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 2023/03/10 12:28:21 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@302cee99482a9afae3b4a2b0b396083d66b70577)
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 6d2f082223 deploying docs (apache/tvm@302cee99482a9afae3b4a2b0b396083d66b70577)
6d2f082223 is described below
commit 6d2f082223a753d6e93c7161a7d8663cf0595361
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Mar 10 12:28:15 2023 +0000
deploying docs (apache/tvm@302cee99482a9afae3b4a2b0b396083d66b70577)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 330018 -> 346533 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24252 -> 24178 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.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_adreno.rst.txt | 2 +-
.../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 | 20 +-
.../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 | 369 ++++-----------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 126 +------
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 332 +++++++++++++++---
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 16 +-
.../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 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 57 ++--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 ++-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 12 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 46 +--
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../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 | 369 ++++-----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 126 +------
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 332 +++++++++++++++---
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 16 +-
.../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/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 ++--
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 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../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 | 124 +++----
.../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 | 4 +-
.../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 | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 271 +++++++--------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 45 ++-
130 files changed, 1596 insertions(+), 1744 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index c4e860d6e8..1612aabc2c 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index b77852b4c4..b25d3cb0c8 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
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 76a7d02cab..6b4fc8bce2 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.953 seconds)
+ **Total running time of the script:** ( 1 minutes 19.316 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 8a9950f340..a75baed493 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 977ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 948ms/step
Keras top-1 id: 285, class name: Egyptian cat
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 f2eb1444b9..48635aafad 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1e231c9e-8342-4f91-a6b7-b3f6ea80cea4 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6b2e4bbc-c6d7-4f8c-b821-f661a6b6ac9d 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 bbbc6218a3..3502590e23 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ 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, 44.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 55.4MB/s]
58%|#####8 | 24.1M/41.5M [00:00<00:00, 61.6MB/s]
78%|#######8 | 32.4M/41.5M [00:00<00:00, 69.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 71.7MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 70.5MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 65.3MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 61.2MB/s]
68%|######7 | 28.2M/41.5M [00:00<00:00, 60.7MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 58.0MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 59.9MB/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 5a8786eae0..262a31fee7 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
32%|###1 | 14.3M/44.7M [00:00<00:00, 149MB/s]
64%|######3 | 28.5M/44.7M [00:00<00:00, 116MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 102MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
19%|#9 | 8.70M/44.7M [00:00<00:00, 91.2MB/s]
53%|#####2 | 23.5M/44.7M [00:00<00:00, 129MB/s]
80%|######## | 35.8M/44.7M [00:00<00:00, 105MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 bf0145ba9f..41cd06715d 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.414 seconds)
+ **Total running time of the script:** ( 1 minutes 23.814 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 a823c4a65c..365967dc91 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
=================
-**06:47.730** total execution time for **how_to_compile_models** files:
+**06:39.311** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:25.414 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:23.814 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:20.953 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:19.316 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:57.711 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:56.669 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.849 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.769 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:33.338 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.224 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.940 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.142 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.719 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.151 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.944 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.755 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.567 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.726 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.715 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 78f1eac739..e9199da06b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2544.2584 2543.6457 2547.1859 2542.8441 1.4623
+ 2544.7430 2544.4574 2548.6983 2542.6062 1.7976
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 27c0a9a689..2ead95209c 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
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3725 16.3763 16.4598 16.2788 0.0573
+ 15.9786 15.9592 16.1951 15.7948 0.1107
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 25e0b8dc36..632d1d8566 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
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
5%|4 | 7.99M/170M [00:00<00:02, 82.5MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 69.7MB/s]
15%|#4 | 25.2M/170M [00:00<00:01, 80.8MB/s]
19%|#9 | 33.1M/170M [00:00<00:01, 72.6MB/s]
24%|##3 | 40.5M/170M [00:00<00:01, 74.1MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 73.9MB/s]
33%|###2 | 56.0M/170M [00:00<00:01, 75.6MB/s]
38%|###7 | 64.0M/170M [00:00<00:01, 73.6MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 72.5MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 71.6MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 68.6MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 70.5MB/s]
61%|######1 | 104M/170M [00:01<00:00, 69.4MB/s]
66%|######6 | 112M/170M [00:01<00:00, 70.5MB/s]
71%|####### | 120M/170M [00:01<00:00, 71.7MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 71.4MB/s]
80%|######## | 136M/170M [00:01<00:00, 72.6MB/s]
85%|########4 | 144M/170M [00:02<00:00, 73.3MB/s]
89%|########9 | 152M/170M [00:02<00:00, 69.4MB/s]
93%|#########3| 159M/170M [00:02<00:00, 69.0MB/s]
97%|#########7| 165M/170M [00:02<00:00, 68.3MB/s]
100%|##########| 170M/170M [00:02<00:00, 70.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 60.2MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 67.3MB/s]
16%|#5 | 26.5M/170M [00:00<00:01, 84.5MB/s]
20%|## | 34.8M/170M [00:00<00:01, 83.8MB/s]
25%|##5 | 42.9M/170M [00:00<00:01, 68.3MB/s]
29%|##9 | 49.9M/170M [00:00<00:02, 57.9MB/s]
33%|###2 | 56.0M/170M [00:00<00:02, 59.3MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 61.5MB/s]
43%|####2 | 72.5M/170M [00:01<00:01, 68.7MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 60.6MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 61.0MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 62.6MB/s]
61%|######1 | 104M/170M [00:01<00:01, 62.5MB/s]
66%|######5 | 112M/170M [00:01<00:01, 59.6MB/s]
71%|####### | 120M/170M [00:01<00:00, 63.3MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 59.1MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 64.4MB/s]
84%|########3 | 142M/170M [00:02<00:00, 68.8MB/s]
88%|########8 | 150M/170M [00:02<00:00, 71.1MB/s]
93%|#########2| 157M/170M [00:02<00:00, 70.5MB/s]
97%|#########6| 164M/170M [00:02<00:00, 67.5MB/s]
100%|##########| 170M/170M [00:02<00:00, 65.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 46.261 seconds)
+ **Total running time of the script:** ( 3 minutes 37.562 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 382701bd2a..5e5ad1fb20 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 67.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 94.8MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 57.2MB/s]
99%|#########9| 13.4M/13.6M [00:00<00:00, 49.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 50.6MB/s]
@@ -409,7 +409,7 @@ 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)
- 90.4631 90.3581 94.5143 90.2003 0.4664
+ 90.4818 90.4405 91.7996 90.0547 0.3539
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.335 seconds)
+ **Total running time of the script:** ( 1 minutes 18.105 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 fa4d0e8473..c748b334f6 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
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.2523 119.0169 122.0774 118.0157 0.7747
+ 122.4297 122.4189 124.4351 121.4632 0.4831
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 30.380 seconds)
+ **Total running time of the script:** ( 2 minutes 31.228 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 b480e2e1d0..7ddf90ae91 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 28.479 seconds)
+ **Total running time of the script:** ( 1 minutes 32.640 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 bb68a7c67c..4d2665542f 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
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4517/132723 [00:00<00:02, 44731.61KB/s]
9%|8 | 11941/132723 [00:00<00:01, 62010.14KB/s]
15%|#5 | 19985/132723 [00:00<00:01, 70401.93KB/s]
21%|##1 | 28094/132723 [00:00<00:01, 74611.59KB/s]
27%|##7 | 36105/132723 [00:00<00:01, 76589.69KB/s]
33%|###3 | 44136/132723 [00:00<00:01, 77847.75KB/s]
39%|###9 | 52253/132723 [00:00<00:01, 78931.22KB/s]
45%|####5 | 60341/132723 [00:00<00:00, 79549.92KB/s]
52%|#####1 | 68444/132723 [00:00<00:00, 80010.67KB/s]
58%|#####7 | 76580/132723 [00:01<00:00, 80417.77KB/s]
64%|######3 | 84685/132723 [00:01<00:00, 80609.31KB/s]
70%|######9 | 92819/132723 [00:01<00:00, 80829.06KB/s]
76%|#######6 | 100961/132723 [00:01<00:00, 81002.93KB/s]
82%|########2 | 109126/132723 [00:01<00:00, 81195.21KB/s]
88%|########8 | 117246/132723 [00:01<00:00, 81133.89KB/s]
94%|########
#4| 125389/132723 [00:01<00:00, 81221.01KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78453.45KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5720/132723 [00:00<00:02, 57183.42KB/s]
11%|# | 14202/132723 [00:00<00:01, 73435.14KB/s]
17%|#7 | 22705/132723 [00:00<00:01, 78721.37KB/s]
24%|##3 | 31281/132723 [00:00<00:01, 81494.03KB/s]
30%|##9 | 39431/132723 [00:00<00:01, 81217.28KB/s]
36%|###6 | 47998/132723 [00:00<00:01, 82724.95KB/s]
43%|####2 | 56567/132723 [00:00<00:00, 83690.62KB/s]
49%|####9 | 65201/132723 [00:00<00:00, 84520.66KB/s]
56%|#####5 | 73809/132723 [00:00<00:00, 85004.95KB/s]
62%|######2 | 82334/132723 [00:01<00:00, 85079.33KB/s]
68%|######8 | 90898/132723 [00:01<00:00, 85244.66KB/s]
75%|#######4 | 99480/132723 [00:01<00:00, 85418.22KB/s]
81%|########1 | 108114/132723 [00:01<00:00, 85694.63KB/s]
88%|########7 | 116704/132723 [00:01<00:00, 85752.47KB/s]
94%|#########4| 125336/132723 [00:01<00:00, 85916.25KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83532.47KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 56.715 seconds)
+ **Total running time of the script:** ( 3 minutes 48.935 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 c406368b6f..71d289d7ed 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
@@ -5,26 +5,26 @@
Computation times
=================
-**15:38.919** total execution time for **how_to_deploy_models** files:
+**15:22.759** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:56.715 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:48.935 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:46.261 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:37.562 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.380 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:31.228 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.479 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.640 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:19.335 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:18.105 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.842 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.817 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:44.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.203 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:29.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.288 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.372 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.975 | 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 bfd341ec68..acf1f8642b 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa236796f-f216-4846-9111-70494937f353 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip790d5b65-7aa6-4013-a8b1-70a8edc6e534 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 b6f132fa6e..14047785f0 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
