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 2022/08/24 17:05:39 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@038523e5a21e13ff2802913ec32b73fb47413b35)
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 b0b462377 deploying docs (apache/tvm@038523e5a21e13ff2802913ec32b73fb47413b35)
b0b462377 is described below
commit b0b462377b412d4b193d628576850c05ac58a13f
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Aug 24 17:05:33 2022 +0000
deploying docs (apache/tvm@038523e5a21e13ff2802913ec32b73fb47413b35)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 375 +++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 31 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../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 | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 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 | 4 +-
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 | 44 +--
docs/commit_hash | 2 +-
docs/genindex.html | 10 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 11 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 36 +-
docs/how_to/deploy_models/deploy_prequantized.html | 7 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 375 +++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 31 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
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 | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/objects.inv | Bin 23304 -> 23323 bytes
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 191 +++++++----
.../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 | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +--
125 files changed, 1633 insertions(+), 998 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 4918cdb7d..cd79df55c 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.634 seconds)
+ **Total running time of the script:** ( 1 minutes 2.155 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
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 f908d3aac..82750a02c 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipaf84c463-677d-4cff-ba73-43f731bd1cc3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4276bc4f-ed00-46c4-bfe5-5e2a88f38344 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 3a30fea90..5914ba6b8 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 50.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 65.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 57.7MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.2MB/s]
93%|#########2| 38.4M/41.5M [00:00<00:00, 64.4MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 63.7MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 64.3MB/s]
30%|### | 12.5M/41.5M [00:00<00:00, 53.1MB/s]
42%|####2 | 17.6M/41.5M [00:00<00:00, 39.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 42.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 53.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 50.7MB/s]
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 0521614ba..8e28be023 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###6 | 16.5M/44.7M [00:00<00:00, 172MB/s]
88%|########8 | 39.5M/44.7M [00:00<00:00, 213MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 208MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
7%|7 | 3.20M/44.7M [00:00<00:01, 33.0MB/s]
14%|#4 | 6.35M/44.7M [00:00<00:01, 30.5MB/s]
28%|##7 | 12.4M/44.7M [00:00<00:00, 44.0MB/s]
40%|###9 | 17.7M/44.7M [00:00<00:00, 48.7MB/s]
60%|###### | 27.0M/44.7M [00:00<00:00, 65.8MB/s]
81%|########1 | 36.3M/44.7M [00:00<00:00, 74.1MB/s]
97%|#########7| 43.4M/44.7M [00:00<00:00, 54.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 54.1MB/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 62a754d75..1e5be9297 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.389 seconds)
+ **Total running time of the script:** ( 1 minutes 0.744 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 69323f3a5..6aa07af8a 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
=================
-**05:00.033** total execution time for **how_to_compile_models** files:
+**05:06.148** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.634 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:02.155 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.389 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:00.744 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.090 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.597 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.222 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.799 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.950 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.521 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.088 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.179 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.908 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.742 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.254 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.396 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.564 | 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 5b1b2a6be..d16a3a9cc 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9719 15.9607 16.2666 15.7528 0.1290
+ 15.5554 15.5336 15.7682 15.4656 0.0898
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 1da6dd7dc..b565defbf 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
@@ -123,7 +123,7 @@ 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]
11%|# | 18.2M/170M [00:00<00:00, 190MB/s]
26%|##6 | 44.2M/170M [00:00<00:00, 239MB/s]
40%|#### | 68.2M/170M [00:00<00:00, 245MB/s]
54%|#####4 | 92.4M/170M [00:00<00:00, 248MB/s]
69%|######8 | 117M/170M [00:00<00:00, 251MB/s]
83%|########3 | 141M/170M [00:00<00:00, 253MB/s]
99%|#########9| 169M/170M [00:00<00:00, 265MB/s]
100%|##########| 170M/170M [00:00<00:00, 253MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.21M/170M [00:00<00:03, 54.6MB/s]
7%|6 | 11.1M/170M [00:00<00:02, 58.9MB/s]
11%|# | 18.5M/170M [00:00<00:02, 67.2MB/s]
15%|#5 | 26.1M/170M [00:00<00:02, 72.3MB/s]
19%|#9 | 33.0M/170M [00:00<00:02, 63.5MB/s]
24%|##3 | 40.2M/170M [00:00<00:02, 67.2MB/s]
28%|##7 | 46.8M/170M [00:00<00:01, 64.6MB/s]
31%|###1 | 53.3M/170M [00:00<00:01, 65.6MB/s]
35%|###5 | 59.6M/170M [00:00<00:01, 65.5MB/s]
39%|###8 | 65.9M/170M [00:01<00:01, 58.3MB/s]
43%|####3 | 73.7M/170M [00:01<00:01, 64.6MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 59.4MB/s]
51%|##### | 85.9M/170M [00:01<00:01, 57.5MB/s]
54%|#####3 | 91.5M/170M [00:01<00:01, 56.1MB/s]
58%|#####7 | 98.3M/170M [00:01<00:01, 60.3MB/s]
62%|######2 | 106M/170M [00:01<00:01, 64.9MB/s]
66%|######5 | 112M/170M [00:01<00:00, 63.5MB/s
]
70%|######9 | 119M/170M [00:01<00:00, 65.2MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 67.6MB/s]
78%|#######7 | 132M/170M [00:02<00:00, 46.8MB/s]
82%|########1 | 139M/170M [00:02<00:00, 51.5MB/s]
86%|########5 | 145M/170M [00:02<00:00, 55.9MB/s]
90%|########9 | 152M/170M [00:02<00:00, 60.4MB/s]
94%|#########3| 159M/170M [00:02<00:00, 64.0MB/s]
98%|#########7| 166M/170M [00:02<00:00, 66.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 61.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 56.902 seconds)
+ **Total running time of the script:** ( 2 minutes 54.561 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 8ba40c5b9..cc3a5511c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ 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, 185MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
56%|#####6 | 7.66M/13.6M [00:00<00:00, 80.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 85.3MB/s]
@@ -412,7 +412,7 @@ 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)
- 90.4422 90.0267 115.0666 89.8931 2.5116
+ 89.9606 89.9258 90.5808 89.7724 0.1615
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.414 seconds)
+ **Total running time of the script:** ( 1 minutes 7.848 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 b08282253..153f5ce5a 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
@@ -439,7 +439,7 @@ 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)
- 120.1325 120.0947 123.4845 119.5897 0.4378
+ 118.8230 118.7278 125.9085 117.1407 0.9966
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 51.736 seconds)
+ **Total running time of the script:** ( 1 minutes 51.469 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 62675e93a..f94c0173b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.107 seconds)
+ **Total running time of the script:** ( 1 minutes 31.726 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 ceb1c6b6e..38aa9d994 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
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6622/132723 [00:00<00:01, 66209.01KB/s]
11%|#1 | 14766/132723 [00:00<00:01, 75163.21KB/s]
17%|#7 | 22866/132723 [00:00<00:01, 77826.73KB/s]
23%|##3 | 30941/132723 [00:00<00:01, 78977.95KB/s]
29%|##9 | 39059/132723 [00:00<00:01, 79768.99KB/s]
36%|###5 | 47194/132723 [00:00<00:01, 80304.18KB/s]
42%|####1 | 55379/132723 [00:00<00:00, 80808.34KB/s]
48%|####7 | 63473/132723 [00:00<00:00, 80845.37KB/s]
54%|#####3 | 71666/132723 [00:00<00:00, 81180.81KB/s]
60%|###### | 79841/132723 [00:01<00:00, 81353.55KB/s]
66%|######6 | 87997/132723 [00:01<00:00, 81413.13KB/s]
72%|#######2 | 96213/132723 [00:01<00:00, 81636.61KB/s]
79%|#######8 | 104377/132723 [00:01<00:00, 81529.26KB/s]
85%|########4 | 112530/132723 [00:01<00:00, 81495.50KB/s]
91%|######### | 120682/132723 [00:01<00:00, 81499.63KB/s]
97%|########
#7| 128868/132723 [00:01<00:00, 81605.65KB/s]
100%|##########| 132723/132723 [00:01<00:00, 80475.49KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3601/132723 [00:00<00:03, 36005.48KB/s]
7%|7 | 9727/132723 [00:00<00:02, 50858.06KB/s]
13%|#3 | 17631/132723 [00:00<00:01, 63722.48KB/s]
20%|#9 | 26195/132723 [00:00<00:01, 72372.09KB/s]
25%|##5 | 33433/132723 [00:00<00:01, 61690.61KB/s]
31%|###1 | 41350/132723 [00:00<00:01, 67021.47KB/s]
37%|###7 | 49140/132723 [00:00<00:01, 67980.72KB/s]
43%|####3 | 57640/132723 [00:00<00:01, 73005.77KB/s]
49%|####9 | 65523/132723 [00:00<00:00, 71598.58KB/s]
55%|#####5 | 73054/132723 [00:01<00:00, 72668.42KB/s]
61%|###### | 80396/132723 [00:01<00:00, 65841.54KB/s]
66%|######5 | 87462/132723 [00:01<00:00, 67158.40KB/s]
72%|#######2 | 96025/132723 [00:01<00:00, 72349.88KB/s]
78%|#######7 | 103386/132723 [00:01<00:00, 64296.36KB/s]
84%|########4 | 111924/132723 [00:01<00:00, 69897.89KB/s]
90%|########9
| 119153/132723 [00:01<00:00, 61415.14KB/s]
96%|#########6| 127575/132723 [00:01<00:00, 67227.12KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67286.45KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 37.229 seconds)
+ **Total running time of the script:** ( 2 minutes 33.677 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 5b6e34620..7ea58de23 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
@@ -5,24 +5,24 @@
Computation times
=================
-**11:05.297** total execution time for **how_to_deploy_models** files:
+**11:11.814** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:56.902 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:54.561 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:37.229 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:33.677 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.736 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.469 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:17.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:31.726 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.414 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.848 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.958 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.008 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:21.971 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.727 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.548 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 102f5f1d2..30bad24f5 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
@@ -476,7 +476,7 @@ 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.zip68faa473-ff07-4865-9f37-c414c57e207f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip66792731-faea-4dba-b9bf-6fcdf29913aa from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 3ca101c7e..763545784 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
=================
-**00:42.144** total execution time for **how_to_extend_tvm** files:
+**00:40.605** 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``) | 00:38.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.557 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.244 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.135 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.968 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.906 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 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 |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 78ebf6417..b72537972 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
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6678us [6678us] (46.01%; 46.01%)
- FoldScaleAxis: 7834us [6us] (53.99%; 53.99%)
- FoldConstant: 7829us [1627us] (53.95%; 99.93%)
- InferType: 6202us [6202us] (42.74%; 79.22%)
+ InferType: 6769us [6769us] (46.20%; 46.20%)
+ FoldScaleAxis: 7882us [5us] (53.80%; 53.80%)
+ FoldConstant: 7876us [1641us] (53.76%; 99.93%)
+ InferType: 6235us [6235us] (42.56%; 79.16%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6253us [6253us] (43.24%; 43.24%)
- FoldScaleAxis: 8209us [4us] (56.76%; 56.76%)
- FoldConstant: 8204us [1702us] (56.73%; 99.95%)
- InferType: 6503us [6503us] (44.96%; 79.26%)
+ InferType: 6311us [6311us] (44.88%; 44.88%)
+ FoldScaleAxis: 7752us [4us] (55.12%; 55.12%)
+ FoldConstant: 7747us [1604us] (55.09%; 99.95%)
+ InferType: 6143us [6143us] (43.69%; 79.30%)
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 818461e1f..cdb02b3ab 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
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 49.141609 ms
+ Convolution: 50.695199 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 2ca935d8e..a27e3ecc8 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
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.657923 ms
+ conv2d with tensor core: 6.696495 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 bbc8c6e39..aabd2adbc 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018327
- Baseline: 3.438462
+ Numpy running time: 0.017770
+ Baseline: 3.280152
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.309396
+ Opt1: 0.303941
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.341529
+ Opt2: 0.333138
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118068
+ Opt3: 0.113462
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112702
+ Opt4: 0.109358
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111174
+ Opt5: 0.110568
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147364
+ Opt6: 0.145905
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 d73631885..a586e223a 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
=================
-**00:34.798** total execution time for **how_to_optimize_operators** files:
+**00:33.868** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.709 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.189 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.970 | 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 59a54395b..5ddaa83d7 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
=================
-**06:09.753** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:05.289** 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``) | 03:23.985 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:20.275 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.109 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.715 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.743 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.235 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:18.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.863 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.802 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.705 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.588 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.496 | 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 7c94248b0..5aac1b271 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
@@ -241,10 +241,10 @@ cooperative fetching, unrolling and operator fusion.
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -252,27 +252,178 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 9) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer [...]
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)) < 24), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2)] = kernel[((((((blockIdx.x*36864) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*8) + threadIdx.x_2), 24), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fused.ax2.fused.ax3. [...]
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*576)
+ {
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 144) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4) + floordiv(threadIdx.x_1, 7)), 9)) && (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4) + floordiv(threadIdx.x_1, 7)), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx. [...]
}
- }
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 28), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 252)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 140), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 168), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 56), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 224), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 252), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 308)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 308), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 364), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 172), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 420)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 420), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 476)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 476), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 92), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 532)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 532), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 148), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 644)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 644), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 700)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 700), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 124), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 756)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 756), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 60), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 812)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 812), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 44), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 868)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 868), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 100), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 924)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 924), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 52)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1008), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1036)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1036), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 76), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1092)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1092), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 44)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1148)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1148), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1204)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1204), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1260)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1260), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 36)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1316)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1316), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1428)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1428), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1484)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1484), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ for (rc.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ }
}
}
}
@@ -284,6 +435,13 @@ cooperative fetching, unrolling and operator fusion.
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 196)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 203)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 210)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 217)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 224)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 231)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 238)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
}
}
@@ -337,7 +495,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.390 ms
+ Execution time of this operator: 0.288 ms
@@ -387,8 +545,8 @@ 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=8)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
@@ -397,19 +555,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_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=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_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=8)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
@@ -434,14 +592,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ 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=28)
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=56)
+ 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=28)
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", 0)
+ 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:
@@ -459,10 +617,10 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[192];
+ extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -470,27 +628,121 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 9; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x))] = (((((1 <= (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer)) && ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2 [...]
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 144; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + ((int)threadIdx.x))] = (((((1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4) + (((int)threadIdx.x) / 7)) % 9)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4) + (((int)threadIdx.x) / 7)) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer [...]
