | 9.18 s
-[Task 5/25] Current/Best: 12.06/ 22.89 GFLOPS | Progress: (20/20) | 11.05 s Done.
+[Task 5/25] Current/Best: 9.55/ 10.41 GFLOPS | Progress: (4/20) | 2.49 s
+[Task 5/25] Current/Best: 11.80/ 12.67 GFLOPS | Progress: (8/20) | 4.54 s
+[Task 5/25] Current/Best: 11.56/ 18.31 GFLOPS | Progress: (12/20) | 7.67 s
+[Task 5/25] Current/Best: 11.89/ 22.47 GFLOPS | Progress: (16/20) | 9.07 s
+[Task 5/25] Current/Best: 12.15/ 22.47 GFLOPS | Progress: (20/20) | 10.97 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.26/ 20.72 GFLOPS | Progress: (4/20) | 4.05 s
-[Task 6/25] Current/Best: 18.86/ 20.72 GFLOPS | Progress: (8/20) | 5.83 s
-[Task 6/25] Current/Best: 13.28/ 20.72 GFLOPS | Progress: (12/20) | 7.77 s
-[Task 6/25] Current/Best: 19.76/ 20.72 GFLOPS | Progress: (16/20) | 10.03 s
-[Task 6/25] Current/Best: 3.75/ 20.72 GFLOPS | Progress: (20/20) | 12.58 s Done.
+[Task 6/25] Current/Best: 12.38/ 20.98 GFLOPS | Progress: (4/20) | 3.95 s
+[Task 6/25] Current/Best: 19.24/ 20.98 GFLOPS | Progress: (8/20) | 5.69 s
+[Task 6/25] Current/Best: 13.52/ 20.98 GFLOPS | Progress: (12/20) | 7.61 s
+[Task 6/25] Current/Best: 20.34/ 20.98 GFLOPS | Progress: (16/20) | 9.82 s
+[Task 6/25] Current/Best: 3.74/ 20.98 GFLOPS | Progress: (20/20) | 12.29 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.25/ 12.72 GFLOPS | Progress: (4/20) | 3.54 s
-[Task 7/25] Current/Best: 19.93/ 21.09 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 7/25] Current/Best: 16.09/ 21.09 GFLOPS | Progress: (12/20) | 6.95 s
-[Task 7/25] Current/Best: 12.23/ 21.09 GFLOPS | Progress: (16/20) | 9.00 s
-[Task 7/25] Current/Best: 6.45/ 21.69 GFLOPS | Progress: (20/20) | 11.46 s Done.
+[Task 7/25] Current/Best: 11.33/ 12.41 GFLOPS | Progress: (4/20) | 3.50 s
+[Task 7/25] Current/Best: 20.61/ 21.35 GFLOPS | Progress: (8/20) | 5.00 s
+[Task 7/25] Current/Best: 16.46/ 21.35 GFLOPS | Progress: (12/20) | 6.87 s
+[Task 7/25] Current/Best: 12.45/ 21.35 GFLOPS | Progress: (16/20) | 8.88 s
+[Task 7/25] Current/Best: 6.38/ 22.17 GFLOPS | Progress: (20/20) | 11.30 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.25/ 14.57 GFLOPS | Progress: (4/20) | 2.86 s
-[Task 8/25] Current/Best: 9.46/ 14.57 GFLOPS | Progress: (8/20) | 8.00 s
-[Task 8/25] Current/Best: 13.39/ 14.57 GFLOPS | Progress: (12/20) | 14.41 s
-[Task 8/25] Current/Best: 18.59/ 18.59 GFLOPS | Progress: (16/20) | 16.48 s
-[Task 8/25] Current/Best: 20.09/ 20.09 GFLOPS | Progress: (20/20) | 23.49 s Done.