=================
-**00:56.136** total execution time for **how_to_extend_tvm** files:
+**00:54.717** 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``) | 00:52.139 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.851 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.863 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.762 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.125 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.096 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.009 | 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 |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 7fc5b95057..061e984eeb 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
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 23455us [23455us] (49.20%; 49.20%)
- FoldScaleAxis: 24220us [9us] (50.80%; 50.80%)
- FoldConstant: 24210us [1805us] (50.78%; 99.96%)
- InferType: 22405us [22405us] (47.00%; 92.54%)
+ InferType: 22334us [22334us] (48.81%; 48.81%)
+ FoldScaleAxis: 23420us [8us] (51.19%; 51.19%)
+ FoldConstant: 23412us [1734us] (51.17%; 99.96%)
+ InferType: 21678us [21678us] (47.38%; 92.59%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 22222us [22222us] (48.17%; 48.17%)
- FoldScaleAxis: 23911us [8us] (51.83%; 51.83%)
- FoldConstant: 23903us [1783us] (51.81%; 99.97%)
- InferType: 22120us [22120us] (47.95%; 92.54%)
+ InferType: 21597us [21597us] (48.24%; 48.24%)
+ FoldScaleAxis: 23171us [6us] (51.76%; 51.76%)
+ FoldConstant: 23165us [1707us] (51.75%; 99.98%)
+ InferType: 21458us [21458us] (47.93%; 92.63%)
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 8a8308e9bb..53cc81d1fa 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
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.202400 ms
+ Convolution: 54.153598 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 0e84e8f327..072591540c 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
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.910198 ms
+ conv2d with tensor core: 13.015479 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 5540ba2c58..4a52d6343b 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019480
- Baseline: 3.417026
+ Numpy running time: 0.018795
+ Baseline: 3.260761
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.318271
+ Opt1: 0.301293
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345521
+ Opt2: 0.339000
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120954
+ Opt3: 0.117957
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109566
+ Opt4: 0.109464
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111945
+ Opt5: 0.111570
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146752
+ Opt6: 0.146677
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 292338deb5..f9335c350c 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
=================
-**00:35.482** total execution time for **how_to_optimize_operators** files:
+**00:34.634** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.865 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.936 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.501 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.595 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.102 | 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 1c72088fca..2c19fab74b 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
=================
-**10:11.915** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:49.495** 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``) | 06:06.585 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:58.659 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:43.983 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:43.537 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:07.522 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:44.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.792 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.372 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.949 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.614 | 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 148af8a379..9d8f79922f 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
@@ -244,152 +244,31 @@ cooperative fetching, unrolling and operator fusion.
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.launch_thread("blockIdx.x", 32)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([6272], "float32", "shared")
- kernel_shared = T.allocate([2048], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 56)
- conv2d_nchw_1 = T.Buffer((49,), data=conv2d_nchw, scope="local", align=16)
- conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(4, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 1152
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((6272,), data=pad_temp_shared, scope="shared")
- for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(112):
- cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56
- threadIdx_x_1 = T.launch_thread("threadIdx.x", 56)
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 // 7 + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7 and ry_outer_outer + (threadIdx_x_1 // 7 + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 6272 + cse_var_3 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((2048,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 9]
- kernel_shared_1[threadIdx_x_1 * 8 + 2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 18]
- kernel_shared_1[threadIdx_x_1 * 8 + 3] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 27]
- kernel_shared_1[threadIdx_x_1 * 8 + 4] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 36]
- kernel_shared_1[threadIdx_x_1 * 8 + 5] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 45]
- kernel_shared_1[threadIdx_x_1 * 8 + 6] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 54]
- kernel_shared_1[threadIdx_x_1 * 8 + 7] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 63]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 64) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 449] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 65) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 450] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 66) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 451] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 67) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 452] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 68) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 453] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 69) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 454] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 70) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 455] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 71) % 128 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 896] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32256]
- kernel_shared_1[threadIdx_x_1 * 8 + 897] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32265]
- kernel_shared_1[threadIdx_x_1 * 8 + 898] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32274]
- kernel_shared_1[threadIdx_x_1 * 8 + 899] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32283]
- kernel_shared_1[threadIdx_x_1 * 8 + 900] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32292]
- kernel_shared_1[threadIdx_x_1 * 8 + 901] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32301]
- kernel_shared_1[threadIdx_x_1 * 8 + 902] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32310]
- kernel_shared_1[threadIdx_x_1 * 8 + 903] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32319]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 1344] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 64) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1345] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 65) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1346] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 66) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1347] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 67) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1348] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 68) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1349] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 69) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1350] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 70) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1351] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 71) % 128 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 56):
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1792] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64512]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1793] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64521]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1794] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64530]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1795] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64539]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1796] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64548]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1797] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64557]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1798] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64566]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1799] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64575]
- for rc_outer_inner in range(32):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 133] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 133] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 140] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 140] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 147] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 147] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 161] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 161] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 168] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 168] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 175] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 175] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- for i2_inner in range(7):
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([576], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 392)
+ conv2d_nchw_1 = T.Buffer((2,), data=conv2d_nchw, scope="local", align=8)
+ for ff_outer_inner_init in range(2):
+ conv2d_nchw_1[ff_outer_inner_init] = T.float32(0)
+ for rc_outer_outer in range(128):
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 392) as threadIdx_x_1:
+ if T.likely(threadIdx_x_1 < 324):
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 196 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ kernel_shared_1 = T.Buffer((576,), data=kernel_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(2):
+ threadIdx_x_1 = T.launch_thread("threadIdx.x", 392)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49 + threadIdx_x_1 // 8 < 72):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ kernel_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392 + threadIdx_x_1] = kernel_1[blockIdx_x * 73728 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98 + threadIdx_x_1 // 4) // 9 * 4608 + rc_outer_outer * 36 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32 + threadIdx_x_1) % 36 // 3 * 3 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2 + threadIdx_x_1) % 3]
+ for ry_outer_inner, ff_outer_inner, rc_inner, rx_inner in T.grid(3, 2, 4, 3):
+ conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + rx_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + ff_outer_inner * 36 + rc_inner * 9 + ry_outer_inner * 3 + rx_inner]
+ for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7 + 392] = T.max(conv2d_nchw_1[i2_inner + 7] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 + 8], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
@@ -439,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.389 ms
+ Execution time of this operator: 0.335 ms
@@ -488,32 +367,32 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=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_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=2)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_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=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ 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_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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
- 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=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -534,16 +413,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=8)
+ 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=392)
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=392)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -561,152 +440,36 @@ 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[14];
- __shared__ float pad_temp_shared[6272];
- __shared__ float kernel_shared[2048];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 4; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_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 < 112; ++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 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 6272) + (ax0_ax1_fused_ [...]