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) < 24) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x))] = kernel[((((((((int)blockIdx.x) * 36864) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 8) + ((int)threadIdx.x)) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3))];
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 28)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 252)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 140) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 56) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 252)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 180)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 88) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 308)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 116) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 432)];
+ kernel_shared[(((int)threadIdx.x) + 364)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 172) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 420)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 420) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 108)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 476)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 476) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 92) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 360)];
+ kernel_shared[(((int)threadIdx.x) + 532)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 532) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 148) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 644)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 644) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 68) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 288)];
+ kernel_shared[(((int)threadIdx.x) + 700)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 700) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 124) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 152) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 756)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 756) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 60) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 812)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 812) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 44) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 216)];
+ kernel_shared[(((int)threadIdx.x) + 868)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 868) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 100) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 128) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 924)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 924) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 468)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 184) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 20) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1036)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1036) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 76) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 104) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1092)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1092) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 396)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 160) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1148)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1148) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 188) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1204)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1204) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 52) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1260)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1260) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 324)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 136) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1316)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1316) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 164) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1428)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1428) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 252)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1484)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1484) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 140) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 504)];
}
__syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
}
}
}
@@ -502,6 +754,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 196)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 203)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 210)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 217)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 224)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 231)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 238)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
}
@@ -562,7 +821,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 23.985 seconds)
+ **Total running time of the script:** ( 3 minutes 20.275 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 5ca445299..e6b418fa8 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
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.4363 9.4414 9.4586 9.4090 0.0206
+ 9.8768 9.8922 9.9026 9.8356 0.0294
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 d02e584f1..6e7baba82 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
@@ -666,7 +666,7 @@ 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)
- 760.1900 759.5860 761.8455 759.1385 1.1848
+ 748.9067 748.0110 750.8205 747.8886 1.3542
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.109 seconds)
+ **Total running time of the script:** ( 1 minutes 21.715 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 d21b4265f..16a754451 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
@@ -397,29 +397,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer: int32, 0, 2) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ for (i.outer.inner: int32, 0, 16) {
for (i.inner.init: int32, 0, 4) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
for (i.inner: int32, 0, 4) {
for (j: int32, 0, 16) {
- let cse_var_3: int32 = floordiv(i0.outer.i1.outer.fused, 2)
- let cse_var_2: int32 = (((i.outer.inner*64) + (i.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*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[((((i0.outer*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_5: int32 = (i0.outer.i1.outer.fused*8)
- let cse_var_4: int32 = ((i0.inner*512) + cse_var_5)
- compute[ramp(cse_var_4, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_5) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_4, 1, 8)]), broadcast(0f32, 8))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_2: int32 = ((((i0.outer*32768) + (i0.inner*512)) + (i1.outer*16)) + i1.inner)
+ compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
+ }
}
}
}
@@ -475,7 +478,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.900 ms
+ Execution time of this operator: 1.494 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 6c29c7e0a..8c9a065ad 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:45.947** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.621** 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``) | 00:45.912 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.586 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 4c3523956..659a58aac 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
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 177.12/177.12 result: MeasureResult(costs=(0.0013070251666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0436105728149414, timestamp=1661349633.8468184) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/177.12 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 177.37/177.37 result: MeasureResult(costs=(0.0013052061555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1578433513641357, timestamp=1661354693.720595) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/177.37 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
@@ -1280,8 +1280,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.14/260.14 result: MeasureResult(costs=(0.0008899052872928177,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7701294422149658, timestamp=1661349634.7686515) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 259.85/259.85 result: MeasureResult(costs=(0.0008908887513812154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4934370517730713, timestamp=1661354694.6415231) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/259.85 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
@@ -1404,7 +1404,7 @@ 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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/259.85 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
@@ -1527,7 +1527,7 @@ 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/259.85 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
@@ -1650,9 +1650,9 @@ 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.46/260.14 result: MeasureResult(costs=(0.0424288705,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8363773822784424, timestamp=1661349639.3378294) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/260.14 result: MeasureResult(costs=(0.0693977445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.56325888633728, timestamp=1661349640.5698924) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.45/259.85 result: MeasureResult(costs=(0.042488775250000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8390161991119385, timestamp=1661354699.1933777) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/259.85 result: MeasureResult(costs=(0.06939597,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.548490285873413, timestamp=1661354700.425302) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/259.85 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
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 27.29/260.14 result: MeasureResult(costs=(0.00848380482352941,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3170392513275146, timestamp=1661349651.672901) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 26.64/259.85 result: MeasureResult(costs=(0.008689362785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2846324443817139, timestamp=1661354711.4435625) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/259.85 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
@@ -1794,7 +1794,7 @@ 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, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/259.85 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
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001226
+ Time cost of this operator: 0.001231
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 59a5e9735..86a39fc02 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
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.1 98.735 (1, 2, 10, 10, 3) 2 1 [310.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.961 (1, 6, 10, 10) 1 1 [3.017]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.305 (1, 1, 10, 10, 3) 1 1 [0.957]
- Total_time - 314.074 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.728 (1, 2, 10, 10, 3) 2 1 [312.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.054 0.965 (1, 6, 10, 10) 1 1 [3.054]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.306 (1, 1, 10, 10, 3) 1 1 [0.97]
+ Total_time - 316.424 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 119.7 97.749 (1, 6, 10, 10, 1) 2 1 [119.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.796 1.467 (1, 6, 10, 10) 1 1 [1.796]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.784 (1, 1, 10, 10, 3) 1 1 [0.96]
- Total_time - 122.456 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.562 96.752 (1, 6, 10, 10, 1) 2 1 [80.562]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.746 2.097 (1, 6, 10, 10) 1 1 [1.746]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 1.151 (1, 1, 10, 10, 3) 1 1 [0.958]
+ Total_time - 83.267 - - - - -
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 850817ae6..2c0c656e4 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
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp9f61elw3/images/random'
+ '/tmp/tmppn5xytk5/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp9f61elw3/images/target contains 8144 images
- /tmp/tmp9f61elw3/images/random contains 5000 images
+ /tmp/tmppn5xytk5/images/target contains 8144 images
+ /tmp/tmppn5xytk5/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2414 - accuracy: 0.9196 - val_loss: 0.1643 - val_accuracy: 0.9532
+ 328/328 - 55s - loss: 0.2253 - accuracy: 0.9240 - val_loss: 0.1309 - val_accuracy: 0.9581
Epoch 2/3
- 328/328 - 52s - loss: 0.1013 - accuracy: 0.9627 - val_loss: 0.1504 - val_accuracy: 0.9585
+ 328/328 - 52s - loss: 0.0984 - accuracy: 0.9626 - val_loss: 0.1109 - val_accuracy: 0.9653
Epoch 3/3
- 328/328 - 52s - loss: 0.0673 - accuracy: 0.9748 - val_loss: 0.1187 - val_accuracy: 0.9641
+ 328/328 - 52s - loss: 0.0649 - accuracy: 0.9763 - val_loss: 0.1147 - val_accuracy: 0.9649
- <keras.callbacks.History object at 0x7f01ce8670d0>
+ <keras.callbacks.History object at 0x7f29d76e8090>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 54.984 seconds)
+ **Total running time of the script:** ( 5 minutes 16.141 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 a55497a98..f9ebd7ca6 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
@@ -5,16 +5,16 @@
Computation times
=================
-**05:48.614** total execution time for **how_to_work_with_microtvm** files:
+**06:07.747** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:54.984 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:16.141 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.293 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.089 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.320 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.194 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 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 81f216fad..ea9d5a876 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.314** total execution time for **how_to_work_with_relay** files:
+**00:42.002** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.575 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.815 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.073 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.763 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.659 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.417 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 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 ff067ee30..037aba4a0 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
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f0139c5fef0>
+ <function my_cuda_math_rule at 0x7f295b594a70>
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 dff35ef52..e7479602f 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.136** total execution time for **how_to_work_with_schedules** files:
+**00:04.027** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.894 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.859 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.002 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.946 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.534 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.508 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.105 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 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 d3b80afcf..95929b0d7 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ 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/tmpz397jfty/input0.cc'\nsource_filename = \"/tmp/tmpz397jfty/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/tmp4awx27wi/input0.cc'\nsource_filename = \"/tmp/tmp4awx27wi/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 f5f59befc..5eaec9d2f 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
=================
-**00:21.118** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.899** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.111 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.893 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 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 394215431..f7c86d9c4 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 23.11s!
+ resnet18_v1 inference graph built in 22.29s!
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 61c4b891a..784adaac5 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:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.00s!
+ yolov3-tiny inference graph built in 15.73s!
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 f10763e3a..5f95ad1a9 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
=================
-**01:32.089** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.028** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.708 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.654 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.381 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.374 | 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 6548299bf..4097f211e 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
=================
-**00:03.241** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.206** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.841 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.818 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.389 | 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 9b2310803..d619e6c00 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
=================
-**00:00.710** total execution time for **topic_vta_tutorials** files:
+**00:00.702** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.380 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.378 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.329 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.324 | 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 f5ff9ac96..216085aa8 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 97.717 ms
+ Execution time of this operator: 93.664 ms
@@ -444,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.894 seconds)
+ **Total running time of the script:** ( 1 minutes 9.745 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 0dc8b254b..d17006a26 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.62/10.62 result: MeasureResult(costs=(0.025273408200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5365078449249268, timestamp=1661348434.0935004) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.91/10.62 result: MeasureResult(costs=(0.09210231320000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.620378017425537, timestamp=1661348435.727656) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226401432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5713176727294922, timestamp=1661348436.7807186) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.86 result: MeasureResult(costs=(0.1451110114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.440173625946045, timestamp=1661348439.790852) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.70/11.86 result: MeasureResult(costs=(0.0726271558,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2993955612182617, timestamp=1661348441.2189248) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.65/11.86 result: MeasureResult(costs=(0.162793359,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7800753116607666, timestamp=1661348444.0428634) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.86 result: MeasureResult(costs=(0.3082529676,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.050024509429932, timestamp=1661348449.664111) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.61/11.86 result: MeasureResult(costs=(0.025298854800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5479912757873535, timestamp=1661348450.2323132) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.90/11.86 result: MeasureResult(costs=(0.1415973892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.365818977355957, timestamp=1661348452.7178369) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.75/11.86 result: MeasureResult(costs=(0.0975465108,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6585078239440918, timestamp=1661348454.434552) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.55/10.55 result: MeasureResult(costs=(0.0254329492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5407936573028564, timestamp=1661353477.6130342) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.70/10.55 result: MeasureResult(costs=(0.09938775879999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.738696575164795, timestamp=1661353479.3653543) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.022753001000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5553998947143555, timestamp=1661353480.4159062) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.83/11.80 result: MeasureResult(costs=(0.1470107178,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4691286087036133, timestamp=1661353482.9298115) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.65/11.80 result: MeasureResult(costs=(0.07357137999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3136398792266846, timestamp=1661353484.374773) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.56/11.80 result: MeasureResult(costs=(0.17196434260000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8693912029266357, timestamp=1661353487.810747) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.80 result: MeasureResult(costs=(0.3072077364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.036134958267212, timestamp=1661353493.416797) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.80/11.80 result: MeasureResult(costs=(0.024851695200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5428934097290039, timestamp=1661353493.97692) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.80 result: MeasureResult(costs=(0.1413844794,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.359879970550537, timestamp=1661353496.4544868) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.78/11.80 result: MeasureResult(costs=(0.0964911518,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6486308574676514, timestamp=1661353498.1598032) [('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 26db49872..d27d2dedb 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 493.1972569200025, 'median': 492.7358948500114, 'std': 1.136266803649717}
+ {'mean': 491.3749680500017, 'median': 491.27970339999933, 'std': 0.8558464573886108}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: 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: 17.62/ 17.62 GFLOPS | Progress: (4/20) | 6.34 s
[Task 1/25] Current/Best: 6.12/ 17.62 GFLOPS | Progress: (8/20) | 9.35 s
[Task 1/25] Current/Best: 11.55/ 22.77 GFLOPS | Progress: (12/20) | 11.75 s
[Task 1/25] Current/Best: 16.46/ 22.84 GFLOPS | Progress: (16/20) | 13.43 s
[Task 1/25] Current/Best: 11.62/ 23.87 GFLOPS | Progress: (20/20) | 15.16 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 12.98 GFLOPS | Progress: (4/20) | 3.78 s
[Task 2/25] Current/Best: 14.13/ 18.72 GFLOPS | Progress: (8/20) | 5.08 s
[Task 2/25] Current/Best: 21.02/ 21.02 GFLOPS | Progress: (12/20) | 6.39 s
[Task 2/25] Current/Best: 12.28/ 21.02 GFLOPS | Progress: (16/20) | 7.64 s
[Task 2/25] Current/Best: 19.14/ 21.02 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/ 10.84 GFLOPS | Progress: (4/20) | 5.88 s
[Task 3/25] Current/Best: 15.32/ 16.85 GFLOPS | Progress: (8/20) | 7.82 s
[Task 3/25] Current/Best: 15.03/ 16.85 GFLOPS | Progress: (12/20) | 9.54 s
[Task 3/25] Current/Best: 7.25/ 23.70 GFLOPS | Progress: (16/20) | 11.45 s
[Task 3/25] Current/Best: 12.63/ 23.70 GFLOPS | Progress: (20/20) | 15.98 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.39 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.57/ 20.39 GFLOPS | Progress: (8/20) | 6.70 s
[Task 4/25] Current/Best: 22.37/ 22.37 GFLOPS | Progress: (12/20) | 11.23 s
[Task 4/25] Current/Best: 16.84/ 22.37 GFLOPS | Progress: (16/20) | 13.47 s
[Task 4/25] Current/Best: 13.39/ 22.37 GFLOPS | Progress: (20/20) | 15.35 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.63/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.72/ 12.79 GFLOPS | Progress: (8/20) | 4.70 s
[Task 5/25] Current/Best: 11.66/ 18.07 GFLOPS | Progress: (12/20) | 7.76 s
[Task 5/25] Current/Best: 11.70/ 22.61 GFLOPS | Progress: (16/20) | 9.18 s
[Task 5/25] Current/Best: 12.00/ 22.61 GFLOPS | Progress: (20/20) | 11.01 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.71 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 19.01/ 20.71 GFLOPS | Progress: (8/20) | 5.76 s
[Task 6/25] Current/Best: 13.27/ 20.71 GFLOPS | Progress: (12/20) | 7.68 s
[Task 6/25] Current/Best: 20.00/ 20.71 GFLOPS | Progress: (16/20) | 9.93 s
[Task 6/25] Current/Best: 3.73/ 20.71 GFLOPS | Progress: (20/20) | 12.48 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.13/ 12.93 GFLOPS | Progress: (4/20) | 3.64 s
[Task 7/25] Current/Best: 20.29/ 21.14 GFLOPS | Progress: (8/20) | 5.16 s
[Task 7/25] Current/Best: 15.64/ 21.14 GFLOPS | Progress: (12/20) | 7.04 s
[Task 7/25] Current/Best: 12.25/ 21.14 GFLOPS | Progress: (16/20) | 9.08 s
[Task 7/25] Current/Best: 6.32/ 21.72 GFLOPS | Progress: (20/20) | 11.54 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.85/ 13.97 GFLOPS | Progress: (4/20) | 2.94 s
[Task 8/25] Current/Best: 9.35/ 13.97 GFLOPS | Progress: (8/20) | 7.62 s
[Task 8/25] Current/Best: 12.88/ 13.97 GFLOPS | Progress: (12/20) | 13.77 s
[Task 8/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (16/20) | 15.89 s
[Task 8/25] Current/Best: 18.70/ 19.04 GFLOPS | Progress: (20/20) | 22.44 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.24/ 15.79 GFLOPS | Progress: (4/20) | 11.97 s
[Task 9/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (8/20) | 13.76 s
[Task 9/25] Current/Best: 8.24/ 23.51 GFLOPS | Progress: (12/20) | 16.16 s
[Task 9/25] Current/Best: 17.97/ 23.51 GFLOPS | Progress: (16/20) | 18.71 s
[Task 9/25] Current/Best: 9.15/ 23.51 GFLOPS | Progress: (20/20) | 26.40 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.63 s
[Task 10/25] Current/Best: 15.51/ 18.23 GFLOPS | Progress: (8/20) | 4.23 s
[Task 10/25] Current/Best: 12.56/ 18.96 GFLOPS | Progress: (12/20) | 5.76 s
[Task 10/25] Current/Best: 19.10/ 20.42 GFLOPS | Progress: (16/20) | 6.87 s
[Task 10/25] Current/Best: 8.94/ 20.42 GFLOPS | Progress: (20/20
) | 8.43 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.20/ 18.11 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 16.70/ 18.11 GFLOPS | Progress: (8/20) | 6.05 s
[Task 11/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 8.11 s
[Task 11/25] Current/Best: 13.36/ 20.91 GFLOPS | Progress: (16/20) | 10.89 s
[Task 11/25] Current/Best: 19.37/ 21.61 GFLOPS | Progress: (20/20) | 12.94 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.78/ 18.03 GFLOPS | Progress: (4/20) | 5.38 s
[Task 12/25] Current/Best: 5.21/ 18.03 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (12/20) | 11.10 s
[Task 12/25] Current/Best: 15.18/ 19.15 GFLOPS | Progress: (16/20) | 13.88 s
[Task 12/25] Current/Best: 15.17/ 19.15 GFLOPS | Progress: (20/20) | 15.78 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.76/ 17.33 GFLOPS | Progress: (4/20) | 3.71 s
[Task 13/25] Current/Best: 15.49/ 20.79 GFLOPS | Progress: (8/20) | 6.15 s
[Task 13/25] Current/Best: 19.60/ 21.74 GFLOPS | Progress: (12/20) | 9.07 s
[Task 13/25] Current/Best: 12.30/ 21.74 GFLOPS | Progress: (16/20) | 12.43 s
[Task 13/25] Current/Best: 18.44/ 21.74 GFLOPS | Progress: (20/20) | 14.73 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.08/ 13.64 GFLOPS | Progress: (8/20) | 5.57 s
[Task 14/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (12/20) | 8.12 s
[Task 14/25] Current/Best: 16.42/ 20.20 GFLOPS | Progress: (16/20) | 9.80 s Done.