+[Task 8/25] Current/Best: 9.95/ 13.98 GFLOPS | Progress: (4/20) | 2.80 s
+[Task 8/25] Current/Best: 9.24/ 13.98 GFLOPS | Progress: (8/20) | 7.74 s
+[Task 8/25] Current/Best: 12.38/ 13.98 GFLOPS | Progress: (12/20) | 14.14 s
+[Task 8/25] Current/Best: 19.11/ 19.11 GFLOPS | Progress: (16/20) | 16.23 s
+[Task 8/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (20/20) | 23.21 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.34/ 15.78 GFLOPS | Progress: (4/20) | 11.89 s
-[Task 9/25] Current/Best: 23.57/ 23.57 GFLOPS | Progress: (8/20) | 13.64 s
-[Task 9/25] Current/Best: 8.27/ 23.57 GFLOPS | Progress: (12/20) | 16.15 s
-[Task 9/25] Current/Best: 18.01/ 23.57 GFLOPS | Progress: (16/20) | 19.00 s
-[Task 9/25] Current/Best: 9.03/ 23.57 GFLOPS | Progress: (20/20) | 27.46 s
+[Task 9/25] Current/Best: 14.56/ 16.03 GFLOPS | Progress: (4/20) | 11.84 s
+[Task 9/25] Current/Best: 23.82/ 23.82 GFLOPS | Progress: (8/20) | 13.56 s
+[Task 9/25] Current/Best: 8.38/ 23.82 GFLOPS | Progress: (12/20) | 16.02 s
+[Task 9/25] Current/Best: 18.33/ 23.82 GFLOPS | Progress: (16/20) | 18.84 s
+[Task 9/25] Current/Best: 9.11/ 23.82 GFLOPS | Progress: (20/20) | 27.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (4/20) | 2.49 s
-[Task 10/25] Current/Best: 15.52/ 18.16 GFLOPS | Progress: (8/20) | 4.14 s
-[Task 10/25] Current/Best: 12.76/ 18.92 GFLOPS | Progress: (12/20) | 5.67 s
-[Task 10/25] Current/Best: 19.14/ 20.40 GFLOPS | Progress: (16/20) | 6.78 s
-[Task 10/25] Current/Best: 8.90/ 20.40 GFLOPS | Progress: (20/20) | 8.29 s Done.
+[Task 10/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (4/20) | 2.49 s
+[Task 10/25] Current/Best: 15.54/ 18.53 GFLOPS | Progress: (8/20) | 4.11 s
+[Task 10/25] Current/Best: 12.62/ 19.28 GFLOPS | Progress: (12/20) | 5.65 s
+[Task 10/25] Current/Best: 19.44/ 20.50 GFLOPS | Progress: (16/20) | 6.75 s
+[Task 10/25] Current/Best: 8.98/ 20.50 GFLOPS | Progress: (20/20) | 8.26 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.28/ 18.07 GFLOPS | Progress: (4/20) | 3.29 s
-[Task 11/25] Current/Best: 16.82/ 18.07 GFLOPS | Progress: (8/20) | 6.09 s
-[Task 11/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 11/25] Current/Best: 12.39/ 21.16 GFLOPS | Progress: (16/20) | 11.07 s
-[Task 11/25] Current/Best: 19.43/ 21.45 GFLOPS | Progress: (20/20) | 13.16 s Done.
+[Task 11/25] Current/Best: 12.48/ 18.45 GFLOPS | Progress: (4/20) | 3.29 s
+[Task 11/25] Current/Best: 17.05/ 18.45 GFLOPS | Progress: (8/20) | 6.08 s
+[Task 11/25] Current/Best: 18.45/ 18.45 GFLOPS | Progress: (12/20) | 8.09 s
+[Task 11/25] Current/Best: 13.67/ 21.43 GFLOPS | Progress: (16/20) | 11.02 s
+[Task 11/25] Current/Best: 19.69/ 21.86 GFLOPS | Progress: (20/20) | 13.07 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.79/ 18.18 GFLOPS | Progress: (4/20) | 5.63 s
-[Task 12/25] Current/Best: 5.27/ 18.18 GFLOPS | Progress: (8/20) | 9.59 s
-[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 11.59 s
-[Task 12/25] Current/Best: 13.38/ 18.95 GFLOPS | Progress: (16/20) | 14.54 s
-[Task 12/25] Current/Best: 15.13/ 18.95 GFLOPS | Progress: (20/20) | 16.48 s Done.