- }
- kernel_shared[(((int)threadIdx.x) * 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 9)];
- kernel_shared[((((int)threadIdx.x) * 8) + 2)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 18)];
- kernel_shared[((((int)threadIdx.x) * 8) + 3)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 27)];
- kernel_shared[((((int)threadIdx.x) * 8) + 4)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
- kernel_shared[((((int)threadIdx.x) * 8) + 5)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 45)];
- kernel_shared[((((int)threadIdx.x) * 8) + 6)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 54)];
- kernel_shared[((((int)threadIdx.x) * 8) + 7)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 63)];
- kernel_shared[((((int)threadIdx.x) * 8) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 64) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 449)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 65) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 450)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 66) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 451)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 67) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 452)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 68) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 453)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 69) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 454)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 70) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 455)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 71) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 896)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 8) + 897)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32265)];
- kernel_shared[((((int)threadIdx.x) * 8) + 898)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32274)];
- kernel_shared[((((int)threadIdx.x) * 8) + 899)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32283)];
- kernel_shared[((((int)threadIdx.x) * 8) + 900)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32292)];
- kernel_shared[((((int)threadIdx.x) * 8) + 901)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32301)];
- kernel_shared[((((int)threadIdx.x) * 8) + 902)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32310)];
- kernel_shared[((((int)threadIdx.x) * 8) + 903)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32319)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 64) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1345)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 65) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1346)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 66) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1347)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 67) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1348)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 68) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1349)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 69) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1350)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 70) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1351)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 71) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1792)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64512)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1793)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64521)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1794)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64530)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1795)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64539)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1796)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64548)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1797)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64557)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1798)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64566)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1799)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64575)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 196) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 196) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
+ extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[576];
+ for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
+ conv2d_nchw[ff_outer_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 324) {
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + (((int)threadIdx.x) >> 3)) < 72) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) >> 2)) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + ((int)threadIdx.x)) % 36) / 3) * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3))];
+ }
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ for (int rx_inner = 0; rx_inner < 3; ++rx_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 72) + (ff_outer_inner * 36)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_inner)]));
+ }
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -766,7 +529,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 6.585 seconds)
+ **Total running time of the script:** ( 5 minutes 58.659 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 87aec52c4c..be5bd08c33 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)
- 7.8837 7.8934 7.8969 7.8606 0.0164
+ 7.8926 7.8922 7.8973 7.8883 0.0037
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.523 seconds)
+ **Total running time of the script:** ( 1 minutes 7.522 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 aad5226d79..76f2b4152a 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)
- 771.8443 773.2231 773.2783 769.0315 1.9891
+ 754.7036 754.2461 756.1573 753.7073 1.0512
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 43.983 seconds)
+ **Total running time of the script:** ( 1 minutes 43.537 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 7aee4120c6..7eedab0bf1 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
@@ -389,116 +389,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(2048):
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 128 // 4
+ for i0_outer in T.parallel(128):
compute_1 = T.allocate([32], "float32", "global")
- compute_2 = T.Buffer((32,), data=compute_1)
- compute_2[0] = T.float32(0)
- compute_2[1] = T.float32(0)
- compute_2[2] = T.float32(0)
- compute_2[3] = T.float32(0)
- compute_2[4] = T.float32(0)
- compute_2[5] = T.float32(0)
- compute_2[6] = T.float32(0)
- compute_2[7] = T.float32(0)
- compute_2[8] = T.float32(0)
- compute_2[9] = T.float32(0)
- compute_2[10] = T.float32(0)
- compute_2[11] = T.float32(0)
- compute_2[12] = T.float32(0)
- compute_2[13] = T.float32(0)
- compute_2[14] = T.float32(0)
- compute_2[15] = T.float32(0)
- compute_2[16] = T.float32(0)
- compute_2[17] = T.float32(0)
- compute_2[18] = T.float32(0)
- compute_2[19] = T.float32(0)
- compute_2[20] = T.float32(0)
- compute_2[21] = T.float32(0)
- compute_2[22] = T.float32(0)
- compute_2[23] = T.float32(0)
- compute_2[24] = T.float32(0)
- compute_2[25] = T.float32(0)
- compute_2[26] = T.float32(0)
- compute_2[27] = T.float32(0)
- compute_2[28] = T.float32(0)
- compute_2[29] = T.float32(0)
- compute_2[30] = T.float32(0)
- compute_2[31] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
- placeholder_7 = T.Buffer((32768,), data=placeholder.data)
- placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[0] = compute_2[0] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[1] = compute_2[1] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[2] = compute_2[2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[3] = compute_2[3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[4] = compute_2[4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[5] = compute_2[5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[6] = compute_2[6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[7] = compute_2[7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[8] = compute_2[8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[9] = compute_2[9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[10] = compute_2[10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[11] = compute_2[11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[12] = compute_2[12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[13] = compute_2[13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[14] = compute_2[14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[15] = compute_2[15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[16] = compute_2[16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[17] = compute_2[17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[18] = compute_2[18] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[19] = compute_2[19] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[20] = compute_2[20] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[21] = compute_2[21] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[22] = compute_2[22] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[23] = compute_2[23] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[24] = compute_2[24] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[25] = compute_2[25] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[26] = compute_2[26] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[27] = compute_2[27] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[28] = compute_2[28] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[29] = compute_2[29] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[30] = compute_2[30] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[31] = compute_2[31] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- for i0_inner in range(8):
- cse_var_2: T.int32 = i0_outer_i1_outer_fused // 128 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 128 * 4
+ for i1_outer in range(16):
+ cse_var_1: T.int32 = i0_outer * 512 + i1_outer * 32
+ compute_2 = T.Buffer((32,), data=compute_1)
+ for nb_j_inner in range(2):
+ for j_init in range(16):
+ compute_2[nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, j in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 16):
+ cse_var_2 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_4: T.int32 = nb_j_inner * 16 + j
+ cse_var_3: T.int32 = i1_outer * 2 + nb_j_inner
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_2:cse_var_2 + 4] = T.max(compute_2[i0_inner * 4:i0_inner * 4 + 4] + placeholder_5[cse_var_2:cse_var_2 + 4], T.Broadcast(T.float32(0), 4))
+ compute_3[cse_var_1:cse_var_1 + 32] = T.max(compute_2[0:32] + placeholder_5[cse_var_1:cse_var_1 + 32], T.Broadcast(T.float32(0), 32))
@@ -548,7 +458,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.094 ms
+ Execution time of this operator: 1.927 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 6a4247e0bd..264338eb64 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:43.947** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.419** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.913 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.385 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 bfa4a52f87..7c1e9e089d 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
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4495725
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1415250
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,7 +513,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3190031
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4947620
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -636,7 +636,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5446445