-
[Task 14/25] Current/Best: 17.06/ 20.20 GFLOPS | Progress: (20/20) | 11.57 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.64 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.36/ 18.03 GFLOPS | Progress: (8/20) | 4.08 s
[Task 15/25] Current/Best: 10.39/ 22.30 GFLOPS | Progress: (12/20) | 6.14 s
[Task 15/25] Current/Best: 20.36/ 22.30 GFLOPS | Progress: (16/20) | 9.49 s
[Task 15/25] Current/Best: 9.69/ 22.30 GFLOPS | Progress: (20/20) | 10.51 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 3.02/ 20.44 GFLOPS | Progress: (8/20) | 4.57 s
[Task 16/25] Current/Best: 19.46/ 20.44 GFLOPS | Progress: (12/20) | 5.77 s
[Task 16/25] Current/Best: 17.83/ 20.44 GFLOPS | Progress: (16/20) |
7.14 s
[Task 16/25] Current/Best: 10.03/ 20.44 GFLOPS | Progress: (20/20) | 9.19 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.79/ 18.16 GFLOPS | Progress: (4/20) | 4.73 s
[Task 17/25] Current/Best: 12.64/ 23.33 GFLOPS | Progress: (8/20) | 7.60 s
[Task 17/25] Current/Best: 18.77/ 23.33 GFLOPS | Progress: (12/20) | 9.65 s
[Task 17/25] Current/Best: 16.48/ 23.33 GFLOPS | Progress: (16/20) | 11.78 s
[Task 17/25] Current/Best: 10.02/ 23.33 GFLOPS | Progress: (20/20) | 13.90 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.27/ 17.01 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.58/ 19.04 GFLOPS | Progress: (8/20) | 7.12 s
[Task 18/25] Current/Best: 18.85/ 19.04 GFLOPS | Progress: (12/20) | 9.03 s
[Task 18/25] Current/Best: 10.06/ 19.04 GFLOPS | Progress: (16/20) | 12.62 s
[Task 18/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (20/20) | 14.12 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.13/ 20.35 GFLOPS | Progress: (4/20) | 6.05 s
[Task 19/25] Current/Best: 2.69/ 20.35 GFLOPS | Progress: (8/20) | 9.33 s
[Task 19/25] Current/Best: 19.30/ 21.21 GFLOPS | Progress: (12/20) | 12.17 s
[Task 19/25] Current/Best: 15.35/ 21.21 GFLOPS | Progress: (16/20) | 14.99 s
[Task 19/25] Current/Best: 2.70/ 22.59 GFLOPS | Progress: (20/20) | 17.82 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.75/ 15.28 GFLOPS | Progress: (4/20) | 3.38 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.59/ 17.59 GFLOPS | Progress: (4/20) | 6.32 s
[Task 1/25] Current/Best: 6.16/ 17.59 GFLOPS | Progress: (8/20) | 9.32 s
[Task 1/25] Current/Best: 11.56/ 22.85 GFLOPS | Progress: (12/20) | 11.71 s
[Task 1/25] Current/Best: 16.55/ 22.85 GFLOPS | Progress: (16/20) | 13.40 s
[Task 1/25] Current/Best: 11.57/ 23.90 GFLOPS | Progress: (20/20) | 15.12 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.26/ 13.22 GFLOPS | Progress: (4/20) | 3.75 s
[Task 2/25] Current/Best: 14.12/ 18.74 GFLOPS | Progress: (8/20) | 5.04 s
[Task 2/25] Current/Best: 21.31/ 21.31 GFLOPS | Progress: (12/20) | 6.36 s
[Task 2/25] Current/Best: 12.71/ 21.31 GFLOPS | Progress: (16/20) | 7.64 s
[Task 2/25] Current/Best: 20.18/ 21.31 GFLOPS | Progress: (20/20) | 9.24 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/ 10.82 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.36/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.99/ 16.81 GFLOPS | Progress: (12/20) | 9.51 s
[Task 3/25] Current/Best: 7.24/ 23.76 GFLOPS | Progress: (16/20) | 11.44 s
[Task 3/25] Current/Best: 12.68/ 23.76 GFLOPS | Progress: (20/20) | 15.93 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.52/ 20.27 GFLOPS | Progress: (4/20) | 2.37 s
[Task 4/25] Current/Best: 6.80/ 20.27 GFLOPS | Progress: (8/20) | 6.68 s
[Task 4/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (12/20) | 11.18 s
[Task 4/25] Current/Best: 17.48/ 21.38 GFLOPS | Progress: (16/20) | 13.41 s
[Task 4/25] Current/Best: 13.36/ 21.38 GFLOPS | Progress: (20/20) | 15.30 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.75/ 10.34 GFLOPS | Progress: (4/20) | 2.58 s
[Task 5/25] Current/Best: 11.67/ 12.71 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.77/ 18.07 GFLOPS | Progress: (12/20) | 7.76 s
[Task 5/25] Current/Best: 11.75/ 22.59 GFLOPS | Progress: (16/20) | 9.16 s
[Task 5/25] Current/Best: 12.08/ 22.59 GFLOPS | Progress: (20/20) | 11.01 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.22/ 20.67 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 18.99/ 20.67 GFLOPS | Progress: (8/20) | 5.73 s
[Task 6/25] Current/Best: 13.32/ 20.67 GFLOPS | Progress: (12/20) | 7.65 s
[Task 6/25] Current/Best: 19.98/ 20.67 GFLOPS | Progress: (16/20) | 9.92 s
[Task 6/25] Current/Best: 3.65/ 20.67 GFLOPS | Progress: (20/20) | 12.43 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.21/ 12.97 GFLOPS | Progress: (4/20) | 3.52 s
[Task 7/25] Current/Best: 20.32/ 21.10 GFLOPS | Progress: (8/20) | 5.03 s
[Task 7/25] Current/Best: 16.08/ 21.10 GFLOPS | Progress: (12/20) | 6.92 s
[Task 7/25] Current/Best: 12.27/ 21.10 GFLOPS | Progress: (16/20) | 8.96 s
[Task 7/25] Current/Best: 6.35/ 21.83 GFLOPS | Progress: (20/20) | 11.44 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.81/ 14.09 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.20/ 14.09 GFLOPS | Progress: (8/20) | 7.62 s
[Task 8/25] Current/Best: 12.35/ 14.09 GFLOPS | Progress: (12/20) | 13.67 s
[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 15.79 s
[Task 8/25] Current/Best: 19.84/ 19.84 GFLOPS | Progress: (20/20) | 22.22 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.75 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.73 s
[Task 9/25] Current/Best: 8.25/ 23.45 GFLOPS | Progress: (12/20) | 16.04 s
[Task 9/25] Current/Best: 17.96/ 23.45 GFLOPS | Progress: (16/20) | 18.57 s
[Task 9/25] Current/Best: 9.21/ 23.45 GFLOPS | Progress: (20/20) | 26.18 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/20) | 2.53 s
[Task 10/25] Current/Best: 15.54/ 18.26 GFLOPS | Progress: (8/20) | 4.10 s
[Task 10/25] Current/Best: 12.77/ 18.88 GFLOPS | Progress: (12/20) | 5.62 s
[Task 10/25] Current/Best: 18.80/ 20.37 GFLOPS | Progress: (16/20) | 6.71 s
[Task 10/25] Current/Best: 8.87/ 20.37 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: 12.30/ 18.30 GFLOPS | Progress: (4/20) | 3.30 s
[Task 11/25] Current/Best: 16.80/ 18.30 GFLOPS | Progress: (8/20) | 5.99 s
[Task 11/25] Current/Best: 16.58/ 18.30 GFLOPS | Progress: (12/20) | 8.06 s
[Task 11/25] Current/Best: 13.63/ 20.77 GFLOPS | Progress: (16/20) | 10.75 s
[Task 11/25] Current/Best: 19.47/ 21.68 GFLOPS | Progress: (20/20) | 12.78 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.84/ 18.15 GFLOPS | Progress: (4/20) | 5.34 s
[Task 12/25] Current/Best: 5.23/ 18.15 GFLOPS | Progress: (8/20) | 8.99 s
[Task 12/25] Current/Best: 18.88/ 18.96 GFLOPS | Progress: (12/20) | 10.97 s
[Task 12/25] Current/Best: 15.38/ 18.96 GFLOPS | Progress: (16/20) | 13.70 s
[Task 12/25] Current/Best: 15.20/ 18.96 GFLOPS | Progress: (20/20) | 15.62 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.77/ 17.30 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 15.58/ 20.92 GFLOPS | Progress: (8/20) | 6.11 s
[Task 13/25] Current/Best: 19.67/ 21.32 GFLOPS | Progress: (12/20) | 8.93 s
[Task 13/25] Current/Best: 12.32/ 21.32 GFLOPS | Progress: (16/20) | 12.33 s
[Task 13/25] Current/Best: 17.95/ 21.32 GFLOPS | Progress: (20/20) | 14.66 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.92/ 13.00 GFLOPS | Progress: (4/20) | 3.25 s
[Task 14/25] Current/Best: 6.09/ 13.28 GFLOPS | Progress: (8/20) | 5.42 s
[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 7.93 s
[Task 14/25] Current/Best: 16.28/ 20.32 GFLOPS | Progress: (16/20) | 9.58 s Done.
+
[Task 14/25] Current/Best: 17.05/ 20.32 GFLOPS | Progress: (20/20) | 11.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.19/ 17.68 GFLOPS | Progress: (4/20) | 2.72 s
[Task 15/25] Current/Best: 13.92/ 18.09 GFLOPS | Progress: (8/20) | 4.07 s
[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.18 s
[Task 15/25] Current/Best: 20.25/ 22.28 GFLOPS | Progress: (16/20) | 9.16 s
[Task 15/25] Current/Best: 9.71/ 22.28 GFLOPS | Progress: (20/20) | 10.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/20) | 3.01 s
[Task 16/25] Current/Best: 3.04/ 20.66 GFLOPS | Progress: (8/20) | 4.65 s
[Task 16/25] Current/Best: 19.33/ 20.66 GFLOPS | Progress: (12/20) | 5.87 s
[Task 16/25] Current/Best: 17.57/ 20.66 GFLOPS | Progress: (16/20) |
7.22 s
[Task 16/25] Current/Best: 9.97/ 22.44 GFLOPS | Progress: (20/20) | 9.24 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.54/ 18.20 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 13.00/ 23.42 GFLOPS | Progress: (8/20) | 7.51 s
[Task 17/25] Current/Best: 17.64/ 23.42 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 16.43/ 23.42 GFLOPS | Progress: (16/20) | 11.66 s
[Task 17/25] Current/Best: 10.04/ 23.42 GFLOPS | Progress: (20/20) | 13.77 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.91/ 17.89 GFLOPS | Progress: (4/20) | 3.68 s
[Task 18/25] Current/Best: 10.54/ 19.77 GFLOPS | Progress: (8/20) | 7.07 s
[Task 18/25] Current/Best: 19.53/ 19.77 GFLOPS | Progress: (12/20) | 8.97 s
[Task 18/25] Current/Best: 10.05/ 19.77 GFLOPS | Progress: (16/20) | 12.48 s
[Task 18/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (20/20) | 13.99 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.16/ 20.55 GFLOPS | Progress: (4/20) | 5.97 s
[Task 19/25] Current/Best: 2.69/ 20.55 GFLOPS | Progress: (8/20) | 9.21 s
[Task 19/25] Current/Best: 20.13/ 21.84 GFLOPS | Progress: (12/20) | 11.99 s
[Task 19/25] Current/Best: 14.46/ 22.07 GFLOPS | Progress: (16/20) | 14.88 s
[Task 19/25] Current/Best: 2.70/ 23.24 GFLOPS | Progress: (20/20) | 17.68 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.32/ 15.22 GFLOPS | Progress: (4/20) | 3.29 s Done.
Done.
-
[Task 20/25] Current/Best: 9.87/ 15.28 GFLOPS | Progress: (8/20) | 6.80 s
[Task 20/25] Current/Best: 2.33/ 16.68 GFLOPS | Progress: (12/20) | 10.73 s
[Task 20/25] Current/Best: 12.46/ 16.68 GFLOPS | Progress: (16/20) | 14.50 s
[Task 20/25] Current/Best: 13.25/ 22.05 GFLOPS | Progress: (20/20) | 16.61 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.71 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.60/ 17.71 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.97 s
[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.41 s
[Task 21/25] Current/Best: 4.44/ 17.91 GFLOPS | Progress: (20/20) | 17.49 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.80 GFLOPS | Progress: (4/20
) | 2.68 s
[Task 22/25] Current/Best: 8.78/ 21.92 GFLOPS | Progress: (8/20) | 4.69 s
[Task 22/25] Current/Best: 19.16/ 21.92 GFLOPS | Progress: (12/20) | 7.01 s
[Task 22/25] Current/Best: 15.36/ 21.92 GFLOPS | Progress: (16/20) | 9.10 s
[Task 22/25] Current/Best: 13.96/ 21.92 GFLOPS | Progress: (20/20) | 10.76 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.45/ 20.47 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 15.82/ 20.47 GFLOPS | Progress: (8/20) | 6.65 s
[Task 23/25] Current/Best: 20.84/ 21.66 GFLOPS | Progress: (12/20) | 8.46 s
[Task 23/25] Current/Best: 6.35/ 21.66 GFLOPS | Progress: (16/20) | 15.57 s
[Task 23/25] Current/Best: 7.78/ 21.66 GFLOPS | Progress: (20/20) | 19.76 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.83 s
[Task 24/25] Current/Best: 1.92/ 8.40 GFLOPS | Progress: (8/20) | 22.87 s
[Task 24/25] Current/Best: 4.36/ 8.40 GFLOPS | Progress: (12/20) | 34.42 s Done.
-
[Task 24/25] Current/Best: 6.24/ 8.59 GFLOPS | Progress: (16/20) | 39.74 s
[Task 24/25] Current/Best: 3.37/ 8.93 GFLOPS | Progress: (20/20) | 45.66 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.76 GFLOPS | Progress: (4/20) | 11.60 s
[Task 25/25] Current/Best: 5.86/ 8.34 GFLOPS | Progress: (8/20) | 22.85 s
[Task 25/25] Current/Best: 6.02/ 8.34 GFLOPS | Progress: (12/20) | 34.29 s
[Task 25/25] Current/Best: 5.88/ 8.82 GFLOPS | Progress: (16/20) | 36.14 s
[Task 25/25] Current/Best: 2.86/ 9.15 GFLOPS | Progress: (20/20) | 46.79 s
+
[Task 20/25] Current/Best: 9.69/ 15.22 GFLOPS | Progress: (8/20) | 6.74 s
[Task 20/25] Current/Best: 2.33/ 16.70 GFLOPS | Progress: (12/20) | 10.62 s
[Task 20/25] Current/Best: 11.75/ 16.70 GFLOPS | Progress: (16/20) | 14.15 s
[Task 20/25] Current/Best: 13.54/ 22.33 GFLOPS | Progress: (20/20) | 16.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.71 GFLOPS | Progress: (4/20) | 3.23 s
[Task 21/25] Current/Best: 14.66/ 17.71 GFLOPS | Progress: (8/20) | 4.77 s
[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.92 s
[Task 21/25] Current/Best: 17.89/ 17.89 GFLOPS | Progress: (16/20) | 10.34 s
[Task 21/25] Current/Best: 4.47/ 17.89 GFLOPS | Progress: (20/20) | 17.34 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.93 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.58/ 22.15 GFLOPS | Progress: (8/20) | 4.57 s
[Task 22/25] Current/Best: 20.08/ 22.15 GFLOPS | Progress: (12/20) | 6.85 s
[Task 22/25] Current/Best: 15.42/ 22.15 GFLOPS | Progress: (16/20) | 8.88 s
[Task 22/25] Current/Best: 13.99/ 22.15 GFLOPS | Progress: (20/20) | 10.59 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.77/ 20.90 GFLOPS | Progress: (4/20) | 3.26 s
[Task 23/25] Current/Best: 14.57/ 20.90 GFLOPS | Progress: (8/20) | 6.51 s
[Task 23/25] Current/Best: 21.04/ 21.86 GFLOPS | Progress: (12/20) | 8.28 s
[Task 23/25] Current/Best: 6.36/ 21.86 GFLOPS | Progress: (16/20) | 15.23 s
[Task 23/25] Current/Best: 7.88/ 21.86 GFLOPS | Progress: (20/20) | 19.38 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (4/20) | 11.80 s
[Task 24/25] Current/Best: 2.16/ 8.48 GFLOPS | Progress: (8/20) | 22.81 s
[Task 24/25] Current/Best: 4.34/ 8.48 GFLOPS | Progress: (12/20) | 34.34 s Done.