+[Task 12/25] Current/Best: 7.95/ 18.21 GFLOPS | Progress: (4/20) | 5.58 s
+[Task 12/25] Current/Best: 5.22/ 18.21 GFLOPS | Progress: (8/20) | 9.45 s
+[Task 12/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (12/20) | 11.40 s
+[Task 12/25] Current/Best: 15.45/ 19.21 GFLOPS | Progress: (16/20) | 14.25 s
+[Task 12/25] Current/Best: 15.35/ 19.21 GFLOPS | Progress: (20/20) | 16.16 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.71/ 17.14 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 13/25] Current/Best: 15.55/ 20.76 GFLOPS | Progress: (8/20) | 6.33 s
-[Task 13/25] Current/Best: 19.42/ 21.40 GFLOPS | Progress: (12/20) | 9.39 s
-[Task 13/25] Current/Best: 12.22/ 21.40 GFLOPS | Progress: (16/20) | 12.84 s
-[Task 13/25] Current/Best: 18.59/ 21.40 GFLOPS | Progress: (20/20) | 15.16 s Done.
+[Task 13/25] Current/Best: 8.80/ 17.56 GFLOPS | Progress: (4/20) | 3.67 s
+[Task 13/25] Current/Best: 16.40/ 21.19 GFLOPS | Progress: (8/20) | 6.23 s
+[Task 13/25] Current/Best: 19.84/ 21.66 GFLOPS | Progress: (12/20) | 9.22 s
+[Task 13/25] Current/Best: 12.50/ 21.66 GFLOPS | Progress: (16/20) | 12.59 s
+[Task 13/25] Current/Best: 19.02/ 21.66 GFLOPS | Progress: (20/20) | 14.85 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.50/ 13.50 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 14/25] Current/Best: 6.07/ 13.50 GFLOPS | Progress: (8/20) | 5.47 s
-[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 8.18 s
-[Task 14/25] Current/Best: 15.59/ 20.32 GFLOPS | Progress: (16/20) | 9.90 s Done.
+[Task 14/25] Current/Best: 13.84/ 13.84 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 14/25] Current/Best: 6.20/ 13.84 GFLOPS | Progress: (8/20) | 5.44 s
+[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 8.04 s
+[Task 14/25] Current/Best: 18.38/ 20.49 GFLOPS | Progress: (16/20) | 9.66 s Done.
-[Task 14/25] Current/Best: 17.07/ 20.32 GFLOPS | Progress: (20/20) | 11.63 s
+[Task 14/25] Current/Best: 17.44/ 20.49 GFLOPS | Progress: (20/20) | 11.32 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.13/ 17.54 GFLOPS | Progress: (4/20) | 2.69 s
-[Task 15/25] Current/Best: 14.14/ 17.91 GFLOPS | Progress: (8/20) | 4.05 s
-[Task 15/25] Current/Best: 10.37/ 21.83 GFLOPS | Progress: (12/20) | 6.29 s
-[Task 15/25] Current/Best: 20.38/ 21.83 GFLOPS | Progress: (16/20) | 9.57 s
-[Task 15/25] Current/Best: 9.68/ 21.83 GFLOPS | Progress: (20/20) | 10.59 s
+[Task 15/25] Current/Best: 16.48/ 17.88 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 15/25] Current/Best: 14.68/ 18.41 GFLOPS | Progress: (8/20) | 3.89 s
+[Task 15/25] Current/Best: 10.50/ 22.63 GFLOPS | Progress: (12/20) | 6.07 s
+[Task 15/25] Current/Best: 20.59/ 22.63 GFLOPS | Progress: (16/20) | 9.05 s
+[Task 15/25] Current/Best: 9.86/ 22.63 GFLOPS | Progress: (20/20) | 10.01 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (4/20) | 2.92 s
-[Task 16/25] Current/Best: 3.04/ 20.35 GFLOPS | Progress: (8/20) | 4.56 s
-[Task 16/25] Current/Best: 19.25/ 20.35 GFLOPS | Progress: (12/20) | 5.79 s
-[Task 16/25] Current/Best: 17.76/ 20.35 GFLOPS | Progress: (16/20) | 7.19 s
-[Task 16/25] Current/Best: 9.99/ 22.29 GFLOPS | Progress: (20/20) | 9.36 s Done.