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6863977
No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -759,7 +759,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10409873
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8191978
No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -882,7 +882,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 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', 0), ('unroll_explicit', 1)],None,5966615
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3636310
No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1005,8 +1005,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5969846
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,428879
No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8366442
+ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1128,9 +1146,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1, 128]), ('tile_y', [-1, 7, 1, 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', 0)],None,4968032
- No: 8 GFLOPS: 205.61/205.61 result: MeasureResult(costs=(0.0011259272327586208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4645109176635742, timestamp=1678428272.7521389) [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2206066
- No: 9 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3069985
+ No: 9 GFLOPS: 1.13/1.13 result: MeasureResult(costs=(0.20414002975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.034067392349243, timestamp=1678448430.429522) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7395507
+ No: 10 GFLOPS: 0.00/1.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1252,8 +1270,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187417
- No: 10 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5009849
+ No: 11 GFLOPS: 0.00/1.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1375,9 +1393,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10199138
- No: 11 GFLOPS: 2.36/205.61 result: MeasureResult(costs=(0.097943878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2757134437561035, timestamp=1678428275.2391717) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5934905
- No: 12 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2926766
+ No: 12 GFLOPS: 439.95/439.95 result: MeasureResult(costs=(0.0005261959246231155,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3744254112243652, timestamp=1678448431.1799793) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6204121
+ No: 13 GFLOPS: 11.71/439.95 result: MeasureResult(costs=(0.01977544016666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9113430976867676, timestamp=1678448433.2637806) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3306929
+ No: 14 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1499,8 +1518,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1548188
- No: 13 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3706601
+ No: 15 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1622,29 +1641,255 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6379277
- No: 14 GFLOPS: 58.57/205.61 result: MeasureResult(costs=(0.003952753666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6202030181884766, timestamp=1678428286.3232596) [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1977963
- No: 15 GFLOPS: 44.12/205.61 result: MeasureResult(costs=(0.005246554533333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5721538066864014, timestamp=1678428287.3428786) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,797395
- No: 16 GFLOPS: 0.00/205.61 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
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4006394
+ No: 16 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,437413
+ No: 17 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1829314
- No: 17 GFLOPS: 21.13/205.61 result: MeasureResult(costs=(0.010954393699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.659226655960083, timestamp=1678428290.7535312) [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,99611
- No: 18 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1506156
+ No: 18 GFLOPS: 63.28/439.95 result: MeasureResult(costs=(0.0036581668571428576,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.190415859222412, timestamp=1678448434.683022) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5817431
+ No: 19 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1766,9 +2011,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6173079
- No: 19 GFLOPS: 2.30/205.61 result: MeasureResult(costs=(0.10057411949999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.698042631149292, timestamp=1678428292.497313) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8267700
- No: 20 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5989628
+ No: 20 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1890,7 +2134,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1524872
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9599607
@@ -1945,9 +2189,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2206066
+ [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6204121
Finish loading 20 records
- Time cost of this operator: 0.001298
+ Time cost of this operator: 0.000954
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 5df8638add..f585bdb538 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
@@ -360,10 +360,10 @@ 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 313.8 98.736 (1, 2, 10, 10, 3) 2 1 [313.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.965 (1, 6, 10, 10) 1 1 [3.066]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.3 (1, 1, 10, 10, 3) 1 1 [0.952]
- Total_time - 317.818 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.8 98.731 (1, 2, 10, 10, 3) 2 1 [315.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.971 (1, 6, 10, 10) 1 1 [3.106]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.298 (1, 1, 10, 10, 3) 1 1 [0.953]
+ Total_time - 319.86 - - - - -
@@ -428,10 +428,10 @@ 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 104.1 97.518 (1, 6, 10, 10, 1) 2 1 [104.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 1.678 (1, 6, 10, 10) 1 1 [1.791]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.859 0.804 (1, 3, 10, 10, 1) 1 1 [0.859]
- Total_time - 106.75 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 137.6 98.104 (1, 6, 10, 10, 1) 2 1 [137.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.284 (1, 6, 10, 10) 1 1 [1.8]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.859 0.613 (1, 3, 10, 10, 1) 1 1 [0.859]
+ Total_time - 140.26 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.917 seconds)
+ **Total running time of the script:** ( 1 minutes 21.347 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 57bb015684..0fec8fcb6d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 35.9MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 205MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.445 seconds)
+ **Total running time of the script:** ( 1 minutes 18.360 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 5dba8b37a0..61e02563b6 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
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpgqqr5530/images/random'
+ '/tmp/tmpt0pz0bwf/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpgqqr5530/images/target contains 8144 images
- /tmp/tmpgqqr5530/images/random contains 5000 images
+ /tmp/tmpt0pz0bwf/images/target contains 8144 images
+ /tmp/tmpt0pz0bwf/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 48s - loss: 0.2011 - accuracy: 0.9298 - val_loss: 0.1062 - val_accuracy: 0.9630 - 48s/epoch - 145ms/step
+ 328/328 - 47s - loss: 0.2256 - accuracy: 0.9233 - val_loss: 0.1240 - val_accuracy: 0.9577 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0984 - accuracy: 0.9643 - val_loss: 0.1690 - val_accuracy: 0.9449 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0982 - accuracy: 0.9631 - val_loss: 0.1112 - val_accuracy: 0.9668 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0622 - accuracy: 0.9763 - val_loss: 0.1043 - val_accuracy: 0.9660 - 43s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0624 - accuracy: 0.9777 - val_loss: 0.1148 - val_accuracy: 0.9645 - 43s/epoch - 130ms/step
- <keras.callbacks.History object at 0x7f8a6d7b6ad0>
+ <keras.callbacks.History object at 0x7f13d07c2b50>
@@ -861,7 +861,7 @@ 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 31.228 seconds)
+ **Total running time of the script:** ( 4 minutes 18.132 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 42e1f8ef68..abf9dc51ac 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
@@ -5,22 +5,22 @@
Computation times
=================
-**07:33.595** total execution time for **how_to_work_with_microtvm** files:
+**07:15.271** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:31.228 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:18.132 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:23.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:21.347 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:20.445 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:18.360 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.511 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.202 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.494 | 0.0 MB |
-+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.230 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
++-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_mlperftiny.py` (``micro_mlperftiny.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index b2728624b0..ff3b53b361 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
=================
-**00:47.150** total execution time for **how_to_work_with_relay** files:
+**00:45.725** 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``) | 00:34.871 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.718 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.645 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.384 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.628 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.618 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index d826b01d74..2118947f6f 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
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f891bf9d9e0>
+ <function my_cuda_math_rule at 0x7f141332d290>
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 2adc1c88ca..fb3789d6cf 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.231** total execution time for **how_to_work_with_schedules** files:
+**00:07.854** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.655 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.401 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.593 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.573 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.578 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.551 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.117 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
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 5c4ccb7206..a18dfaa5ba 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
=================
-**00:32.905** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.661** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.899 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.655 | 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 3e363c7a7e..0cdd038434 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ 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 35.13s!
+ resnet18_v1 inference graph built in 33.70s!
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 f9f942a7bc..0f34b5e299 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/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 23.63s!
+ yolov3-tiny inference graph built in 23.00s!