+
[Task 24/25] Current/Best: 6.19/ 8.76 GFLOPS | Progress: (16/20) | 39.63 s
[Task 24/25] Current/Best: 3.03/ 8.76 GFLOPS | Progress: (20/20) | 45.50 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 6.20/ 8.23 GFLOPS | Progress: (8/20) | 22.86 s
[Task 25/25] Current/Best: 6.08/ 8.23 GFLOPS | Progress: (12/20) | 34.14 s
[Task 25/25] Current/Best: 5.85/ 8.93 GFLOPS | Progress: (16/20) | 35.88 s
[Task 25/25] Current/Best: 2.88/ 8.99 GFLOPS | Progress: (20/20) | 46.55 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.21851686999526, 'median': 415.0496100999817, 'std': 0.7492938069752674}
- unoptimized: {'mean': 493.1972569200025, 'median': 492.7358948500114, 'std': 1.136266803649717}
+ optimized: {'mean': 407.42993023999816, 'median': 407.5165550999941, 'std': 0.7069837393560074}
+ unoptimized: {'mean': 491.3749680500017, 'median': 491.27970339999933, 'std': 0.8558464573886108}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 18.273 seconds)
+ **Total running time of the script:** ( 10 minutes 24.658 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 5d34055c2..c13f5696b 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.307e-07 secs/op
+ 1.248e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index cc05a35fa..5f5231daf 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x1a66d2d0)), stage(b, placeholder(b, 0x207619c0)), 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, 0xb1d7ad0)), stage(b, placeholder(b, 0x2457ef80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 2d08a27cf..0fd0abc51 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**13:18.225** total execution time for **tutorial** files:
+**13:31.322** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.273 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:24.658 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:02.894 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:09.745 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.751 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.372 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.163 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.487 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.789 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.975 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.692 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.244 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.514 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.694 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.142 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.139 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 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 a6ffaea57..534d09928 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000008
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000006
+ parallel: 0.000007
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.79289000092831e-06 1.0
- naive 7.652799999999999e-06 0.9820233570714302
- parallel 6.0388e-06 0.7749114897400889
- vector 2.46657e-05 3.16515439035605
+ numpy 7.188160000168864e-06 1.0
+ naive 7.6387e-06 1.0626780705800305
+ parallel 7.0917e-06 0.9865807104785372
+ vector 2.45589e-05 3.416576703832839
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018585
+ Numpy running time: 0.017881
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 3.419016
+ none: 3.407148
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.292311
+ blocking: 0.284340
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.327124
+ vectorization: 0.322829
@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], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.118134
+ loop permutation: 0.115480
@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], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.108763
+ array packing: 0.109448
@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], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.110233
+ block caching: 0.110238
@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], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: 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: 0.145499
+ parallelization: 0.146285
@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], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4190162362 1.0
- blocking 0.29231131489999995 0.08549573757651521
- vectorization 0.3271236663 0.0956777165421055
- loop permutation 0.1181339512 0.0345520298936333
- array packing 0.1087628013 0.03181113916583278
- block caching 0.110232949 0.03224113060150784
- parallelization 0.14549852140000002 0.04255566845792799
+ none 3.4071484422000005 1.0
+ blocking 0.2843397731 0.08345388465563931
+ vectorization 0.3228287596 0.09475042402072421
+ loop permutation 0.11548016459999999 0.03389349379959339
+ array packing 0.1094476059 0.0321229344000432
+ block caching 0.11023844509999998 0.032355046153732844
+ parallelization 0.1462853325 0.04293482804803872
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.751 seconds)
+ **Total running time of the script:** ( 1 minutes 0.372 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index d4b8d3767..0ef3edeb4 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-a0fe74b3c3608929b21faeaea422ac09aa2f75eb
+038523e5a21e13ff2802913ec32b73fb47413b35
diff --git a/docs/genindex.html b/docs/genindex.html
index e7146332e..089e25037 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -4670,6 +4670,10 @@
<li><a href="reference/api/python/te.html#tvm.te.var">var() (in module tvm.te)</a>
</li>
<li><a href="reference/api/python/relay/dataflow_pattern.html#tvm.relay.dataflow_pattern.VarPattern">VarPattern (class in tvm.relay.dataflow_pattern)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.vectorcombine">vectorcombine() (in module tvm.tir)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.vectorhigh">vectorhigh() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/te.html#tvm.te.Stage.vectorize">vectorize() (tvm.te.Stage method)</a>
@@ -4678,17 +4682,19 @@
</li>
</ul></li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.VectorizeLoop">VectorizeLoop() (in module tvm.tir.transform)</a>
+</li>
+ <li><a href="reference/api/python/tir.html#tvm.tir.vectorlow">vectorlow() (in module tvm.tir)</a>
</li>
<li><a href="reference/api/python/tir.html#tvm.tir.transform.VerifyMemory">VerifyMemory() (in module tvm.tir.transform)</a>
</li>
<li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.space.VirtualAxis">VirtualAxis (class in tvm.autotvm.task.space)</a>
</li>
+ </ul></td>
+ <td style="width: 33%; vertical-align: top;"><ul>
<li><a href="reference/api/python/target.html#tvm.target.VirtualDevice">VirtualDevice (class in tvm.target)</a>
</li>
<li><a href="reference/api/python/contrib.html#tvm.contrib.relay_viz.interface.VizEdge">VizEdge (class in tvm.contrib.relay_viz.interface)</a>
</li>
- </ul></td>
- <td style="width: 33%; vertical-align: top;"><ul>
<li><a href="reference/api/python/contrib.html#tvm.contrib.relay_viz.interface.VizGraph">VizGraph (class in tvm.contrib.relay_viz.interface)</a>
</li>
<li><a href="reference/api/python/contrib.html#tvm.contrib.relay_viz.interface.VizNode">VizNode (class in tvm.contrib.relay_viz.interface)</a>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 2f4f075be..c51205394 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.634 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.155 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.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_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 2d9d7eb50..4a379b1e0 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ 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.zipaf84c463-677d-4cff-ba73-43f731bd1cc3 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.zip4276bc4f-ed00-46c4-bfe5-5e2a88f38344 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 6eb444467..70a85e6c9 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,12 +432,13 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 50.7MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 65.0MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 57.7MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 63.2MB/s]
- 93%|#########2| 38.4M/41.5M [00:00<00:00, 64.4MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 63.7MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 64.3MB/s]
+ 30%|### | 12.5M/41.5M [00:00<00:00, 53.1MB/s]
+ 42%|####2 | 17.6M/41.5M [00:00<00:00, 39.4MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 42.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 53.0MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 53.0MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 50.7MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index fc136680c..da05ba438 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 37%|###6 | 16.5M/44.7M [00:00<00:00, 172MB/s]
- 88%|########8 | 39.5M/44.7M [00:00<00:00, 213MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 208MB/s]
+ 7%|7 | 3.20M/44.7M [00:00<00:01, 33.0MB/s]
+ 14%|#4 | 6.35M/44.7M [00:00<00:01, 30.5MB/s]
+ 28%|##7 | 12.4M/44.7M [00:00<00:00, 44.0MB/s]
+ 40%|###9 | 17.7M/44.7M [00:00<00:00, 48.7MB/s]
+ 60%|###### | 27.0M/44.7M [00:00<00:00, 65.8MB/s]
+ 81%|########1 | 36.3M/44.7M [00:00<00:00, 74.1MB/s]
+ 97%|#########7| 43.4M/44.7M [00:00<00:00, 54.9MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 54.1MB/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 308c7517b..8de4381dd 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.389 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.744 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 be69b52ad..fb876abca 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>05:00.033</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:06.148</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<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>01:02.634</p></td>
+<td><p>01:02.155</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>01:01.389</p></td>
+<td><p>01:00.744</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:38.592</p></td>
+<td><p>00:46.090</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>00:27.814</p></td>
+<td><p>00:27.597</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.222</p></td>
+<td><p>00:24.799</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:24.545</p></td>
+<td><p>00:23.950</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.521</p></td>
+<td><p>00:22.088</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.179</p></td>
+<td><p>00:19.908</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>00:15.742</p></td>
+<td><p>00:16.254</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>00:02.396</p></td>
+<td><p>00:02.564</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 2b02bf98f..c52a44210 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9719 15.9607 16.2666 15.7528 0.1290
+ 15.5554 15.5336 15.7682 15.4656 0.0898
</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 98d137a2d..63a784ff9 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,32 @@ 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]
- 11%|# | 18.2M/170M [00:00<00:00, 190MB/s]
- 26%|##6 | 44.2M/170M [00:00<00:00, 239MB/s]
- 40%|#### | 68.2M/170M [00:00<00:00, 245MB/s]
- 54%|#####4 | 92.4M/170M [00:00<00:00, 248MB/s]
- 69%|######8 | 117M/170M [00:00<00:00, 251MB/s]
- 83%|########3 | 141M/170M [00:00<00:00, 253MB/s]
- 99%|#########9| 169M/170M [00:00<00:00, 265MB/s]
-100%|##########| 170M/170M [00:00<00:00, 253MB/s]
+ 3%|3 | 5.21M/170M [00:00<00:03, 54.6MB/s]
+ 7%|6 | 11.1M/170M [00:00<00:02, 58.9MB/s]
+ 11%|# | 18.5M/170M [00:00<00:02, 67.2MB/s]
+ 15%|#5 | 26.1M/170M [00:00<00:02, 72.3MB/s]
+ 19%|#9 | 33.0M/170M [00:00<00:02, 63.5MB/s]
+ 24%|##3 | 40.2M/170M [00:00<00:02, 67.2MB/s]
+ 28%|##7 | 46.8M/170M [00:00<00:01, 64.6MB/s]
+ 31%|###1 | 53.3M/170M [00:00<00:01, 65.6MB/s]
+ 35%|###5 | 59.6M/170M [00:00<00:01, 65.5MB/s]
+ 39%|###8 | 65.9M/170M [00:01<00:01, 58.3MB/s]
+ 43%|####3 | 73.7M/170M [00:01<00:01, 64.6MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 59.4MB/s]
+ 51%|##### | 85.9M/170M [00:01<00:01, 57.5MB/s]
+ 54%|#####3 | 91.5M/170M [00:01<00:01, 56.1MB/s]
+ 58%|#####7 | 98.3M/170M [00:01<00:01, 60.3MB/s]
+ 62%|######2 | 106M/170M [00:01<00:01, 64.9MB/s]
+ 66%|######5 | 112M/170M [00:01<00:00, 63.5MB/s]
+ 70%|######9 | 119M/170M [00:01<00:00, 65.2MB/s]
+ 74%|#######4 | 126M/170M [00:02<00:00, 67.6MB/s]
+ 78%|#######7 | 132M/170M [00:02<00:00, 46.8MB/s]
+ 82%|########1 | 139M/170M [00:02<00:00, 51.5MB/s]
+ 86%|########5 | 145M/170M [00:02<00:00, 55.9MB/s]
+ 90%|########9 | 152M/170M [00:02<00:00, 60.4MB/s]
+ 94%|#########3| 159M/170M [00:02<00:00, 64.0MB/s]
+ 98%|#########7| 166M/170M [00:02<00:00, 66.2MB/s]
+100%|##########| 170M/170M [00:02<00:00, 61.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -538,7 +556,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 56.902 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 54.561 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 30dad8566..f8f6899a8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,8 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 185MB/s]
+ 56%|#####6 | 7.66M/13.6M [00:00<00:00, 80.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 85.3MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +570,7 @@ 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)
- 90.4422 90.0267 115.0666 89.8931 2.5116
+ 89.9606 89.9258 90.5808 89.7724 0.1615
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +609,7 @@ 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 8.414 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.848 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 4262298e7..b5e6b05c6 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ 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)
- 120.1325 120.0947 123.4845 119.5897 0.4378
+ 118.8230 118.7278 125.9085 117.1407 0.9966
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.736 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.469 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 2c9f22e89..c489b474a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ 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 17.107 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.726 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 f8aa7f46a..eaeb9b649 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6622/132723 [00:00<00:01, 66209.01KB/s]
- 11%|#1 | 14766/132723 [00:00<00:01, 75163.21KB/s]
- 17%|#7 | 22866/132723 [00:00<00:01, 77826.73KB/s]
- 23%|##3 | 30941/132723 [00:00<00:01, 78977.95KB/s]
- 29%|##9 | 39059/132723 [00:00<00:01, 79768.99KB/s]
- 36%|###5 | 47194/132723 [00:00<00:01, 80304.18KB/s]
- 42%|####1 | 55379/132723 [00:00<00:00, 80808.34KB/s]
- 48%|####7 | 63473/132723 [00:00<00:00, 80845.37KB/s]
- 54%|#####3 | 71666/132723 [00:00<00:00, 81180.81KB/s]
- 60%|###### | 79841/132723 [00:01<00:00, 81353.55KB/s]
- 66%|######6 | 87997/132723 [00:01<00:00, 81413.13KB/s]
- 72%|#######2 | 96213/132723 [00:01<00:00, 81636.61KB/s]
- 79%|#######8 | 104377/132723 [00:01<00:00, 81529.26KB/s]
- 85%|########4 | 112530/132723 [00:01<00:00, 81495.50KB/s]
- 91%|######### | 120682/132723 [00:01<00:00, 81499.63KB/s]
- 97%|#########7| 128868/132723 [00:01<00:00, 81605.65KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 80475.49KB/s]
+ 3%|2 | 3601/132723 [00:00<00:03, 36005.48KB/s]
+ 7%|7 | 9727/132723 [00:00<00:02, 50858.06KB/s]
+ 13%|#3 | 17631/132723 [00:00<00:01, 63722.48KB/s]
+ 20%|#9 | 26195/132723 [00:00<00:01, 72372.09KB/s]
+ 25%|##5 | 33433/132723 [00:00<00:01, 61690.61KB/s]
+ 31%|###1 | 41350/132723 [00:00<00:01, 67021.47KB/s]
+ 37%|###7 | 49140/132723 [00:00<00:01, 67980.72KB/s]
+ 43%|####3 | 57640/132723 [00:00<00:01, 73005.77KB/s]
+ 49%|####9 | 65523/132723 [00:00<00:00, 71598.58KB/s]
+ 55%|#####5 | 73054/132723 [00:01<00:00, 72668.42KB/s]
+ 61%|###### | 80396/132723 [00:01<00:00, 65841.54KB/s]
+ 66%|######5 | 87462/132723 [00:01<00:00, 67158.40KB/s]
+ 72%|#######2 | 96025/132723 [00:01<00:00, 72349.88KB/s]
+ 78%|#######7 | 103386/132723 [00:01<00:00, 64296.36KB/s]
+ 84%|########4 | 111924/132723 [00:01<00:00, 69897.89KB/s]
+ 90%|########9 | 119153/132723 [00:01<00:00, 61415.14KB/s]
+ 96%|#########6| 127575/132723 [00:01<00:00, 67227.12KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67286.45KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +501,7 @@ 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 37.229 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 33.677 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 514987692..9378b8778 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>11:05.297</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:11.814</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</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>02:56.902</p></td>
+<td><p>02:54.561</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>02:37.229</p></td>
+<td><p>02:33.677</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:51.736</p></td>
+<td><p>01:51.469</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>01:17.107</p></td>
+<td><p>01:31.726</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>01:08.414</p></td>
+<td><p>01:07.848</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>00:29.958</p></td>
+<td><p>00:29.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.219</p></td>
+<td><p>00:21.971</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.727</p></td>
+<td><p>00:21.548</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index ee8a0c51a..1e3b5bf1a 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ 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.zip68faa473-ff07-4865-9f37-c414c57e207f 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.zip66792731-faea-4dba-b9bf-6fcdf29913aa from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 9cb1dc0a1..8ae9eff77 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:42.144</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.605</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</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>00:38.924</p></td>
+<td><p>00:37.557</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>00:02.244</p></td>
+<td><p>00:02.135</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>00:00.968</p></td>
+<td><p>00:00.906</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>00:00.008</p></td>
+<td><p>00:00.007</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 965f29e46..518804dc9 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ 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: 6678us [6678us] (46.01%; 46.01%)
-FoldScaleAxis: 7834us [6us] (53.99%; 53.99%)
- FoldConstant: 7829us [1627us] (53.95%; 99.93%)
- InferType: 6202us [6202us] (42.74%; 79.22%)
+InferType: 6769us [6769us] (46.20%; 46.20%)
+FoldScaleAxis: 7882us [5us] (53.80%; 53.80%)
+ FoldConstant: 7876us [1641us] (53.76%; 99.93%)
+ InferType: 6235us [6235us] (42.56%; 79.16%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ 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: 6253us [6253us] (43.24%; 43.24%)
-FoldScaleAxis: 8209us [4us] (56.76%; 56.76%)
- FoldConstant: 8204us [1702us] (56.73%; 99.95%)
- InferType: 6503us [6503us] (44.96%; 79.26%)
+InferType: 6311us [6311us] (44.88%; 44.88%)
+FoldScaleAxis: 7752us [4us] (55.12%; 55.12%)
+ FoldConstant: 7747us [1604us] (55.09%; 99.95%)
+ InferType: 6143us [6143us] (43.69%; 79.30%)
</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 de5e7b8d0..7011e94c5 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ 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: 49.141609 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 50.695199 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 d44b10f73..fb5cfcfe8 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.657923 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.696495 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 4656bf1c1..db64931b4 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ 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: 0.018327
-Baseline: 3.438462
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017770
+Baseline: 3.280152
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ 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: 0.309396
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.303941
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.341529
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.333138
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ 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: 0.118068
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.113462
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ 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: 0.112702
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109358
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ 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: 0.111174
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110568
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ 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: 0.147364
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145905
</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 3745dd6dd..e0ef333be 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:34.798</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:33.868</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</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>00:32.573</p></td>
+<td><p>00:31.709</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>00:01.225</p></td>
+<td><p>00:01.189</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>00:01.001</p></td>
+<td><p>00:00.970</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 43d2b0ed2..482d56cbf 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>06:09.753</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:05.289</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</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>03:23.985</p></td>
+<td><p>03:20.275</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>01:23.109</p></td>
+<td><p>01:21.715</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>00:46.743</p></td>
+<td><p>00:46.235</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>00:18.525</p></td>
+<td><p>00:19.863</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>00:08.802</p></td>
+<td><p>00:08.705</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>00:08.588</p></td>
+<td><p>00:08.496</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 e1fbcb60a..9f2d2e232 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
@@ -492,10 +492,10 @@ cooperative fetching, unrolling and operator fusion.</p>
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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [192]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
@@ -503,27 +503,178 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 9) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + threadIdx.x_1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((ax0.ax1. [...]