+[Task 16/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (4/20) | 2.79 s
+[Task 16/25] Current/Best: 3.06/ 20.87 GFLOPS | Progress: (8/20) | 4.38 s
+[Task 16/25] Current/Best: 19.78/ 20.87 GFLOPS | Progress: (12/20) | 5.58 s
+[Task 16/25] Current/Best: 18.06/ 20.87 GFLOPS | Progress: (16/20) | 6.91 s
+[Task 16/25] Current/Best: 10.22/ 22.92 GFLOPS | Progress: (20/20) | 9.01 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.87/ 18.81 GFLOPS | Progress: (4/20) | 4.79 s
-[Task 17/25] Current/Best: 14.40/ 22.62 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 17/25] Current/Best: 17.25/ 22.62 GFLOPS | Progress: (12/20) | 9.82 s
-[Task 17/25] Current/Best: 16.41/ 22.62 GFLOPS | Progress: (16/20) | 12.02 s
-[Task 17/25] Current/Best: 10.01/ 22.62 GFLOPS | Progress: (20/20) | 14.20 s Done.
+[Task 17/25] Current/Best: 12.94/ 19.17 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 17/25] Current/Best: 14.48/ 23.72 GFLOPS | Progress: (8/20) | 7.50 s
+[Task 17/25] Current/Best: 17.21/ 23.72 GFLOPS | Progress: (12/20) | 9.54 s
+[Task 17/25] Current/Best: 16.77/ 23.72 GFLOPS | Progress: (16/20) | 11.72 s
+[Task 17/25] Current/Best: 10.20/ 23.72 GFLOPS | Progress: (20/20) | 13.82 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.07/ 17.88 GFLOPS | Progress: (4/20) | 3.82 s
-[Task 18/25] Current/Best: 10.59/ 19.12 GFLOPS | Progress: (8/20) | 7.55 s
-[Task 18/25] Current/Best: 19.47/ 19.47 GFLOPS | Progress: (12/20) | 9.48 s
-[Task 18/25] Current/Best: 9.90/ 19.47 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.93 s Done.
+[Task 18/25] Current/Best: 11.43/ 18.53 GFLOPS | Progress: (4/20) | 3.66 s
+[Task 18/25] Current/Best: 10.69/ 20.08 GFLOPS | Progress: (8/20) | 7.25 s
+[Task 18/25] Current/Best: 19.71/ 20.08 GFLOPS | Progress: (12/20) | 9.13 s
+[Task 18/25] Current/Best: 10.20/ 20.08 GFLOPS | Progress: (16/20) | 12.91 s
+[Task 18/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (20/20) | 14.40 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.98/ 20.05 GFLOPS | Progress: (4/20) | 6.10 s
-[Task 19/25] Current/Best: 2.60/ 20.05 GFLOPS | Progress: (8/20) | 9.46 s
-[Task 19/25] Current/Best: 19.67/ 21.84 GFLOPS | Progress: (12/20) | 12.38 s
-[Task 19/25] Current/Best: 14.91/ 21.88 GFLOPS | Progress: (16/20) | 15.33 s
-[Task 19/25] Current/Best: 2.70/ 23.58 GFLOPS | Progress: (20/20) | 18.12 s Done.