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 4f6486c2ba..aed6f58702 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
=================
-**01:42.484** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.032** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:52.010 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.483 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.474 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.549 | 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 a8d1daf3ce..9ce78a0a18 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
=================
-**00:03.182** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.163** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.709 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.705 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.474 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.458 | 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 6c68267667..0a0812246a 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
=================
-**00:00.776** total execution time for **topic_vta_tutorials** files:
+**00:00.756** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.392 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.376 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.364 | 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 afb9a71d88..62e0e44c09 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ *E
+
@@ -318,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.062 ms
+ Execution time of this operator: 97.464 ms
@@ -434,7 +441,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.802 seconds)
+ **Total running time of the script:** ( 1 minutes 45.783 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 a17026df43..f7f9cf56b6 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.20/10.20 result: MeasureResult(costs=(0.026328871600000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6988813877105713, timestamp=1678426663.706219) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 2 GFLOPS: 11.93/11.93 result: MeasureResult(costs=(0.022504498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6487886905670166, timestamp=1678426664.3307338) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
- No: 3 GFLOPS: 2.60/11.93 result: MeasureResult(costs=(0.10327460799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8966200351715088, timestamp=1678426667.5236785) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
- No: 4 GFLOPS: 3.05/11.93 result: MeasureResult(costs=(0.0878680908,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6547558307647705, timestamp=1678426670.46842) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
- No: 5 GFLOPS: 10.44/11.93 result: MeasureResult(costs=(0.025708404600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6992964744567871, timestamp=1678426671.3154767) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 6 GFLOPS: 0.50/11.93 result: MeasureResult(costs=(0.5373314396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.858155727386475, timestamp=1678426680.1892262) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 7 GFLOPS: 1.97/11.93 result: MeasureResult(costs=(0.1360990762,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4152307510375977, timestamp=1678426683.9060924) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
- No: 8 GFLOPS: 14.33/14.33 result: MeasureResult(costs=(0.0187316278,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6062562465667725, timestamp=1678426684.4665697) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 9 GFLOPS: 13.72/14.33 result: MeasureResult(costs=(0.019561779,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5515782833099365, timestamp=1678426685.1321933) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 10 GFLOPS: 1.52/14.33 result: MeasureResult(costs=(0.1768868496,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.027825117111206, timestamp=1678426688.2163513) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+ No: 1 GFLOPS: 2.10/2.10 result: MeasureResult(costs=(0.1280552958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.290757417678833, timestamp=1678446816.224587) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 2 GFLOPS: 10.37/10.37 result: MeasureResult(costs=(0.025887476400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.661827802658081, timestamp=1678446816.8975248) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
+ No: 3 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.0213346208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6048679351806641, timestamp=1678446818.7509968) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+ No: 4 GFLOPS: 11.47/12.58 result: MeasureResult(costs=(0.023393145400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6308467388153076, timestamp=1678446820.635989) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+ No: 5 GFLOPS: 2.70/12.58 result: MeasureResult(costs=(0.0992693184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.853567361831665, timestamp=1678446823.9130473) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+ No: 6 GFLOPS: 0.95/12.58 result: MeasureResult(costs=(0.28228105919999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.76443076133728, timestamp=1678446828.6901522) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
+ No: 7 GFLOPS: 11.93/12.58 result: MeasureResult(costs=(0.022503239400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6788883209228516, timestamp=1678446829.3152707) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 8 GFLOPS: 9.16/12.58 result: MeasureResult(costs=(0.0293137744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7261197566986084, timestamp=1678446830.045977) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+ No: 9 GFLOPS: 11.63/12.58 result: MeasureResult(costs=(0.0230815666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.598088264465332, timestamp=1678446830.7595081) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 10 GFLOPS: 3.36/12.58 result: MeasureResult(costs=(0.079912539,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4955024719238281, timestamp=1678446832.2990744) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 2699f61a67..a75449ceb0 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 521.825519730005, 'median': 521.9138121500066, 'std': 3.297140399641487}
+ {'mean': 513.9942594399997, 'median': 513.6630722999996, 'std': 1.3362884486950066}
@@ -545,30 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 13.36/ 17.42 GFLOPS | Progress: (4/20) | 10.26 s
[Task 1/25] Current/Best: 14.26/ 22.17 GFLOPS | Progress: (8/20) | 16.49 s
[Task 1/25] Current/Best: 6.39/ 22.17 GFLOPS | Progress: (12/20) | 20.47 s
[Task 1/25] Current/Best: 10.52/ 22.82 GFLOPS | Progress: (16/20) | 23.27 s
[Task 1/25] Current/Best: 23.53/ 23.53 GFLOPS | Progress: (20/20) | 25.15 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.21/ 16.97 GFLOPS | Progress: (4/20) | 4.43 s
[Task 2/25] Current/Best: 7.11/ 16.97 GFLOPS | Progress: (8/20) | 6.38 s
[Task 2/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (12/20) | 7.80 s
[Task 2/25] Current/Best: 15.12/ 19.06 GFLOPS | Progress: (16/20) | 9.29 s
[Task 2/25] Current/Best: 11.24/ 19.06 GFLOPS | Progress: (20/20) | 11.10 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.98/ 17.96 GFLOPS | Progress: (4/20) | 5.42 s
[Task 3/25] Current/Best: 14.47/ 23.59 GFLOPS | Progress: (8/20) | 7.67 s
[Task 3/25] Current/Best: 11.39/ 23.59 GFLOPS | Progress: (12/20) | 11.27 s
[Task 3/25] Current/Best: 5.78/ 23.59 GFLOPS | Progress: (16/20) | 14.52 s
[Task 3/25] Current/Best: 15.00/ 23.59 GFLOPS | Progress: (20/20) | 17.30 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (4/20) | 5.04 s
[Task 4/25] Current/Best: 6.73/ 21.98 GFLOPS | Progress: (8/20) | 7.42 s
[Task 4/25] Current/Best: 9.06/ 21.98 GFLOPS | Progress: (12/20) | 12.16 s
[Task 4/25] Current/Best: 9.63/ 21.98 GFLOPS | Progress: (16/20) | 18.40 s
[Task 4/25] Current/Best: 8.37/ 21.98 GFLOPS | Progress: (20/20) | 29.56 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.86/ 19.40 GFLOPS | Progress: (4/20) | 5.87 s
[Task 5/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (8/20) | 8.08 s
[Task 5/25] Current/Best: 5.27/ 20.43 GFLOPS | Progress: (12/20) | 10.59 s
[Task 5/25] Current/Best: 8.58/ 20.43 GFLOPS | Progress: (16/20) | 12.75 s
[Task 5/25] Current/Best: 20.19/ 20.43 GFLOPS | Progress: (20/20
) | 15.11 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.03/ 17.52 GFLOPS | Progress: (4/20) | 5.51 s
[Task 6/25] Current/Best: 7.89/ 17.52 GFLOPS | Progress: (8/20) | 9.00 s
[Task 6/25] Current/Best: 14.11/ 18.07 GFLOPS | Progress: (12/20) | 11.37 s
[Task 6/25] Current/Best: 8.93/ 18.07 GFLOPS | Progress: (16/20) | 15.10 s
[Task 6/25] Current/Best: 8.85/ 20.02 GFLOPS | Progress: (20/20) | 18.43 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.53/ 20.70 GFLOPS | Progress: (4/20) | 5.19 s
[Task 7/25] Current/Best: 10.77/ 20.70 GFLOPS | Progress: (8/20) | 7.90 s
[Task 7/25] Current/Best: 1.58/ 20.70 GFLOPS | Progress: (12/20) | 11.96 s
[Task 7/25] Current/Best: 12.73/ 20.70 GFLOPS | Progress: (16/20) | 14.67 s
[Task 7/25] Current/Best: 13.30/ 20.70 GFLOPS | Progress: (20/20) | 16.87 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (4/20) | 6.60 s
[Task 8/25] Current/Best: 12.97/ 15.74 GFLOPS | Progress: (8/20) | 9.85 s
[Task 8/25] Current/Best: 13.52/ 15.74 GFLOPS | Progress: (12/20) | 12.86 s
[Task 8/25] Current/Best: 6.19/ 15.74 GFLOPS | Progress: (16/20) | 15.97 s
[Task 8/25] Current/Best: 11.50/ 15.74 GFLOPS | Progress: (20/20) | 22.36 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (4/20) | 4.49 s
[Task 9/25] Current/Best: 15.96/ 21.85 GFLOPS | Progress: (8/20) | 6.53 s
[Task 9/25] Current/Best: 10.08/ 21.85 GFLOPS | Progress: (12/20) | 8.84 s Done.