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)) < 24), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [192], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + threadIdx.x_2)] = kernel[((((((blockIdx.x*36864) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 8)), 3)*4608)) + (rc.outer.outer*72)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*8) + threadIdx.x_2), 24), 3)*9)) + (ry.outer.outer*3)) + floormod(((ax0.ax1.fused.ax2.fuse [...]
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*576)
+ {
+ for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 144) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4) + floordiv(threadIdx.x_1, 7)), 9)) && (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*4) + floordiv(threadIdx.x_1, 7)), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && [...]
}
- }
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.inner*63) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*24) + (rc.inner*3)) + rx.outer.inner)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 28), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 252)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 112), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (floordiv((threadIdx.x_2 + 140), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 168), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 56), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 224), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 252), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 280), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 308)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 308), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 336), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 48)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 364), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 172), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 420)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 420), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 448), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 476)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 476), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 92), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 504), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 40)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 532)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 532), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 148), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 560), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 616), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 644)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 644), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 672), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 700)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 700), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 124), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 728), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 756)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 756), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 60), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 812)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 812), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 44), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 840), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 868)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 868), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 100), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 896), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 924)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 924), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 52)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 952), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 184), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1008), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1036)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1036), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 76), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1064), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1092)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1092), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 44)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1120), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1148)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1148), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1204)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1204), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1232), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1260)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1260), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 36)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1288), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1316)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1316), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1400), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1428)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1428), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1456), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ kernel.shared_1[(threadIdx.x_2 + 1484)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1484), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 1512), 192)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 56)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ for (rc.inner: int32, 0, 4) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3))]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 768)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 769)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 49)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*252) + (rc.inner*63)) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*12)) + (rc.inner*3)) + 770)]))
+ }
}
}
}
@@ -535,6 +686,13 @@ cooperative fetching, unrolling and operator fusion.</p>
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 196)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 203)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 210)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 217)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 224)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 231)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + floormod(threadIdx.x, 7)) + 238)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
}
}
</pre></div>
@@ -570,7 +728,7 @@ 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: 0.390 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.288 ms
</pre></div>
</div>
</div>
@@ -601,8 +759,8 @@ 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=8)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
@@ -611,19 +769,19 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_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=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_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=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
@@ -648,14 +806,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+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=28)
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=56)
+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=28)
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", 0)
+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:
@@ -673,10 +831,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[192];
+extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -684,27 +842,121 @@ extern "C" __global__ void __launch_bounds__(56) default_function_kern
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 9; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x))] = (((((1 <= (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer)) && ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + ((int)threadIdx.x)) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fu [...]
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 144; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + ((int)threadIdx.x))] = (((((1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4) + (((int)threadIdx.x) / 7)) % 9)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 4) + (((int)threadIdx.x) / 7)) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + ((((ax0_ax1 [...]
}
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) < 24) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + ((int)threadIdx.x))] = kernel[((((((((int)blockIdx.x) * 36864) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 3)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 8) + ((int)threadIdx.x)) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 2) + ((int)threadIdx.x)) % 3))];
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 28)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 252)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 140) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 56) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 252)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 180)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 88) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 308)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 116) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 432)];
+ kernel_shared[(((int)threadIdx.x) + 364)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 172) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 420)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 420) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 108)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 476)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 476) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 92) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 504) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 360)];
+ kernel_shared[(((int)threadIdx.x) + 532)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 532) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 148) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 616) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 644)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 644) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 68) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 288)];
+ kernel_shared[(((int)threadIdx.x) + 700)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 700) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 124) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 728) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 152) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 756)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 756) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 60) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 812)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 812) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 44) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 840) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 216)];
+ kernel_shared[(((int)threadIdx.x) + 868)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 868) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 100) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 128) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 924)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 924) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 468)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 952) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 184) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 20) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1036)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1036) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 76) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1064) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 104) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1092)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1092) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 396)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 160) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1148)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1148) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 188) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 1204)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1204) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 52) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1260)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1260) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 324)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1288) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 136) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1316)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1316) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 164) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 28) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1400) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1428)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1428) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 252)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1484)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1484) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 140) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 1512) / 192) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 504)];
}
__syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_inner * 63) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + (rc_inner * 3)) + rx_outer_inner)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3))]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 768)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 769)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 252) + (rc_inner * 63)) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 12)) + (rc_inner * 3)) + 770)]));
}
}
}
@@ -716,6 +968,13 @@ extern "C" __global__ void __launch_bounds__(56) default_function_kern
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 196)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 203)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 210)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 217)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 224)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 231)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (((int)threadIdx.x) % 7)) + 238)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -751,7 +1010,7 @@ 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> ( 3 minutes 23.985 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.275 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 e0f646f83..c41503b76 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.4363 9.4414 9.4586 9.4090 0.0206
+ 9.8768 9.8922 9.9026 9.8356 0.0294
</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 60b28d9fa..7b355138f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
- 760.1900 759.5860 761.8455 759.1385 1.1848
+ 748.9067 748.0110 750.8205 747.8886 1.3542
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ 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 23.109 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.715 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 a51b249b0..595fcbb92 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,29 +625,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer: int32, 0, 2) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 32) {
+ for (i.outer.inner: int32, 0, 16) {
for (i.inner.init: int32, 0, 4) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
for (i.inner: int32, 0, 4) {
for (j: int32, 0, 16) {
- let cse_var_3: int32 = floordiv(i0.outer.i1.outer.fused, 2)
- let cse_var_2: int32 = (((i.outer.inner*64) + (i.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*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
+ compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + j)]*max(placeholder[((((i0.outer*16384) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_5: int32 = (i0.outer.i1.outer.fused*8)
- let cse_var_4: int32 = ((i0.inner*512) + cse_var_5)
- compute[ramp(cse_var_4, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_5) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_4, 1, 8)]), broadcast(0f32, 8))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_2: int32 = ((((i0.outer*32768) + (i0.inner*512)) + (i1.outer*16)) + i1.inner)
+ compute[cse_var_2] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_2]), 0f32)
+ }
}
}
}
@@ -685,7 +688,7 @@ 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: 2.900 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.494 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 7f10a1670..d674289d2 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:45.947</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.621</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.912</p></td>
+<td><p>00:45.586</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index e18486caa..04fc82aad 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 177.12/177.12 result: MeasureResult(costs=(0.0013070251666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0436105728149414, timestamp=1661349633.8468184) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/177.12 result: Traceback (most recent call last):
+No: 9 GFLOPS: 177.37/177.37 result: MeasureResult(costs=(0.0013052061555555556,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1578433513641357, timestamp=1661354693.720595) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/177.37 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
@@ -1560,8 +1560,8 @@ 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, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.14/260.14 result: MeasureResult(costs=(0.0008899052872928177,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7701294422149658, timestamp=1661349634.7686515) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 11 GFLOPS: 259.85/259.85 result: MeasureResult(costs=(0.0008908887513812154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4934370517730713, timestamp=1661354694.6415231) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/259.85 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
@@ -1684,7 +1684,7 @@ 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, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/259.85 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
@@ -1807,7 +1807,7 @@ 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, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/259.85 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
@@ -1930,9 +1930,9 @@ 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, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.46/260.14 result: MeasureResult(costs=(0.0424288705,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8363773822784424, timestamp=1661349639.3378294) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/260.14 result: MeasureResult(costs=(0.0693977445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.56325888633728, timestamp=1661349640.5698924) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.45/259.85 result: MeasureResult(costs=(0.042488775250000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8390161991119385, timestamp=1661354699.1933777) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/259.85 result: MeasureResult(costs=(0.06939597,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.548490285873413, timestamp=1661354700.425302) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/259.85 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
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 27.29/260.14 result: MeasureResult(costs=(0.00848380482352941,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3170392513275146, timestamp=1661349651.672901) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 18 GFLOPS: 26.64/259.85 result: MeasureResult(costs=(0.008689362785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2846324443817139, timestamp=1661354711.4435625) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/259.85 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
@@ -2074,7 +2074,7 @@ 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, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.14 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/259.85 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
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001226
+Time cost of this operator: 0.001231
</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 4d2c1bc39..9f7445bd9 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.1 98.735 (1, 2, 10, 10, 3) 2 1 [310.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.961 (1, 6, 10, 10) 1 1 [3.017]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 0.305 (1, 1, 10, 10, 3) 1 1 [0.957]
-Total_time - 314.074 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.4 98.728 (1, 2, 10, 10, 3) 2 1 [312.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.054 0.965 (1, 6, 10, 10) 1 1 [3.054]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.97 0.306 (1, 1, 10, 10, 3) 1 1 [0.97]
+Total_time - 316.424 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 119.7 97.749 (1, 6, 10, 10, 1) 2 1 [119.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.796 1.467 (1, 6, 10, 10) 1 1 [1.796]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.784 (1, 1, 10, 10, 3) 1 1 [0.96]
-Total_time - 122.456 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.562 96.752 (1, 6, 10, 10, 1) 2 1 [80.562]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.746 2.097 (1, 6, 10, 10) 1 1 [1.746]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 1.151 (1, 1, 10, 10, 3) 1 1 [0.958]
+Total_time - 83.267 - - - - -
</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 23e54ea05..c4ed519d6 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ 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/tmp9f61elw3/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmppn5xytk5/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ 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/tmp9f61elw3/images/target contains 8144 images
-/tmp/tmp9f61elw3/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/tmppn5xytk5/images/target contains 8144 images
+/tmp/tmppn5xytk5/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ 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: 0.2414 - accuracy: 0.9196 - val_loss: 0.1643 - val_accuracy: 0.9532
+328/328 - 55s - loss: 0.2253 - accuracy: 0.9240 - val_loss: 0.1309 - val_accuracy: 0.9581
Epoch 2/3
-328/328 - 52s - loss: 0.1013 - accuracy: 0.9627 - val_loss: 0.1504 - val_accuracy: 0.9585
+328/328 - 52s - loss: 0.0984 - accuracy: 0.9626 - val_loss: 0.1109 - val_accuracy: 0.9653
Epoch 3/3
-328/328 - 52s - loss: 0.0673 - accuracy: 0.9748 - val_loss: 0.1187 - val_accuracy: 0.9641
+328/328 - 52s - loss: 0.0649 - accuracy: 0.9763 - val_loss: 0.1147 - val_accuracy: 0.9649
-<keras.callbacks.History object at 0x7f01ce8670d0>
+<keras.callbacks.History object at 0x7f29d76e8090>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 54.984 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 16.141 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 0f7567c12..e005b60cc 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>05:48.614</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:07.747</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:54.984</p></td>
+<td><p>05:16.141</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>00:42.293</p></td>
+<td><p>00:41.089</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.028</p></td>
+<td><p>00:07.320</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:03.306</p></td>
+<td><p>00:03.194</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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 18dff9c12..a5607a2d1 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:43.314</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:42.002</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.575</p></td>
+<td><p>00:30.815</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:10.073</p></td>
+<td><p>00:09.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:01.659</p></td>
+<td><p>00:01.417</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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 bf9807162..f356fa883 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ 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 0x7f0139c5fef0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f295b594a70>
</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 5ef28309b..3dd08b212 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:04.136</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.027</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</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>00:01.894</p></td>
+<td><p>00:01.859</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>00:01.002</p></td>
+<td><p>00:00.946</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>00:00.534</p></td>
+<td><p>00:00.524</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>00:00.517</p></td>
+<td><p>00:00.508</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>00:00.105</p></td>
+<td><p>00:00.100</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.042</p></td>
+<td><p>00:00.049</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 8cc9fc714..d83178f04 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ 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/tmpz397jfty/input0.cc'\nsource_filename = \"/tmp/tmpz397jfty/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/tmp4awx27wi/input0.cc'\nsource_filename = \"/tmp/tmp4awx27wi/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/install/nnpack.html b/docs/install/nnpack.html
index 3153785d7..aa2238b85 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -224,7 +224,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/objects.inv b/docs/objects.inv
index f5bf3c5ec..9303fd403 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 5aa8d9736..bd00eaad1 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<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>
@@ -1886,7 +1886,7 @@ Candidates:
<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">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index 34ea38e5b..44037bd95 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -705,187 +705,196 @@
<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tvm_throw_last_error" title="tvm.tir.tvm_throw_last_error"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tvm_throw_last_error</span></code></a>()</p></td>
<td><p>Throw TVMGetLastError()</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.infinity" title="tvm.tir.infinity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infinity</span></code></a>(dtype[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.vectorlow" title="tvm.tir.vectorlow"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorlow</span></code></a>(dtype, vec)</p></td>
+<td><p>Get the low level half of the vector</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.vectorhigh" title="tvm.tir.vectorhigh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorhigh</span></code></a>(dtype, vec)</p></td>
+<td><p>Get the high level half of the vector</p></td>
+</tr>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.vectorcombine" title="tvm.tir.vectorcombine"><code class="xref py py-obj docutils literal notranslate"><span class="pre">vectorcombine</span></code></a>(dtype, vec1, vec2)</p></td>
+<td><p>Concat two vectors</p></td>
+</tr>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.infinity" title="tvm.tir.infinity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infinity</span></code></a>(dtype[, span])</p></td>
<td><p>infinity value of dtype</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.reinterpret" title="tvm.tir.reinterpret"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reinterpret</span></code></a>(dtype, value)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.reinterpret" title="tvm.tir.reinterpret"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reinterpret</span></code></a>(dtype, value)</p></td>
<td><p>infinity value of dtype</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp" title="tvm.tir.exp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp" title="tvm.tir.exp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp</span></code></a>(x)</p></td>