+[Task 19/25] Current/Best: 7.29/ 20.90 GFLOPS | Progress: (4/20) | 5.94 s
+[Task 19/25] Current/Best: 2.65/ 20.90 GFLOPS | Progress: (8/20) | 9.27 s
+[Task 19/25] Current/Best: 20.47/ 22.27 GFLOPS | Progress: (12/20) | 12.19 s
+[Task 19/25] Current/Best: 14.40/ 22.27 GFLOPS | Progress: (16/20) | 15.16 s
+[Task 19/25] Current/Best: 2.74/ 24.29 GFLOPS | Progress: (20/20) | 17.95 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.13/ 15.43 GFLOPS | Progress: (4/20) | 3.22 s Done.
+[Task 20/25] Current/Best: 9.63/ 15.05 GFLOPS | Progress: (4/20) | 3.25 s Done.
Done.
-[Task 20/25] Current/Best: 9.66/ 15.43 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 20/25] Current/Best: 2.32/ 16.60 GFLOPS | Progress: (12/20) | 10.52 s
-[Task 20/25] Current/Best: 12.47/ 16.60 GFLOPS | Progress: (16/20) | 14.43 s
-[Task 20/25] Current/Best: 12.13/ 22.02 GFLOPS | Progress: (20/20) | 16.53 s
+[Task 20/25] Current/Best: 9.75/ 15.05 GFLOPS | Progress: (8/20) | 6.75 s
+[Task 20/25] Current/Best: 2.36/ 16.65 GFLOPS | Progress: (12/20) | 10.83 s
+[Task 20/25] Current/Best: 12.49/ 16.65 GFLOPS | Progress: (16/20) | 14.50 s
+[Task 20/25] Current/Best: 12.25/ 22.67 GFLOPS | Progress: (20/20) | 16.56 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.42/ 17.66 GFLOPS | Progress: (4/20) | 3.20 s
-[Task 21/25] Current/Best: 14.66/ 17.66 GFLOPS | Progress: (8/20) | 4.78 s
-[Task 21/25] Current/Best: 1.61/ 17.66 GFLOPS | Progress: (12/20) | 6.88 s
-[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.39 s
-[Task 21/25] Current/Best: 4.45/ 17.91 GFLOPS | Progress: (20/20) | 17.58 s
+[Task 21/25] Current/Best: 6.52/ 18.01 GFLOPS | Progress: (4/20) | 3.14 s
+[Task 21/25] Current/Best: 14.91/ 18.01 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 21/25] Current/Best: 1.64/ 18.01 GFLOPS | Progress: (12/20) | 6.78 s
+[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.20 s
+[Task 21/25] Current/Best: 4.54/ 18.05 GFLOPS | Progress: (20/20) | 17.33 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.71/ 16.81 GFLOPS | Progress: (4/20) | 2.60 s
-[Task 22/25] Current/Best: 8.89/ 21.92 GFLOPS | Progress: (8/20) | 4.63 s
-[Task 22/25] Current/Best: 20.03/ 21.92 GFLOPS | Progress: (12/20) | 6.98 s
-[Task 22/25] Current/Best: 15.37/ 21.92 GFLOPS | Progress: (16/20) | 9.07 s
-[Task 22/25] Current/Best: 14.21/ 21.92 GFLOPS | Progress: (20/20) | 10.73 s Done.