-
[Task 9/25] Current/Best: 12.93/ 21.85 GFLOPS | Progress: (16/20) | 10.70 s
[Task 9/25] Current/Best: 13.99/ 21.85 GFLOPS | Progress: (20/20) | 13.21 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.78/ 14.57 GFLOPS | Progress: (4/20) | 4.90 s
[Task 10/25] Current/Best: 14.00/ 14.57 GFLOPS | Progress: (8/20) | 9.67 s
[Task 10/25] Current/Best: 11.79/ 14.57 GFLOPS | Progress: (12/20) | 11.70 s
[Task 10/25] Current/Best: 14.34/ 14.57 GFLOPS | Progress: (16/20) | 14.54 s
[Task 10/25] Current/Best: 13.16/ 14.57 GFLOPS | Progress: (20/20) | 16.98 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.66/ 22.69 GFLOPS | Progress: (4/20) | 4.99 s
[Task 11/25] Current/Best: 15.77/ 22.69 GFLOPS | Progress: (8/20) | 7.15 s
[Task 11/25] Current/Best: 17.95/ 22.69 GFLOPS | Progress: (12/20) | 9.13 s
[Task 11/25] Current/Best: 13.74/ 22.69 GFLOPS | Progress: (16/20) | 11.49 s
[Task 11/25] Current/Best: 15.90/ 22.69 GFLOPS | Progress: (20/20) | 13.76 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.56/ 19.99 GFLOPS | Progress: (4/20) | 5.40 s
[Task 12/25] Current/Best: 7.92/ 19.99 GFLOPS | Progress: (8/20) | 10.28 s
[Task 12/25] Current/Best: 10.10/ 19.99 GFLOPS | Progress: (12/20) | 12.47 s
[Task 12/25] Current/Best: 12.15/ 19.99 GFLOPS | Progress: (16/20) | 15.16 s
[Task 12/25] Current/Best: 11.05/ 19.99 GFLOPS | Progress: (20/20) | 19.22 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (4/20) | 6.19 s
[Task 13/25] Current/Best: 14.33/ 19.00 GFLOPS | Progress: (8/20) | 9.35 s
[Task 13/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (12/20) | 12.52 s
[Task 13/25] Current/Best: 5.12/ 20.83 GFLOPS | Progress: (16/20) | 16.45 s
[Task 13/25] Current/Best: 19.31/ 22.09 GFLOPS | Progress: (20/20) | 18.82 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.13/ 13.13 GFLOPS | Progress: (4/20) | 6.30 s
[Task 14/25] Current/Best: 8.56/ 16.26 GFLOPS | Progress: (8/20) | 12.35 s
[Task 14/25] Current/Best: 8.34/ 16.26 GFLOPS | Progress: (12/20) | 15.93 s
[Task 14/25] Current/Best: 16.31/ 17.95 GFLOPS | Progress: (16/20) | 21.72 s
[Task 14/25] Current/Best: 13.56/ 17.95 GFLOPS | Progress: (20/20) | 24.79 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 14.26/ 20.27 GFLOPS | Progress: (4/20) | 4.64 s
[Task 15/25] Current/Best: 3.19/ 20.27 GFLOPS | Progress: (8/20) | 7.54 s
[Task 15/25] Current/Best: 19.90/ 20.27 GFLOPS | Progress: (12/20) | 10.25 s
[Task 15/25] Current/Best: 4.86/ 20.27 GFLOPS | Progress: (16/20) | 12.94 s Done.
-
[Task 15/25] Current/Best: 18.89/ 20.27 GFLOPS | Progress: (20/20) | 15.85 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 3.08/ 11.52 GFLOPS | Progress: (4/20) | 6.41 s
[Task 16/25] Current/Best: 12.18/ 18.67 GFLOPS | Progress: (8/20) | 7.93 s
[Task 16/25] Current/Best: 10.66/ 22.75 GFLOPS | Progress: (12/20) | 9.59 s
[Task 16/25] Current/Best: 14.94/ 22.75 GFLOPS | Progress: (16/20) | 11.16 s
[Task 16/25] Current/Best: 16.18/ 22.75 GFLOPS | Progress: (20/20) | 12.99 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 19.46 GFLOPS | Progress: (4/20) | 6.65 s
[Task 17/25] Current/Best: 12.86/ 19.46 GFLOPS | Progress: (8/20) | 8.89 s
[Task 17/25] Current/Best: 13.15/ 19.46 GFLOPS | Progress: (12/20) | 11.52 s
[Task 17/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (16/20) | 13.97 s
[Task 17/25] Current/Best: 9.71/ 20.68 GFLOPS | Progress: (20/20) | 16.97 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 9.23/ 15.08 GFLOPS | Progress: (4/20) | 5.64 s
[Task 18/25] Current/Best: 19.16/ 19.16 GFLOPS | Progress: (8/20) | 8.89 s
[Task 18/25] Current/Best: 15.10/ 19.16 GFLOPS | Progress: (12/20) | 11.15 s
[Task 18/25] Current/Best: 7.76/ 19.16 GFLOPS | Progress: (16/20) | 17.23 s
[Task 18/25] Current/Best: 16.92/ 19.16 GFLOPS | Progress: (20/20) | 22.91 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.59/ 11.77 GFLOPS | Progress: (4/20) | 7.90 s
[Task 19/25] Current/Best: 3.08/ 22.86 GFLOPS | Progress: (8/20) | 11.61 s
[Task 19/25] Current/Best: 9.69/ 22.86 GFLOPS | Progress: (12/20) | 15.61 s
[Task 19/25] Current/Best: 10.67/ 22.86 GFLOPS | Progress: (16/20) | 19.14 s
[Task 19/25] Current/Best: 8.75/ 22.86 GFLOPS | Progress: (20/20) | 21.56 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.41/ 18.34 GFLOPS | Progress: (4/20) | 5.97 s
[Task 20/25] Current/Best: 9.69/ 18.34 GFLOPS | Progress: (8/20) | 8.46 s
[Task 20/25] Current/Best: 12.91/ 18.34 GFLOPS | Progress: (12/20) | 11.39 s
[Task 20/25] Current/Best: 14.83/ 18.34 GFLOPS | Progress: (16/20) | 14.31 s
[Task 20/25] Current/Best: 11.21/ 18.34 GFLOPS | Progress: (20/20) | 17.38 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.33/ 18.09 GFLOPS | Progress: (4/20) | 5.58 s Done.
-
[Task 21/25] Current/Best: 8.17/ 18.09 GFLOPS | Progress: (8/20) | 9.20 s
[Task 21/25] Current/Best: 15.60/ 18.09 GFLOPS | Progress: (12/20) | 11.93 s
[Task 21/25] Current/Best: 14.55/ 18.09 GFLOPS | Progress: (16/20) | 14.79 s
[Task 21/25] Current/Best: 18.70/ 18.70 GFLOPS | Progress: (20/20) | 17.63 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.93/ 18.10 GFLOPS | Progress: (4/20) | 5.75 s
[Task 22/25] Current/Best: 9.25/ 18.73 GFLOPS | Progress: (8/20) | 7.62 s
[Task 22/25] Current/Best: 13.30/ 18.73 GFLOPS | Progress: (12/20) | 9.59 s
[Task 22/25] Current/Best: 6.74/ 18.73 GFLOPS | Progress: (16/20) | 11.43 s
[Task 22/25] Current/Best: 5.31/ 18.73 GFLOPS | Progress: (20/20) | 14.93 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (4/20) | 5.21 s
[Task 23/25] Current/Best: 10.33/ 21.85 GFLOPS | Progress: (8/20) | 8.50 s
[Task 23/25] Current/Best: 9.08/ 21.85 GFLOPS | Progress: (12/20) | 12.46 s
[Task 23/25] Current/Best: 3.09/ 22.39 GFLOPS | Progress: (16/20) | 16.58 s
[Task 23/25] Current/Best: 18.00/ 22.39 GFLOPS | Progress: (20/20) | 21.11 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.12/ 6.98 GFLOPS | Progress: (4/20) | 13.82 s
[Task 24/25] Current/Best: 9.22/ 9.22 GFLOPS | Progress: (8/20) | 23.00 s
[Task 24/25] Current/Best: 9.81/ 9.81 GFLOPS | Progress: (12/20) | 33.97 s Done.