<td><p>Take exponential of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp2" title="tvm.tir.exp2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp2</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp2" title="tvm.tir.exp2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp2</span></code></a>(x)</p></td>
<td><p>Calculate 2**x</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.exp10" title="tvm.tir.exp10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp10</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.exp10" title="tvm.tir.exp10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exp10</span></code></a>(x)</p></td>
<td><p>Calculate 10**x</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log" title="tvm.tir.log"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log" title="tvm.tir.log"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log</span></code></a>(x)</p></td>
<td><p>Take log of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log2" title="tvm.tir.log2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log2</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log2" title="tvm.tir.log2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log2</span></code></a>(x)</p></td>
<td><p>Take log2 of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log10" title="tvm.tir.log10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log10</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log10" title="tvm.tir.log10"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log10</span></code></a>(x)</p></td>
<td><p>Take log10 of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.log1p" title="tvm.tir.log1p"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log1p</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.log1p" title="tvm.tir.log1p"><code class="xref py py-obj docutils literal notranslate"><span class="pre">log1p</span></code></a>(x)</p></td>
<td><p>Take log(x + 1) with respect to input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ldexp" title="tvm.tir.ldexp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ldexp</span></code></a>(x1, x2)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ldexp" title="tvm.tir.ldexp"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ldexp</span></code></a>(x1, x2)</p></td>
<td><p>Returns x1 * (2 ** x2).</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.clz" title="tvm.tir.clz"><code class="xref py py-obj docutils literal notranslate"><span class="pre">clz</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.clz" title="tvm.tir.clz"><code class="xref py py-obj docutils literal notranslate"><span class="pre">clz</span></code></a>(x)</p></td>
<td><p>Count leading zero bits of an integer x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sin" title="tvm.tir.sin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sin</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sin" title="tvm.tir.sin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sin</span></code></a>(x)</p></td>
<td><p>Take sin of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sinh" title="tvm.tir.sinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sinh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sinh" title="tvm.tir.sinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sinh</span></code></a>(x)</p></td>
<td><p>Take sinh of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.asin" title="tvm.tir.asin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asin</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.asin" title="tvm.tir.asin"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asin</span></code></a>(x)</p></td>
<td><p>Take asin of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.asinh" title="tvm.tir.asinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asinh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.asinh" title="tvm.tir.asinh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">asinh</span></code></a>(x)</p></td>
<td><p>Take asinh of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.cos" title="tvm.tir.cos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cos</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.cos" title="tvm.tir.cos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cos</span></code></a>(x)</p></td>
<td><p>Take cos of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.cosh" title="tvm.tir.cosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cosh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.cosh" title="tvm.tir.cosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cosh</span></code></a>(x)</p></td>
<td><p>Take cosh of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.acos" title="tvm.tir.acos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acos</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.acos" title="tvm.tir.acos"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acos</span></code></a>(x)</p></td>
<td><p>Take acos of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.acosh" title="tvm.tir.acosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acosh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.acosh" title="tvm.tir.acosh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">acosh</span></code></a>(x)</p></td>
<td><p>Take acos of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tan" title="tvm.tir.tan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tan</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tan" title="tvm.tir.tan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tan</span></code></a>(x)</p></td>
<td><p>Take tan of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.tanh" title="tvm.tir.tanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tanh</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.tanh" title="tvm.tir.tanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">tanh</span></code></a>(x)</p></td>
<td><p>Take hyperbolic tanh of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atan" title="tvm.tir.atan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atan" title="tvm.tir.atan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan</span></code></a>(x)</p></td>
<td><p>Take atan of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atan2" title="tvm.tir.atan2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan2</span></code></a>(x1, x2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atan2" title="tvm.tir.atan2"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atan2</span></code></a>(x1, x2)</p></td>
<td><p>Take arctan2(x1, x2).</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.atanh" title="tvm.tir.atanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atanh</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.atanh" title="tvm.tir.atanh"><code class="xref py py-obj docutils literal notranslate"><span class="pre">atanh</span></code></a>(x)</p></td>
<td><p>Take atanh of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.erf" title="tvm.tir.erf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">erf</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.erf" title="tvm.tir.erf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">erf</span></code></a>(x)</p></td>
<td><p>Take gauss error function of the input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sigmoid" title="tvm.tir.sigmoid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sigmoid</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sigmoid" title="tvm.tir.sigmoid"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sigmoid</span></code></a>(x)</p></td>
<td><p>Quick function to get sigmoid</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sqrt" title="tvm.tir.sqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sqrt</span></code></a>(x)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sqrt" title="tvm.tir.sqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sqrt</span></code></a>(x)</p></td>
<td><p>Take square root of input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.rsqrt" title="tvm.tir.rsqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rsqrt</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.rsqrt" title="tvm.tir.rsqrt"><code class="xref py py-obj docutils literal notranslate"><span class="pre">rsqrt</span></code></a>(x)</p></td>
<td><p>Take reciprocal of square root of input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floor" title="tvm.tir.floor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floor</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floor" title="tvm.tir.floor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floor</span></code></a>(x[, span])</p></td>
<td><p>Take floor of float input x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ceil" title="tvm.tir.ceil"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceil</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ceil" title="tvm.tir.ceil"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceil</span></code></a>(x[, span])</p></td>
<td><p>Take ceil of float input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.hypot" title="tvm.tir.hypot"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hypot</span></code></a>(x1, x2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.hypot" title="tvm.tir.hypot"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hypot</span></code></a>(x1, x2)</p></td>
<td><p>Equivalent to sqrt(x1**2 + x2**2), element-wise.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.trunc" title="tvm.tir.trunc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">trunc</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.trunc" title="tvm.tir.trunc"><code class="xref py py-obj docutils literal notranslate"><span class="pre">trunc</span></code></a>(x[, span])</p></td>
<td><p>Get truncated value of the input.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.abs" title="tvm.tir.abs"><code class="xref py py-obj docutils literal notranslate"><span class="pre">abs</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.abs" title="tvm.tir.abs"><code class="xref py py-obj docutils literal notranslate"><span class="pre">abs</span></code></a>(x[, span])</p></td>
<td><p>Get absolute value of the input element-wise.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.round" title="tvm.tir.round"><code class="xref py py-obj docutils literal notranslate"><span class="pre">round</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.round" title="tvm.tir.round"><code class="xref py py-obj docutils literal notranslate"><span class="pre">round</span></code></a>(x[, span])</p></td>
<td><p>Round elements of the array to the nearest integer.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.nextafter" title="tvm.tir.nextafter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nextafter</span></code></a>(x1, x2)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.nextafter" title="tvm.tir.nextafter"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nextafter</span></code></a>(x1, x2)</p></td>
<td><p>Return the next floating-point value after x1 towards x2.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.nearbyint" title="tvm.tir.nearbyint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nearbyint</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.nearbyint" title="tvm.tir.nearbyint"><code class="xref py py-obj docutils literal notranslate"><span class="pre">nearbyint</span></code></a>(x[, span])</p></td>
<td><p>Round elements of the array to the nearest integer.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.power" title="tvm.tir.power"><code class="xref py py-obj docutils literal notranslate"><span class="pre">power</span></code></a>(x, y[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.power" title="tvm.tir.power"><code class="xref py py-obj docutils literal notranslate"><span class="pre">power</span></code></a>(x, y[, span])</p></td>
<td><p>x power y</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.popcount" title="tvm.tir.popcount"><code class="xref py py-obj docutils literal notranslate"><span class="pre">popcount</span></code></a>(x)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.popcount" title="tvm.tir.popcount"><code class="xref py py-obj docutils literal notranslate"><span class="pre">popcount</span></code></a>(x)</p></td>
<td><p>Count the number of set bits in input x.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.fmod" title="tvm.tir.fmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fmod</span></code></a>(x, y)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.fmod" title="tvm.tir.fmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">fmod</span></code></a>(x, y)</p></td>
<td><p>Return the remainder of x divided by y with the same sign as x.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.if_then_else" title="tvm.tir.if_then_else"><code class="xref py py-obj docutils literal notranslate"><span class="pre">if_then_else</span></code></a>(cond, t, f[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.if_then_else" title="tvm.tir.if_then_else"><code class="xref py py-obj docutils literal notranslate"><span class="pre">if_then_else</span></code></a>(cond, t, f[, span])</p></td>
<td><p>Conditional selection expression.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.likely" title="tvm.tir.likely"><code class="xref py py-obj docutils literal notranslate"><span class="pre">likely</span></code></a>(cond[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.likely" title="tvm.tir.likely"><code class="xref py py-obj docutils literal notranslate"><span class="pre">likely</span></code></a>(cond[, span])</p></td>
<td><p>Mark condition as likely.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isnan" title="tvm.tir.isnan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnan</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isnan" title="tvm.tir.isnan"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnan</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is Nan.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isnullptr" title="tvm.tir.isnullptr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnullptr</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isnullptr" title="tvm.tir.isnullptr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isnullptr</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is nullptr.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isfinite" title="tvm.tir.isfinite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isfinite</span></code></a>(x[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isfinite" title="tvm.tir.isfinite"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isfinite</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is finite.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.isinf" title="tvm.tir.isinf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isinf</span></code></a>(x[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.isinf" title="tvm.tir.isinf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">isinf</span></code></a>(x[, span])</p></td>
<td><p>Check if input value is infinite.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.copysign" title="tvm.tir.copysign"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copysign</span></code></a>(x1, x2)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.copysign" title="tvm.tir.copysign"><code class="xref py py-obj docutils literal notranslate"><span class="pre">copysign</span></code></a>(x1, x2)</p></td>
<td><p>Change the sign of x1 to that of x2, element-wise.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.div" title="tvm.tir.div"><code class="xref py py-obj docutils literal notranslate"><span class="pre">div</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.div" title="tvm.tir.div"><code class="xref py py-obj docutils literal notranslate"><span class="pre">div</span></code></a>(a, b[, span])</p></td>
<td><p>Compute a / b as in C/C++ semantics.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.indexdiv" title="tvm.tir.indexdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexdiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.indexdiv" title="tvm.tir.indexdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexdiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute floor(a / b) where a and b are non-negative.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.indexmod" title="tvm.tir.indexmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexmod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.indexmod" title="tvm.tir.indexmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">indexmod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the remainder of indexdiv.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.truncdiv" title="tvm.tir.truncdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncdiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.truncdiv" title="tvm.tir.truncdiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncdiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the truncdiv of two expressions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.truncmod" title="tvm.tir.truncmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncmod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.truncmod" title="tvm.tir.truncmod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">truncmod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the truncmod of two expressions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floordiv" title="tvm.tir.floordiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floordiv</span></code></a>(a, b[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floordiv" title="tvm.tir.floordiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floordiv</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the floordiv of two expressions.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.floormod" title="tvm.tir.floormod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floormod</span></code></a>(a, b[, span])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.floormod" title="tvm.tir.floormod"><code class="xref py py-obj docutils literal notranslate"><span class="pre">floormod</span></code></a>(a, b[, span])</p></td>
<td><p>Compute the floormod of two expressions.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.ceildiv" title="tvm.tir.ceildiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceildiv</span></code></a>(lhs, rhs[, span])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.ceildiv" title="tvm.tir.ceildiv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ceildiv</span></code></a>(lhs, rhs[, span])</p></td>
<td><p>Generic ceildiv operator.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.comm_reducer" title="tvm.tir.comm_reducer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">comm_reducer</span></code></a>(fcombine, fidentity[, name])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.comm_reducer" title="tvm.tir.comm_reducer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">comm_reducer</span></code></a>(fcombine, fidentity[, name])</p></td>
<td><p>Create a commutative reducer for reduction.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.min" title="tvm.tir.min"><code class="xref py py-obj docutils literal notranslate"><span class="pre">min</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.min" title="tvm.tir.min"><code class="xref py py-obj docutils literal notranslate"><span class="pre">min</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a min expression over axis.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.max" title="tvm.tir.max"><code class="xref py py-obj docutils literal notranslate"><span class="pre">max</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.max" title="tvm.tir.max"><code class="xref py py-obj docutils literal notranslate"><span class="pre">max</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a max expression over axis.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.sum" title="tvm.tir.sum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sum</span></code></a>(expr, axis[, where, init])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.sum" title="tvm.tir.sum"><code class="xref py py-obj docutils literal notranslate"><span class="pre">sum</span></code></a>(expr, axis[, where, init])</p></td>
<td><p>Create a sum expression over axis.</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.q_multiply_shift" title="tvm.tir.q_multiply_shift"><code class="xref py py-obj docutils literal notranslate"><span class="pre">q_multiply_shift</span></code></a>(x, y, q, s)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.q_multiply_shift" title="tvm.tir.q_multiply_shift"><code class="xref py py-obj docutils literal notranslate"><span class="pre">q_multiply_shift</span></code></a>(x, y, q, s)</p></td>
<td><p>Execute a multiplication between two Q-numbers x and y followed by a right shift s.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendAllocWorkspace" title="tvm.tir.TVMBackendAllocWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendAllocWorkspace</span></code></a>(device_type, ...)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendAllocWorkspace" title="tvm.tir.TVMBackendAllocWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendAllocWorkspace</span></code></a>(device_type, ...)</p></td>
<td><p>Backend function to allocate temporal workspace</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendFreeWorkspace" title="tvm.tir.TVMBackendFreeWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendFreeWorkspace</span></code></a>(device_type, ...)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.TVMBackendFreeWorkspace" title="tvm.tir.TVMBackendFreeWorkspace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TVMBackendFreeWorkspace</span></code></a>(device_type, ...)</p></td>
<td><p>Backend function to free temporal workspace.</p></td>
</tr>
</tbody>
@@ -3386,6 +3395,66 @@ tvm.default_trace_action is used.</p>
</dl>
</dd></dl>
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.vectorlow">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">vectorlow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.vectorlow" title="Permalink to this definition">¶</a></dt>
+<dd><p>Get the low level half of the vector</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a>) – The data type of the result.</p></li>
+<li><p><strong>vec</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a>) – The input vector.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.vectorhigh">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">vectorhigh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.vectorhigh" title="Permalink to this definition">¶</a></dt>
+<dd><p>Get the high level half of the vector</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>dtype</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a>) – The data type of the result.</p></li>
+<li><p><strong>vec</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a>) – The input vector.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
+<dl class="py function">
+<dt class="sig sig-object py" id="tvm.tir.vectorcombine">
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">vectorcombine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vec2</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="# [...]
+<dd><p>Concat two vectors</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>vec1</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a>) – The input vector.</p></li>
+<li><p><strong>vec2</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a>) – The input vector.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Returns</dt>
+<dd class="field-even"><p><strong>call</strong> – The call expression.</p>
+</dd>
+<dt class="field-odd">Return type</dt>
+<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.ir.PrimExpr" title="tvm.ir.PrimExpr">PrimExpr</a></p>
+</dd>
+</dl>
+</dd></dl>
+
<dl class="py function">
<dt class="sig sig-object py" id="tvm.tir.infinity">
<span class="sig-prename descclassname"><span class="pre">tvm.tir.</span></span><span class="sig-name descname"><span class="pre">infinity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><span class="pre">str</span></a></span></em>, <em cl [...]
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index dafd2667c..e4be1c8cb 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/a0fe74b3c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 df67b124f..29c9d2ebb 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/a0fe74b3c/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 39518093d..69e46ba67 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/a0fe74b3c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 2f4997c91..8cff8c29f 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/a0fe74b3c/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 32eceec5d..4055194ef 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/a0fe74b3c/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 efa4c59c1..6c1ffd558 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/a0fe74b3c/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 38f17eadb..378aac46a 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/a0fe74b3c/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 a6f32d64c..31c10ea42 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/a0fe74b3c/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/web/src/runtime.ts#L1145">runtime.ts:1145</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/a0fe74b3c/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 3e3f8d575..13c3e787f 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/a0fe74b3c/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 81ddebc93..2d1e49b69 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/a0fe74b3c/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 743d949f0..d1b5253c9 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/a0fe74b3c/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 5fc2e5c64..9e7dc3a1c 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/a0fe74b3c/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 e5f50270c..898b39a29 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/a0fe74b3c/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 787ab3498..f14829f7c 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/a0fe74b3c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 ed84016c7..13e495223 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/a0fe74b3c/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 0d50ba1ca..b7219db0b 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/a0fe74b3c/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 03d5b4cd0..a51419b66 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/a0fe74b3c/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 1e7381e3e..b25d039cd 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/a0fe74b3c/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 ab1cfa581..d523b514d 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/a0fe74b3c/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 80ff495e5..2ceb45574 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/a0fe74b3c/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 090581a13..82be3d0de 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/a0fe74b3c/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/web/src/runtime.ts#L1367">runtime.ts:1367</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/a0fe74b3c/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 1d10eace4..4d672deb8 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/a0fe74b3c/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 263c1efe5..69b6054df 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/a0fe74b3c/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 a920cb272..0e355d17a 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/a0fe74b3c/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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/a0fe74b3c/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/038523e5a/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 f7294a418..98ad12dfc 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 936dafe01..73c6483f7 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:21.118</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.899</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</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>00:21.111</p></td>
+<td><p>00:20.893</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>00:00.006</p></td>
+<td><p>00:00.007</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 1f66f0898..5783468b1 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ 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 23.11s!
+resnet18_v1 inference graph built in 22.29s!
</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 da6685345..e8b4d74d4 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ 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:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.00s!
+yolov3-tiny inference graph built in 15.73s!