+[Task 22/25] Current/Best: 2.74/ 17.27 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 22/25] Current/Best: 8.80/ 22.37 GFLOPS | Progress: (8/20) | 4.60 s
+[Task 22/25] Current/Best: 20.25/ 22.37 GFLOPS | Progress: (12/20) | 6.96 s
+[Task 22/25] Current/Best: 15.67/ 22.37 GFLOPS | Progress: (16/20) | 9.05 s
+[Task 22/25] Current/Best: 14.30/ 22.37 GFLOPS | Progress: (20/20) | 10.69 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.70/ 20.93 GFLOPS | Progress: (4/20) | 3.12 s
-[Task 23/25] Current/Best: 14.23/ 20.93 GFLOPS | Progress: (8/20) | 6.56 s
-[Task 23/25] Current/Best: 21.03/ 21.94 GFLOPS | Progress: (12/20) | 8.36 s
-[Task 23/25] Current/Best: 6.34/ 21.94 GFLOPS | Progress: (16/20) | 15.62 s
-[Task 23/25] Current/Best: 7.56/ 21.94 GFLOPS | Progress: (20/20) | 19.91 s Done.
+[Task 23/25] Current/Best: 17.90/ 21.15 GFLOPS | Progress: (4/20) | 3.12 s
+[Task 23/25] Current/Best: 14.44/ 21.15 GFLOPS | Progress: (8/20) | 6.53 s
+[Task 23/25] Current/Best: 21.33/ 22.27 GFLOPS | Progress: (12/20) | 8.31 s
+[Task 23/25] Current/Best: 6.46/ 22.27 GFLOPS | Progress: (16/20) | 15.16 s
+[Task 23/25] Current/Best: 7.97/ 22.27 GFLOPS | Progress: (20/20) | 19.28 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.44/ 8.44 GFLOPS | Progress: (4/20) | 11.77 s
-[Task 24/25] Current/Best: 1.89/ 8.44 GFLOPS | Progress: (8/20) | 22.77 s
-[Task 24/25] Current/Best: 4.39/ 8.44 GFLOPS | Progress: (12/20) | 34.29 s Done.
+[Task 24/25] Current/Best: 8.34/ 8.34 GFLOPS | Progress: (4/20) | 11.71 s
+[Task 24/25] Current/Best: 2.06/ 8.34 GFLOPS | Progress: (8/20) | 22.67 s
+[Task 24/25] Current/Best: 4.28/ 8.34 GFLOPS | Progress: (12/20) | 34.14 s Done.
Done.
-[Task 24/25] Current/Best: 6.81/ 8.60 GFLOPS | Progress: (16/20) | 40.22 s
-[Task 24/25] Current/Best: 3.23/ 8.85 GFLOPS | Progress: (20/20) | 46.34 s Done.
+[Task 24/25] Current/Best: 6.11/ 9.17 GFLOPS | Progress: (16/20) | 39.73 s
+[Task 24/25] Current/Best: 3.47/ 9.17 GFLOPS | Progress: (20/20) | 45.64 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.54/ 2.91 GFLOPS | Progress: (4/20) | 11.60 s
-[Task 25/25] Current/Best: 5.80/ 7.85 GFLOPS | Progress: (8/20) | 22.88 s
-[Task 25/25] Current/Best: 5.97/ 7.85 GFLOPS | Progress: (12/20) | 34.14 s
-[Task 25/25] Current/Best: 5.82/ 8.67 GFLOPS | Progress: (16/20) | 35.95 s
-[Task 25/25] Current/Best: 2.83/ 8.67 GFLOPS | Progress: (20/20) | 46.68 s
+[Task 25/25] Current/Best: 1.57/ 2.80 GFLOPS | Progress: (4/20) | 11.51 s
+[Task 25/25] Current/Best: 6.24/ 8.25 GFLOPS | Progress: (8/20) | 22.72 s
+[Task 25/25] Current/Best: 6.13/ 8.25 GFLOPS | Progress: (12/20) | 33.94 s
+[Task 25/25] Current/Best: 6.07/ 9.11 GFLOPS | Progress: (16/20) | 35.63 s
+[Task 25/25] Current/Best: 2.92/ 9.25 GFLOPS | Progress: (20/20) | 46.33 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -953,8 +953,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 413.3635271499952, 'median': 412.78412854990165, 'std': 2.080394213480733}
-unoptimized: {'mean': 496.3567338799112, 'median': 496.84443964979437, 'std': 1.5960987762688807}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 396.4592194200668, 'median': 395.67348075015616, 'std': 1.9716355693665089}
+unoptimized: {'mean': 489.15848393004126, 'median': 488.8971324000522, 'std': 1.4240269798007845}
</pre></div>
</div>
</div>
@@ -968,7 +968,7 @@ 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> ( 10 minutes 27.969 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 9.590 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python 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 e861106eb..43cda1a03 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -499,7 +499,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.264e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.268e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index e8bb4ed68..7e2588740 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -459,7 +459,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x20212070)), stage(b, placeholder(b, 0x21a99110)), 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=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2025d900)), stage(b, placeholder(b, 0x21df3b10)), 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=[ [...]