-
[Task 24/25] Current/Best: 3.05/ 9.81 GFLOPS | Progress: (16/20) | 46.26 s
[Task 24/25] Current/Best: 3.47/ 9.81 GFLOPS | Progress: (20/20) | 58.89 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.44/ 8.54 GFLOPS | Progress: (4/20) | 9.27 s
[Task 25/25] Current/Best: 8.86/ 8.86 GFLOPS | Progress: (8/20) | 12.79 s
[Task 25/25] Current/Best: 8.54/ 8.86 GFLOPS | Progress: (12/20) | 23.75 s
[Task 25/25] Current/Best: 3.00/ 8.99 GFLOPS | Progress: (16/20) | 34.73 s
[Task 25/25] Current/Best: 1.54/ 8.99 GFLOPS | Progress: (20/20) | 41.82 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 13.50/ 13.50 GFLOPS | Progress: (4/20) | 14.82 s
[Task 1/25] Current/Best: 19.14/ 21.96 GFLOPS | Progress: (8/20) | 18.59 s
[Task 1/25] Current/Best: 21.98/ 21.98 GFLOPS | Progress: (12/20) | 21.27 s
[Task 1/25] Current/Best: 17.72/ 21.98 GFLOPS | Progress: (16/20) | 24.37 s
[Task 1/25] Current/Best: 11.49/ 22.46 GFLOPS | Progress: (20/20) | 27.19 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (4/20) | 4.94 s
[Task 2/25] Current/Best: 9.02/ 21.55 GFLOPS | Progress: (8/20) | 6.70 s
[Task 2/25] Current/Best: 16.59/ 21.55 GFLOPS | Progress: (12/20) | 8.33 s
[Task 2/25] Current/Best: 8.58/ 21.55 GFLOPS | Progress: (16/20) | 10.39 s
[Task 2/25] Current/Best: 13.02/ 21.55 GFLOPS | Progress: (20/20) | 12.22 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.87/ 20.10 GFLOPS | Progress: (4/20) | 4.68 s
[Task 3/25] Current/Best: 6.78/ 20.10 GFLOPS | Progress: (8/20) | 7.21 s
[Task 3/25] Current/Best: 16.18/ 20.10 GFLOPS | Progress: (12/20) | 9.58 s
[Task 3/25] Current/Best: 18.10/ 20.10 GFLOPS | Progress: (16/20) | 12.23 s
[Task 3/25] Current/Best: 11.60/ 20.10 GFLOPS | Progress: (20/20) | 15.24 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.57/ 16.63 GFLOPS | Progress: (4/20) | 10.62 s
[Task 4/25] Current/Best: 17.03/ 17.03 GFLOPS | Progress: (8/20) | 14.14 s
[Task 4/25] Current/Best: 12.13/ 17.03 GFLOPS | Progress: (12/20) | 18.53 s
[Task 4/25] Current/Best: 8.43/ 17.03 GFLOPS | Progress: (16/20) | 23.55 s
[Task 4/25] Current/Best: 15.59/ 20.72 GFLOPS | Progress: (20/20) | 28.25 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 4.35/ 16.33 GFLOPS | Progress: (4/20) | 5.11 s
[Task 5/25] Current/Best: 14.39/ 16.33 GFLOPS | Progress: (8/20) | 7.74 s
[Task 5/25] Current/Best: 15.92/ 17.54 GFLOPS | Progress: (12/20) | 9.59 s
[Task 5/25] Current/Best: 13.70/ 19.13 GFLOPS | Progress: (16/20) | 11.51 s
[Task 5/25] Current/Best: 5.27/ 22.19 GFLOPS | Progress: (20/20) | 13.61 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (4/20) | 5.01 s
[Task 6/25] Current/Best: 15.97/ 22.63 GFLOPS | Progress: (8/20) | 7.84 s
[Task 6/25] Current/Best: 10.69/ 22.63 GFLOPS | Progress: (12/20) | 10.35 s
[Task 6/25] Current/Best: 14.41/ 22.63 GFLOPS | Progress: (16/20) | 14.70 s
[Task 6/25] Current/Best: 11.42/ 22.63 GFLOPS | Progress: (20/20) | 17.86 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.55/ 15.22 GFLOPS | Progress: (4/20) | 5.13 s
[Task 7/25] Current/Best: 12.31/ 18.10 GFLOPS | Progress: (8/20) | 7.33 s
[Task 7/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (12/20) | 9.95 s
[Task 7/25] Current/Best: 5.78/ 20.74 GFLOPS | Progress: (16/20) | 12.19 s
[Task 7/25] Current/Best: 11.28/ 20.74 GFLOPS | Progress: (20/20) | 15.17 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.59/ 15.69 GFLOPS | Progress: (4/20) | 5.04 s
[Task 8/25] Current/Best: 11.00/ 18.29 GFLOPS | Progress: (8/20) | 10.34 s
[Task 8/25] Current/Best: 12.41/ 18.29 GFLOPS | Progress: (12/20) | 14.86 s
[Task 8/25] Current/Best: 14.38/ 21.68 GFLOPS | Progress: (16/20) | 21.06 s
[Task 8/25] Current/Best: 11.42/ 21.68 GFLOPS | Progress: (20/20) | 26.77 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.81/ 13.81 GFLOPS | Progress: (4/20) | 10.88 s
[Task 9/25] Current/Best: 15.06/ 15.13 GFLOPS | Progress: (8/20) | 13.58 s
[Task 9/25] Current/Best: 3.40/ 15.13 GFLOPS | Progress: (12/20) | 19.61 s
[Task 9/25] Current/Best: 7.19/ 20.32 GFLOPS | Progress: (16/20) | 22.49 s
[Task 9/25] Current/Best: 15.25/ 20.32 GFLOPS | Progress: (20/20) | 30.24 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.50/ 15.36 GFLOPS | Progress: (4/20) | 5.19 s
[Task 10/25] Current/Best: 18.83/ 18.83 GFLOPS | Progress: (8/20) | 6.95 s
[Task 10/25] Current/Best: 9.21/ 18.83 GFLOPS | Progress: (12/20) | 9.13 s
[Task 10/25] Current/Best: 9.07/ 20.37 GFLOPS | Progress: (16/20) | 11.34 s
[Task 10/25] Current/Best: 7.25/ 20.37 GFLOPS | Progress: (20/20) | 14.11 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 17.09/ 19.36 GFLOPS | Progress: (4/20) | 5.05 s
[Task 11/25] Current/Best: 3.10/ 19.36 GFLOPS | Progress: (8/20) | 8.12 s
[Task 11/25] Current/Best: 18.97/ 19.36 GFLOPS | Progress: (12/20) | 11.28 s
[Task 11/25] Current/Best: 5.82/ 19.36 GFLOPS | Progress: (16/20) | 14.51 s
[Task 11/25] Current/Best: 16.43/ 19.36 GFLOPS | Progress: (20/20) | 16.84 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.48/ 14.48 GFLOPS | Progress: (4/20) | 9.16 s
[Task 12/25] Current/Best: 9.02/ 15.05 GFLOPS | Progress: (8/20) | 17.76 s
[Task 12/25] Current/Best: 10.84/ 17.23 GFLOPS | Progress: (12/20) | 20.19 s
[Task 12/25] Current/Best: 17.81/ 20.84 GFLOPS | Progress: (16/20) | 22.40 s
[Task 12/25] Current/Best: 21.09/ 21.53 GFLOPS | Progress: (20/20) | 27.31 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.75/ 16.69 GFLOPS | Progress: (4/20) | 6.22 s
[Task 13/25] Current/Best: 21.25/ 22.23 GFLOPS | Progress: (8/20) | 9.45 s
[Task 13/25] Current/Best: 16.87/ 22.23 GFLOPS | Progress: (12/20) | 12.35 s
[Task 13/25] Current/Best: 6.98/ 22.23 GFLOPS | Progress: (16/20) | 14.88 s
[Task 13/25] Current/Best: 16.40/ 22.23 GFLOPS | Progress: (20/20) | 17.42 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 5.07/ 18.99 GFLOPS | Progress: (4/20) | 8.57 s
[Task 14/25] Current/Best: 8.59/ 18.99 GFLOPS | Progress: (8/20) | 12.66 s
[Task 14/25] Current/Best: 12.83/ 18.99 GFLOPS | Progress: (12/20) | 15.49 s
[Task 14/25] Current/Best: 15.10/ 18.99 GFLOPS | Progress: (16/20) | 19.15 s