</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 307394bfd..52c2c03df 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>01:32.089</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.028</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:48.708</p></td>
+<td><p>00:48.654</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>00:43.381</p></td>
+<td><p>00:42.374</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 01b3366f3..02133db7e 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:03.241</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.206</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:02.841</p></td>
+<td><p>00:02.818</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>00:00.400</p></td>
+<td><p>00:00.389</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 1a5840e94..042eb7f40 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>00:00.710</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.702</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</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>00:00.380</p></td>
+<td><p>00:00.378</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>00:00.329</p></td>
+<td><p>00:00.324</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 d41da826e..169dbc6a7 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -565,7 +565,7 @@ 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: 97.717 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.664 ms
</pre></div>
</div>
</div>
@@ -639,7 +639,7 @@ 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 2.894 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.745 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 fd6650bbd..86b0142c9 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.62/10.62 result: MeasureResult(costs=(0.025273408200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5365078449249268, timestamp=1661348434.0935004) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.91/10.62 result: MeasureResult(costs=(0.09210231320000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.620378017425537, timestamp=1661348435.727656) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226401432,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5713176727294922, timestamp=1661348436.7807186) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.86 result: MeasureResult(costs=(0.1451110114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.440173625946045, timestamp=1661348439.790852) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.70/11.86 result: MeasureResult(costs=(0.0726271558,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2993955612182617, timestamp=1661348441.2189248) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.65/11.86 result: MeasureResult(costs=(0.162793359,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7800753116607666, timestamp=1661348444.0428634) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.86 result: MeasureResult(costs=(0.3082529676,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.050024509429932, timestamp=1661348449.664111) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.61/11.86 result: MeasureResult(costs=(0.025298854800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5479912757873535, timestamp=1661348450.2323132) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.90/11.86 result: MeasureResult(costs=(0.1415973892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.365818977355957, timestamp=1661348452.7178369) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.75/11.86 result: MeasureResult(costs=(0.0975465108,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6585078239440918, timestamp=1661348454.434552) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.55/10.55 result: MeasureResult(costs=(0.0254329492,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5407936573028564, timestamp=1661353477.6130342) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.70/10.55 result: MeasureResult(costs=(0.09938775879999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.738696575164795, timestamp=1661353479.3653543) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.022753001000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5553998947143555, timestamp=1661353480.4159062) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.83/11.80 result: MeasureResult(costs=(0.1470107178,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4691286087036133, timestamp=1661353482.9298115) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.65/11.80 result: MeasureResult(costs=(0.07357137999999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3136398792266846, timestamp=1661353484.374773) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.56/11.80 result: MeasureResult(costs=(0.17196434260000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8693912029266357, timestamp=1661353487.810747) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.80 result: MeasureResult(costs=(0.3072077364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.036134958267212, timestamp=1661353493.416797) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.80/11.80 result: MeasureResult(costs=(0.024851695200000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5428934097290039, timestamp=1661353493.97692) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.90/11.80 result: MeasureResult(costs=(0.1413844794,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.359879970550537, timestamp=1661353496.4544868) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.78/11.80 result: MeasureResult(costs=(0.0964911518,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6486308574676514, timestamp=1661353498.1598032) [('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 da6be2571..a0fbb6136 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.1972569200025, 'median': 492.7358948500114, 'std': 1.136266803649717}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 491.3749680500017, 'median': 491.27970339999933, 'std': 0.8558464573886108}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ 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: 17.62/ 17.62 GFLOPS | Progress: (4/20) | 6.34 s
-[Task 1/25] Current/Best: 6.12/ 17.62 GFLOPS | Progress: (8/20) | 9.35 s
-[Task 1/25] Current/Best: 11.55/ 22.77 GFLOPS | Progress: (12/20) | 11.75 s
-[Task 1/25] Current/Best: 16.46/ 22.84 GFLOPS | Progress: (16/20) | 13.43 s
-[Task 1/25] Current/Best: 11.62/ 23.87 GFLOPS | Progress: (20/20) | 15.16 s Done.
+[Task 1/25] Current/Best: 17.59/ 17.59 GFLOPS | Progress: (4/20) | 6.32 s
+[Task 1/25] Current/Best: 6.16/ 17.59 GFLOPS | Progress: (8/20) | 9.32 s
+[Task 1/25] Current/Best: 11.56/ 22.85 GFLOPS | Progress: (12/20) | 11.71 s
+[Task 1/25] Current/Best: 16.55/ 22.85 GFLOPS | Progress: (16/20) | 13.40 s
+[Task 1/25] Current/Best: 11.57/ 23.90 GFLOPS | Progress: (20/20) | 15.12 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.20/ 12.98 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 2/25] Current/Best: 14.13/ 18.72 GFLOPS | Progress: (8/20) | 5.08 s
-[Task 2/25] Current/Best: 21.02/ 21.02 GFLOPS | Progress: (12/20) | 6.39 s
-[Task 2/25] Current/Best: 12.28/ 21.02 GFLOPS | Progress: (16/20) | 7.64 s
-[Task 2/25] Current/Best: 19.14/ 21.02 GFLOPS | Progress: (20/20) | 9.22 s Done.
+[Task 2/25] Current/Best: 12.26/ 13.22 GFLOPS | Progress: (4/20) | 3.75 s
+[Task 2/25] Current/Best: 14.12/ 18.74 GFLOPS | Progress: (8/20) | 5.04 s
+[Task 2/25] Current/Best: 21.31/ 21.31 GFLOPS | Progress: (12/20) | 6.36 s
+[Task 2/25] Current/Best: 12.71/ 21.31 GFLOPS | Progress: (16/20) | 7.64 s
+[Task 2/25] Current/Best: 20.18/ 21.31 GFLOPS | Progress: (20/20) | 9.24 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/ 10.84 GFLOPS | Progress: (4/20) | 5.88 s
-[Task 3/25] Current/Best: 15.32/ 16.85 GFLOPS | Progress: (8/20) | 7.82 s
-[Task 3/25] Current/Best: 15.03/ 16.85 GFLOPS | Progress: (12/20) | 9.54 s
-[Task 3/25] Current/Best: 7.25/ 23.70 GFLOPS | Progress: (16/20) | 11.45 s
-[Task 3/25] Current/Best: 12.63/ 23.70 GFLOPS | Progress: (20/20) | 15.98 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.82 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.36/ 16.81 GFLOPS | Progress: (8/20) | 7.78 s
+[Task 3/25] Current/Best: 14.99/ 16.81 GFLOPS | Progress: (12/20) | 9.51 s
+[Task 3/25] Current/Best: 7.24/ 23.76 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 3/25] Current/Best: 12.68/ 23.76 GFLOPS | Progress: (20/20) | 15.93 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.56/ 20.39 GFLOPS | Progress: (4/20) | 2.39 s
-[Task 4/25] Current/Best: 6.57/ 20.39 GFLOPS | Progress: (8/20) | 6.70 s
-[Task 4/25] Current/Best: 22.37/ 22.37 GFLOPS | Progress: (12/20) | 11.23 s
-[Task 4/25] Current/Best: 16.84/ 22.37 GFLOPS | Progress: (16/20) | 13.47 s
-[Task 4/25] Current/Best: 13.39/ 22.37 GFLOPS | Progress: (20/20) | 15.35 s Done.
+[Task 4/25] Current/Best: 9.52/ 20.27 GFLOPS | Progress: (4/20) | 2.37 s
+[Task 4/25] Current/Best: 6.80/ 20.27 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 4/25] Current/Best: 21.38/ 21.38 GFLOPS | Progress: (12/20) | 11.18 s
+[Task 4/25] Current/Best: 17.48/ 21.38 GFLOPS | Progress: (16/20) | 13.41 s
+[Task 4/25] Current/Best: 13.36/ 21.38 GFLOPS | Progress: (20/20) | 15.30 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.63/ 10.22 GFLOPS | Progress: (4/20) | 2.62 s
-[Task 5/25] Current/Best: 11.72/ 12.79 GFLOPS | Progress: (8/20) | 4.70 s
-[Task 5/25] Current/Best: 11.66/ 18.07 GFLOPS | Progress: (12/20) | 7.76 s
-[Task 5/25] Current/Best: 11.70/ 22.61 GFLOPS | Progress: (16/20) | 9.18 s
-[Task 5/25] Current/Best: 12.00/ 22.61 GFLOPS | Progress: (20/20) | 11.01 s Done.
+[Task 5/25] Current/Best: 9.75/ 10.34 GFLOPS | Progress: (4/20) | 2.58 s
+[Task 5/25] Current/Best: 11.67/ 12.71 GFLOPS | Progress: (8/20) | 4.67 s
+[Task 5/25] Current/Best: 11.77/ 18.07 GFLOPS | Progress: (12/20) | 7.76 s
+[Task 5/25] Current/Best: 11.75/ 22.59 GFLOPS | Progress: (16/20) | 9.16 s
+[Task 5/25] Current/Best: 12.08/ 22.59 GFLOPS | Progress: (20/20) | 11.01 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.21/ 20.71 GFLOPS | Progress: (4/20) | 3.98 s
-[Task 6/25] Current/Best: 19.01/ 20.71 GFLOPS | Progress: (8/20) | 5.76 s
-[Task 6/25] Current/Best: 13.27/ 20.71 GFLOPS | Progress: (12/20) | 7.68 s
-[Task 6/25] Current/Best: 20.00/ 20.71 GFLOPS | Progress: (16/20) | 9.93 s
-[Task 6/25] Current/Best: 3.73/ 20.71 GFLOPS | Progress: (20/20) | 12.48 s Done.
+[Task 6/25] Current/Best: 12.22/ 20.67 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 6/25] Current/Best: 18.99/ 20.67 GFLOPS | Progress: (8/20) | 5.73 s
+[Task 6/25] Current/Best: 13.32/ 20.67 GFLOPS | Progress: (12/20) | 7.65 s
+[Task 6/25] Current/Best: 19.98/ 20.67 GFLOPS | Progress: (16/20) | 9.92 s
+[Task 6/25] Current/Best: 3.65/ 20.67 GFLOPS | Progress: (20/20) | 12.43 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.13/ 12.93 GFLOPS | Progress: (4/20) | 3.64 s
-[Task 7/25] Current/Best: 20.29/ 21.14 GFLOPS | Progress: (8/20) | 5.16 s
-[Task 7/25] Current/Best: 15.64/ 21.14 GFLOPS | Progress: (12/20) | 7.04 s
-[Task 7/25] Current/Best: 12.25/ 21.14 GFLOPS | Progress: (16/20) | 9.08 s
-[Task 7/25] Current/Best: 6.32/ 21.72 GFLOPS | Progress: (20/20) | 11.54 s Done.
+[Task 7/25] Current/Best: 11.21/ 12.97 GFLOPS | Progress: (4/20) | 3.52 s
+[Task 7/25] Current/Best: 20.32/ 21.10 GFLOPS | Progress: (8/20) | 5.03 s
+[Task 7/25] Current/Best: 16.08/ 21.10 GFLOPS | Progress: (12/20) | 6.92 s
+[Task 7/25] Current/Best: 12.27/ 21.10 GFLOPS | Progress: (16/20) | 8.96 s
+[Task 7/25] Current/Best: 6.35/ 21.83 GFLOPS | Progress: (20/20) | 11.44 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.85/ 13.97 GFLOPS | Progress: (4/20) | 2.94 s
-[Task 8/25] Current/Best: 9.35/ 13.97 GFLOPS | Progress: (8/20) | 7.62 s
-[Task 8/25] Current/Best: 12.88/ 13.97 GFLOPS | Progress: (12/20) | 13.77 s
-[Task 8/25] Current/Best: 19.04/ 19.04 GFLOPS | Progress: (16/20) | 15.89 s
-[Task 8/25] Current/Best: 18.70/ 19.04 GFLOPS | Progress: (20/20) | 22.44 s Done.
+[Task 8/25] Current/Best: 9.81/ 14.09 GFLOPS | Progress: (4/20) | 2.90 s
+[Task 8/25] Current/Best: 9.20/ 14.09 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 8/25] Current/Best: 12.35/ 14.09 GFLOPS | Progress: (12/20) | 13.67 s
+[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 15.79 s
+[Task 8/25] Current/Best: 19.84/ 19.84 GFLOPS | Progress: (20/20) | 22.22 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.24/ 15.79 GFLOPS | Progress: (4/20) | 11.97 s
-[Task 9/25] Current/Best: 23.51/ 23.51 GFLOPS | Progress: (8/20) | 13.76 s
-[Task 9/25] Current/Best: 8.24/ 23.51 GFLOPS | Progress: (12/20) | 16.16 s
-[Task 9/25] Current/Best: 17.97/ 23.51 GFLOPS | Progress: (16/20) | 18.71 s
-[Task 9/25] Current/Best: 9.15/ 23.51 GFLOPS | Progress: (20/20) | 26.40 s
+[Task 9/25] Current/Best: 14.31/ 15.75 GFLOPS | Progress: (4/20) | 11.93 s
+[Task 9/25] Current/Best: 23.45/ 23.45 GFLOPS | Progress: (8/20) | 13.73 s
+[Task 9/25] Current/Best: 8.25/ 23.45 GFLOPS | Progress: (12/20) | 16.04 s
+[Task 9/25] Current/Best: 17.96/ 23.45 GFLOPS | Progress: (16/20) | 18.57 s
+[Task 9/25] Current/Best: 9.21/ 23.45 GFLOPS | Progress: (20/20) | 26.18 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.63 s
-[Task 10/25] Current/Best: 15.51/ 18.23 GFLOPS | Progress: (8/20) | 4.23 s
-[Task 10/25] Current/Best: 12.56/ 18.96 GFLOPS | Progress: (12/20) | 5.76 s
-[Task 10/25] Current/Best: 19.10/ 20.42 GFLOPS | Progress: (16/20) | 6.87 s
-[Task 10/25] Current/Best: 8.94/ 20.42 GFLOPS | Progress: (20/20) | 8.43 s Done.
+[Task 10/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/20) | 2.53 s
+[Task 10/25] Current/Best: 15.54/ 18.26 GFLOPS | Progress: (8/20) | 4.10 s
+[Task 10/25] Current/Best: 12.77/ 18.88 GFLOPS | Progress: (12/20) | 5.62 s
+[Task 10/25] Current/Best: 18.80/ 20.37 GFLOPS | Progress: (16/20) | 6.71 s
+[Task 10/25] Current/Best: 8.87/ 20.37 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: 12.20/ 18.11 GFLOPS | Progress: (4/20) | 3.33 s
-[Task 11/25] Current/Best: 16.70/ 18.11 GFLOPS | Progress: (8/20) | 6.05 s
-[Task 11/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (12/20) | 8.11 s
-[Task 11/25] Current/Best: 13.36/ 20.91 GFLOPS | Progress: (16/20) | 10.89 s
-[Task 11/25] Current/Best: 19.37/ 21.61 GFLOPS | Progress: (20/20) | 12.94 s Done.
+[Task 11/25] Current/Best: 12.30/ 18.30 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 11/25] Current/Best: 16.80/ 18.30 GFLOPS | Progress: (8/20) | 5.99 s
+[Task 11/25] Current/Best: 16.58/ 18.30 GFLOPS | Progress: (12/20) | 8.06 s
+[Task 11/25] Current/Best: 13.63/ 20.77 GFLOPS | Progress: (16/20) | 10.75 s
+[Task 11/25] Current/Best: 19.47/ 21.68 GFLOPS | Progress: (20/20) | 12.78 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.78/ 18.03 GFLOPS | Progress: (4/20) | 5.38 s
-[Task 12/25] Current/Best: 5.21/ 18.03 GFLOPS | Progress: (8/20) | 9.10 s
-[Task 12/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (12/20) | 11.10 s
-[Task 12/25] Current/Best: 15.18/ 19.15 GFLOPS | Progress: (16/20) | 13.88 s
-[Task 12/25] Current/Best: 15.17/ 19.15 GFLOPS | Progress: (20/20) | 15.78 s Done.
+[Task 12/25] Current/Best: 7.84/ 18.15 GFLOPS | Progress: (4/20) | 5.34 s
+[Task 12/25] Current/Best: 5.23/ 18.15 GFLOPS | Progress: (8/20) | 8.99 s
+[Task 12/25] Current/Best: 18.88/ 18.96 GFLOPS | Progress: (12/20) | 10.97 s
+[Task 12/25] Current/Best: 15.38/ 18.96 GFLOPS | Progress: (16/20) | 13.70 s
+[Task 12/25] Current/Best: 15.20/ 18.96 GFLOPS | Progress: (20/20) | 15.62 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.76/ 17.33 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 13/25] Current/Best: 15.49/ 20.79 GFLOPS | Progress: (8/20) | 6.15 s
-[Task 13/25] Current/Best: 19.60/ 21.74 GFLOPS | Progress: (12/20) | 9.07 s
-[Task 13/25] Current/Best: 12.30/ 21.74 GFLOPS | Progress: (16/20) | 12.43 s
-[Task 13/25] Current/Best: 18.44/ 21.74 GFLOPS | Progress: (20/20) | 14.73 s Done.