</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 6d09005ff..2d602b9fc 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>13:12.143</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:13.543</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,42 +312,42 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><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></td>
-<td><p>10:27.969</p></td>
+<td><p>10:09.590</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
-<td><p>00:59.791</p></td>
+<tr class="row-even"><td><p><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></td>
+<td><p>01:11.720</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>00:49.364</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>01:00.636</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:28.341</p></td>
+<td><p>00:27.260</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:25.094</p></td>
+<td><p>00:23.063</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
-<td><p>00:00.769</p></td>
+<tr class="row-even"><td><p><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></td>
+<td><p>00:00.651</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.668</p></td>
+<tr class="row-odd"><td><p><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></td>
+<td><p>00:00.487</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.147</p></td>
+<td><p>00:00.137</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
+<tr class="row-even"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
@@ -355,7 +355,7 @@
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
+<tr class="row-even"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 375f108ee..f296be3f2 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -607,7 +607,7 @@ factor to be the number of threads on your CPU.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vector: 0.000025
+vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -640,10 +640,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.190530024876352e-06 1.0
- naive 5.853599999999999e-06 0.7146790234846087
-parallel 6.1469e-06 0.7504886718357151
- vector 2.4507e-05 2.9921140543490004
+ numpy 7.506799993279856e-06 1.0
+ naive 5.7591000000000005e-06 0.7671844201464793
+parallel 5.8953999999999995e-06 0.7853412912662661
+ vector 2.38423e-05 3.1760936779112017
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -959,7 +959,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019471
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016072
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1002,7 +1002,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.270069
+none: 3.441797
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1069,7 +1069,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.326683
+blocking: 0.292769
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1130,7 +1130,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.351616
+vectorization: 0.328208
@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], []),
@@ -1187,7 +1187,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.120809
+loop permutation: 0.113438
@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], []),
@@ -1265,7 +1265,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.111510
+array packing: 0.106714
@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], []),
@@ -1341,7 +1341,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.111313
+block caching: 0.108925
@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], []),
@@ -1410,7 +1410,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.143911
+parallelization: 0.142040
@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], []),
@@ -1472,13 +1472,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.270069246 1.0
- blocking 0.3266827326 0.09990086081498228
- vectorization 0.3516162646 0.10752563268502725
-loop permutation 0.1208091131 0.03694390057573723
- array packing 0.11150971219999999 0.034100107310082325
- block caching 0.11131297340000001 0.03403994381347117
- parallelization 0.14391054509999998 0.044008409080643664
+ none 3.4417968634999996 1.0
+ blocking 0.2927686107 0.08506272226719402
+ vectorization 0.3282077072 0.09535940679144035
+loop permutation 0.11343817870000002 0.03295899880176064
+ array packing 0.1067137891 0.031005254909635085
+ block caching 0.10892510979999999 0.0316477450936
+ parallelization 0.14204011889999998 0.04126917553046924
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1510,6 +1510,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.636 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>