+[Task 13/25] Current/Best: 8.77/ 17.30 GFLOPS | Progress: (4/20) | 3.66 s
+[Task 13/25] Current/Best: 15.58/ 20.92 GFLOPS | Progress: (8/20) | 6.11 s
+[Task 13/25] Current/Best: 19.67/ 21.32 GFLOPS | Progress: (12/20) | 8.93 s
+[Task 13/25] Current/Best: 12.32/ 21.32 GFLOPS | Progress: (16/20) | 12.33 s
+[Task 13/25] Current/Best: 17.95/ 21.32 GFLOPS | Progress: (20/20) | 14.66 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (4/20) | 3.40 s
-[Task 14/25] Current/Best: 6.08/ 13.64 GFLOPS | Progress: (8/20) | 5.57 s
-[Task 14/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (12/20) | 8.12 s
-[Task 14/25] Current/Best: 16.42/ 20.20 GFLOPS | Progress: (16/20) | 9.80 s Done.
+[Task 14/25] Current/Best: 12.92/ 13.00 GFLOPS | Progress: (4/20) | 3.25 s
+[Task 14/25] Current/Best: 6.09/ 13.28 GFLOPS | Progress: (8/20) | 5.42 s
+[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 7.93 s
+[Task 14/25] Current/Best: 16.28/ 20.32 GFLOPS | Progress: (16/20) | 9.58 s Done.
-[Task 14/25] Current/Best: 17.06/ 20.20 GFLOPS | Progress: (20/20) | 11.57 s
+[Task 14/25] Current/Best: 17.05/ 20.32 GFLOPS | Progress: (20/20) | 11.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.18/ 17.64 GFLOPS | Progress: (4/20) | 2.74 s
-[Task 15/25] Current/Best: 14.36/ 18.03 GFLOPS | Progress: (8/20) | 4.08 s
-[Task 15/25] Current/Best: 10.39/ 22.30 GFLOPS | Progress: (12/20) | 6.14 s
-[Task 15/25] Current/Best: 20.36/ 22.30 GFLOPS | Progress: (16/20) | 9.49 s
-[Task 15/25] Current/Best: 9.69/ 22.30 GFLOPS | Progress: (20/20) | 10.51 s
+[Task 15/25] Current/Best: 16.19/ 17.68 GFLOPS | Progress: (4/20) | 2.72 s
+[Task 15/25] Current/Best: 13.92/ 18.09 GFLOPS | Progress: (8/20) | 4.07 s
+[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.18 s
+[Task 15/25] Current/Best: 20.25/ 22.28 GFLOPS | Progress: (16/20) | 9.16 s
+[Task 15/25] Current/Best: 9.71/ 22.28 GFLOPS | Progress: (20/20) | 10.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 16/25] Current/Best: 3.02/ 20.44 GFLOPS | Progress: (8/20) | 4.57 s
-[Task 16/25] Current/Best: 19.46/ 20.44 GFLOPS | Progress: (12/20) | 5.77 s
-[Task 16/25] Current/Best: 17.83/ 20.44 GFLOPS | Progress: (16/20) | 7.14 s
-[Task 16/25] Current/Best: 10.03/ 20.44 GFLOPS | Progress: (20/20) | 9.19 s Done.
+[Task 16/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/20) | 3.01 s
+[Task 16/25] Current/Best: 3.04/ 20.66 GFLOPS | Progress: (8/20) | 4.65 s
+[Task 16/25] Current/Best: 19.33/ 20.66 GFLOPS | Progress: (12/20) | 5.87 s
+[Task 16/25] Current/Best: 17.57/ 20.66 GFLOPS | Progress: (16/20) | 7.22 s
+[Task 16/25] Current/Best: 9.97/ 22.44 GFLOPS | Progress: (20/20) | 9.24 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.79/ 18.16 GFLOPS | Progress: (4/20) | 4.73 s
-[Task 17/25] Current/Best: 12.64/ 23.33 GFLOPS | Progress: (8/20) | 7.60 s
-[Task 17/25] Current/Best: 18.77/ 23.33 GFLOPS | Progress: (12/20) | 9.65 s
-[Task 17/25] Current/Best: 16.48/ 23.33 GFLOPS | Progress: (16/20) | 11.78 s
-[Task 17/25] Current/Best: 10.02/ 23.33 GFLOPS | Progress: (20/20) | 13.90 s Done.
+[Task 17/25] Current/Best: 13.54/ 18.20 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 17/25] Current/Best: 13.00/ 23.42 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 17/25] Current/Best: 17.64/ 23.42 GFLOPS | Progress: (12/20) | 9.54 s
+[Task 17/25] Current/Best: 16.43/ 23.42 GFLOPS | Progress: (16/20) | 11.66 s
+[Task 17/25] Current/Best: 10.04/ 23.42 GFLOPS | Progress: (20/20) | 13.77 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.27/ 17.01 GFLOPS | Progress: (4/20) | 3.71 s
-[Task 18/25] Current/Best: 10.58/ 19.04 GFLOPS | Progress: (8/20) | 7.12 s
-[Task 18/25] Current/Best: 18.85/ 19.04 GFLOPS | Progress: (12/20) | 9.03 s
-[Task 18/25] Current/Best: 10.06/ 19.04 GFLOPS | Progress: (16/20) | 12.62 s
-[Task 18/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (20/20) | 14.12 s Done.
+[Task 18/25] Current/Best: 10.91/ 17.89 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 18/25] Current/Best: 10.54/ 19.77 GFLOPS | Progress: (8/20) | 7.07 s
+[Task 18/25] Current/Best: 19.53/ 19.77 GFLOPS | Progress: (12/20) | 8.97 s
+[Task 18/25] Current/Best: 10.05/ 19.77 GFLOPS | Progress: (16/20) | 12.48 s
+[Task 18/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (20/20) | 13.99 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.13/ 20.35 GFLOPS | Progress: (4/20) | 6.05 s
-[Task 19/25] Current/Best: 2.69/ 20.35 GFLOPS | Progress: (8/20) | 9.33 s
-[Task 19/25] Current/Best: 19.30/ 21.21 GFLOPS | Progress: (12/20) | 12.17 s
-[Task 19/25] Current/Best: 15.35/ 21.21 GFLOPS | Progress: (16/20) | 14.99 s
-[Task 19/25] Current/Best: 2.70/ 22.59 GFLOPS | Progress: (20/20) | 17.82 s Done.
+[Task 19/25] Current/Best: 7.16/ 20.55 GFLOPS | Progress: (4/20) | 5.97 s
+[Task 19/25] Current/Best: 2.69/ 20.55 GFLOPS | Progress: (8/20) | 9.21 s
+[Task 19/25] Current/Best: 20.13/ 21.84 GFLOPS | Progress: (12/20) | 11.99 s
+[Task 19/25] Current/Best: 14.46/ 22.07 GFLOPS | Progress: (16/20) | 14.88 s
+[Task 19/25] Current/Best: 2.70/ 23.24 GFLOPS | Progress: (20/20) | 17.68 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.75/ 15.28 GFLOPS | Progress: (4/20) | 3.38 s Done.
+[Task 20/25] Current/Best: 9.32/ 15.22 GFLOPS | Progress: (4/20) | 3.29 s Done.
Done.
-[Task 20/25] Current/Best: 9.87/ 15.28 GFLOPS | Progress: (8/20) | 6.80 s
-[Task 20/25] Current/Best: 2.33/ 16.68 GFLOPS | Progress: (12/20) | 10.73 s
-[Task 20/25] Current/Best: 12.46/ 16.68 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 20/25] Current/Best: 13.25/ 22.05 GFLOPS | Progress: (20/20) | 16.61 s
+[Task 20/25] Current/Best: 9.69/ 15.22 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 20/25] Current/Best: 2.33/ 16.70 GFLOPS | Progress: (12/20) | 10.62 s
+[Task 20/25] Current/Best: 11.75/ 16.70 GFLOPS | Progress: (16/20) | 14.15 s
+[Task 20/25] Current/Best: 13.54/ 22.33 GFLOPS | Progress: (20/20) | 16.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.41/ 17.71 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 21/25] Current/Best: 14.60/ 17.71 GFLOPS | Progress: (8/20) | 4.80 s
-[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.97 s
-[Task 21/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (16/20) | 10.41 s
-[Task 21/25] Current/Best: 4.44/ 17.91 GFLOPS | Progress: (20/20) | 17.49 s
+[Task 21/25] Current/Best: 6.42/ 17.71 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 21/25] Current/Best: 14.66/ 17.71 GFLOPS | Progress: (8/20) | 4.77 s
+[Task 21/25] Current/Best: 1.61/ 17.71 GFLOPS | Progress: (12/20) | 6.92 s
+[Task 21/25] Current/Best: 17.89/ 17.89 GFLOPS | Progress: (16/20) | 10.34 s
+[Task 21/25] Current/Best: 4.47/ 17.89 GFLOPS | Progress: (20/20) | 17.34 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.80 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 22/25] Current/Best: 8.78/ 21.92 GFLOPS | Progress: (8/20) | 4.69 s
-[Task 22/25] Current/Best: 19.16/ 21.92 GFLOPS | Progress: (12/20) | 7.01 s
-[Task 22/25] Current/Best: 15.36/ 21.92 GFLOPS | Progress: (16/20) | 9.10 s
-[Task 22/25] Current/Best: 13.96/ 21.92 GFLOPS | Progress: (20/20) | 10.76 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.93 GFLOPS | Progress: (4/20) | 2.67 s
+[Task 22/25] Current/Best: 8.58/ 22.15 GFLOPS | Progress: (8/20) | 4.57 s
+[Task 22/25] Current/Best: 20.08/ 22.15 GFLOPS | Progress: (12/20) | 6.85 s
+[Task 22/25] Current/Best: 15.42/ 22.15 GFLOPS | Progress: (16/20) | 8.88 s
+[Task 22/25] Current/Best: 13.99/ 22.15 GFLOPS | Progress: (20/20) | 10.59 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.45/ 20.47 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 23/25] Current/Best: 15.82/ 20.47 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 23/25] Current/Best: 20.84/ 21.66 GFLOPS | Progress: (12/20) | 8.46 s
-[Task 23/25] Current/Best: 6.35/ 21.66 GFLOPS | Progress: (16/20) | 15.57 s
-[Task 23/25] Current/Best: 7.78/ 21.66 GFLOPS | Progress: (20/20) | 19.76 s Done.
+[Task 23/25] Current/Best: 17.77/ 20.90 GFLOPS | Progress: (4/20) | 3.26 s
+[Task 23/25] Current/Best: 14.57/ 20.90 GFLOPS | Progress: (8/20) | 6.51 s
+[Task 23/25] Current/Best: 21.04/ 21.86 GFLOPS | Progress: (12/20) | 8.28 s
+[Task 23/25] Current/Best: 6.36/ 21.86 GFLOPS | Progress: (16/20) | 15.23 s
+[Task 23/25] Current/Best: 7.88/ 21.86 GFLOPS | Progress: (20/20) | 19.38 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.83 s
-[Task 24/25] Current/Best: 1.92/ 8.40 GFLOPS | Progress: (8/20) | 22.87 s
-[Task 24/25] Current/Best: 4.36/ 8.40 GFLOPS | Progress: (12/20) | 34.42 s Done.
+[Task 24/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (4/20) | 11.80 s
+[Task 24/25] Current/Best: 2.16/ 8.48 GFLOPS | Progress: (8/20) | 22.81 s
+[Task 24/25] Current/Best: 4.34/ 8.48 GFLOPS | Progress: (12/20) | 34.34 s Done.
-[Task 24/25] Current/Best: 6.24/ 8.59 GFLOPS | Progress: (16/20) | 39.74 s
-[Task 24/25] Current/Best: 3.37/ 8.93 GFLOPS | Progress: (20/20) | 45.66 s Done.
+[Task 24/25] Current/Best: 6.19/ 8.76 GFLOPS | Progress: (16/20) | 39.63 s
+[Task 24/25] Current/Best: 3.03/ 8.76 GFLOPS | Progress: (20/20) | 45.50 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.76 GFLOPS | Progress: (4/20) | 11.60 s
-[Task 25/25] Current/Best: 5.86/ 8.34 GFLOPS | Progress: (8/20) | 22.85 s
-[Task 25/25] Current/Best: 6.02/ 8.34 GFLOPS | Progress: (12/20) | 34.29 s
-[Task 25/25] Current/Best: 5.88/ 8.82 GFLOPS | Progress: (16/20) | 36.14 s
-[Task 25/25] Current/Best: 2.86/ 9.15 GFLOPS | Progress: (20/20) | 46.79 s
+[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.58 s
+[Task 25/25] Current/Best: 6.20/ 8.23 GFLOPS | Progress: (8/20) | 22.86 s
+[Task 25/25] Current/Best: 6.08/ 8.23 GFLOPS | Progress: (12/20) | 34.14 s
+[Task 25/25] Current/Best: 5.85/ 8.93 GFLOPS | Progress: (16/20) | 35.88 s
+[Task 25/25] Current/Best: 2.88/ 8.99 GFLOPS | Progress: (20/20) | 46.55 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ 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': 415.21851686999526, 'median': 415.0496100999817, 'std': 0.7492938069752674}
-unoptimized: {'mean': 493.1972569200025, 'median': 492.7358948500114, 'std': 1.136266803649717}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 407.42993023999816, 'median': 407.5165550999941, 'std': 0.7069837393560074}
+unoptimized: {'mean': 491.3749680500017, 'median': 491.27970339999933, 'std': 0.8558464573886108}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ 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 18.273 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 24.658 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 0c39d9b01..6670056fe 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ 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>1.307e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.248e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 692d2b766..06bfe8eb6 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ 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, 0x1a66d2d0)), stage(b, placeholder(b, 0x207619c0)), 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, 0xb1d7ad0)), stage(b, placeholder(b, 0x2457ef80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 522282f47..398095218 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<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>13:18.225</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:31.322</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,43 +336,43 @@
</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>10:18.273</p></td>
+<td><p>10:24.658</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:02.894</p></td>
+<td><p>01:09.745</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:00.751</p></td>
+<td><p>01:00.372</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>00:31.163</p></td>
+<td><p>00:30.487</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>00:23.789</p></td>
+<td><p>00:23.975</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>00:00.692</p></td>
+<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>00:01.244</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>00:00.514</p></td>
+<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>00:00.694</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>00:00.142</p></td>
+<td><p>00:00.139</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>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index ec1cf0ec6..544a6ff9b 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,7 +542,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000008
</pre></div>
</div>
@@ -594,7 +594,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallel: 0.000006
+parallel: 0.000007
</pre></div>
</div>
</div>
@@ -668,10 +668,10 @@ 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 7.79289000092831e-06 1.0
- naive 7.652799999999999e-06 0.9820233570714302
-parallel 6.0388e-06 0.7749114897400889
- vector 2.46657e-05 3.16515439035605
+ numpy 7.188160000168864e-06 1.0
+ naive 7.6387e-06 1.0626780705800305
+parallel 7.0917e-06 0.9865807104785372
+ vector 2.45589e-05 3.416576703832839
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ 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: 0.018585
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017881
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ 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:267: 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: 3.419016
+none: 3.407148
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ 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:267: 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: 0.292311
+blocking: 0.284340
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ 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:267: 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: 0.327124
+vectorization: 0.322829
@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], []),
@@ -1215,7 +1215,7 @@ 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:267: 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: 0.118134
+loop permutation: 0.115480
@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], []),
@@ -1293,7 +1293,7 @@ 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:267: 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: 0.108763
+array packing: 0.109448
@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], []),
@@ -1369,7 +1369,7 @@ 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:267: 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: 0.110233
+block caching: 0.110238
@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], []),
@@ -1438,7 +1438,7 @@ 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:267: 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: 0.145499
+parallelization: 0.146285
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4190162362 1.0
- blocking 0.29231131489999995 0.08549573757651521
- vectorization 0.3271236663 0.0956777165421055
-loop permutation 0.1181339512 0.0345520298936333
- array packing 0.1087628013 0.03181113916583278
- block caching 0.110232949 0.03224113060150784
- parallelization 0.14549852140000002 0.04255566845792799
+ none 3.4071484422000005 1.0
+ blocking 0.2843397731 0.08345388465563931
+ vectorization 0.3228287596 0.09475042402072421
+loop permutation 0.11548016459999999 0.03389349379959339
+ array packing 0.1094476059 0.0321229344000432
+ block caching 0.11023844509999998 0.032355046153732844
+ parallelization 0.1462853325 0.04293482804803872
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,7 @@ 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 0.751 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.372 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>