[Task 14/25] Current/Best: 11.03/ 18.99 GFLOPS | Progress: (20/20) | 21.57 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 15/25] Current/Best: 18.91/ 18.97 GFLOPS | Progress: (4/20) | 5.58 s
[Task 15/25] Current/Best: 6.37/ 18.97 GFLOPS | Progress: (8/20) | 7.44 s
[Task 15/25] Current/Best: 15.92/ 20.11 GFLOPS | Progress: (12/20) | 11.65 s
[Task 15/25] Current/Best: 12.43/ 20.11 GFLOPS | Progress: (16/20) | 13.53 s
[Task 15/25] Current/Best: 12.27/ 24.03 GFLOPS | Progress: (20/20) | 16.79 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.20/ 16.10 GFLOPS | Progress: (4/20) | 4.96 s
[Task 16/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (8/20) | 8.63 s
[Task 16/25] Current/Best: 15.98/ 18.43 GFLOPS | Progress: (12/20) | 11.60 s
[Task 16/25] Current/Best: 15.40/ 18.43 GFLOPS | Progress: (16/20) | 13.28 s
[Task 16/25] Current/Best: 18.61/ 18.61 GFLOPS | Progress: (20/20) | 15.79 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 18.72/ 19.79 GFLOPS | Progress: (4/20) | 5.35 s
[Task 17/25] Current/Best: 15.43/ 19.79 GFLOPS | Progress: (8/20) | 8.02 s
[Task 17/25] Current/Best: 17.99/ 19.79 GFLOPS | Progress: (12/20) | 10.53 s
[Task 17/25] Current/Best: 13.36/ 22.92 GFLOPS | Progress: (16/20) | 13.91 s
[Task 17/25] Current/Best: 4.94/ 22.92 GFLOPS | Progress: (20/20) | 16.66 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.11/ 13.31 GFLOPS | Progress: (4/20) | 5.39 s
[Task 18/25] Current/Best: 11.73/ 13.31 GFLOPS | Progress: (8/20) | 9.04 s
[Task 18/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (12/20) | 11.37 s
[Task 18/25] Current/Best: 17.46/ 18.36 GFLOPS | Progress: (16/20) | 13.44 s
[Task 18/25] Current/Best: 7.50/ 19.58 GFLOPS | Progress: (20/20) | 16.95 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.65/ 18.52 GFLOPS | Progress: (4/20) | 6.02 s
[Task 19/25] Current/Best: 17.34/ 18.52 GFLOPS | Progress: (8/20) | 9.41 s
[Task 19/25] Current/Best: 7.30/ 18.66 GFLOPS | Progress: (12/20) | 14.42 s
[Task 19/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (16/20) | 17.06 s
[Task 19/25] Current/Best: 12.08/ 21.80 GFLOPS | Progress: (20/20) | 20.63 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 6.60/ 19.94 GFLOPS | Progress: (4/20) | 5.21 s
[Task 20/25] Current/Best: 6.17/ 19.94 GFLOPS | Progress: (8/20) | 7.66 s
[Task 20/25] Current/Best: 9.92/ 19.94 GFLOPS | Progress: (12/20) | 9.92 s
[Task 20/25] Current/Best: 11.28/ 19.94 GFLOPS | Progress: (16/20) | 12.35 s
[Task 20/25] Current/Best: 10.73/ 19.94 GFLOPS | Progress: (20/20) | 14.77 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 13.68/ 15.40 GFLOPS | Progress: (4/20) | 5.29 s
[Task 21/25] Current/Best: 4.80/ 18.57 GFLOPS | Progress: (8/20) | 7.69 s Done.
+ Done.
+
[Task 21/25] Current/Best: 20.35/ 20.89 GFLOPS | Progress: (12/20) | 10.65 s
[Task 21/25] Current/Best: 18.04/ 22.03 GFLOPS | Progress: (16/20) | 12.41 s
[Task 21/25] Current/Best: 9.66/ 22.03 GFLOPS | Progress: (20/20) | 14.43 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (4/20) | 6.34 s
[Task 22/25] Current/Best: 8.95/ 19.75 GFLOPS | Progress: (8/20) | 8.40 s
[Task 22/25] Current/Best: 6.53/ 19.75 GFLOPS | Progress: (12/20) | 10.19 s
[Task 22/25] Current/Best: 17.83/ 19.75 GFLOPS | Progress: (16/20) | 12.09 s
[Task 22/25] Current/Best: 18.54/ 19.75 GFLOPS | Progress: (20/20) | 14.80 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 16.21/ 22.92 GFLOPS | Progress: (4/20) | 5.08 s
[Task 23/25] Current/Best: 18.41/ 22.92 GFLOPS | Progress: (8/20) | 7.55 s
[Task 23/25] Current/Best: 22.40/ 23.83 GFLOPS | Progress: (12/20) | 10.19 s
[Task 23/25] Current/Best: 17.32/ 23.83 GFLOPS | Progress: (16/20) | 14.18 s
[Task 23/25] Current/Best: 2.67/ 23.83 GFLOPS | Progress: (20/20) | 20.46 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.79/ 8.46 GFLOPS | Progress: (4/20) | 8.29 s
[Task 24/25] Current/Best: 3.57/ 10.52 GFLOPS | Progress: (8/20) | 19.25 s
[Task 24/25] Current/Best: 8.26/ 10.52 GFLOPS | Progress: (12/20) | 30.21 s
[Task 24/25] Current/Best: 0.54/ 10.52 GFLOPS | Progress: (16/20) | 40.93 s
[Task 24/25] Current/Best: 2.28/ 10.52 GFLOPS | Progress: (20/20) | 53.51 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 25/25] Current/Best: 8.88/ 8.88 GFLOPS | Progress: (4/20) | 11.40 s
[Task 25/25] Current/Best: 4.12/ 8.88 GFLOPS | Progress: (8/20) | 22.34 s
[Task 25/25] Current/Best: 3.02/ 8.88 GFLOPS | Progress: (12/20) | 33.31 s
[Task 25/25] Current/Best: 8.67/ 8.88 GFLOPS | Progress: (16/20) | 44.29 s
[Task 25/25] Current/Best: 8.01/ 8.88 GFLOPS | Progress: (20/20) | 55.22 s
@@ -722,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 414.7175817000016, 'median': 414.696313449997, 'std': 4.941491717033467}
- unoptimized: {'mean': 521.825519730005, 'median': 521.9138121500066, 'std': 3.297140399641487}
+ optimized: {'mean': 422.6275845400028, 'median': 421.9335912000133, 'std': 3.3812746177135073}
+ unoptimized: {'mean': 513.9942594399997, 'median': 513.6630722999996, 'std': 1.3362884486950066}
@@ -746,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 39.114 seconds)
+ **Total running time of the script:** ( 12 minutes 56.615 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 2452f5434f..49fd112529 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.253e-07 secs/op
+ 1.237e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 6f9827f059..662fd1d703 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xfc94d60)), stage(b, placeholder(b, 0x668a470)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.R [...]
+ [stage(a, placeholder(a, 0x23ff03c0)), stage(b, placeholder(b, 0x931f590)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index f0af71b58f..e833cb0f7b 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:12.665** total execution time for **tutorial** files:
+**16:45.426** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:39.114 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:56.615 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.802 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:45.783 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.362 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.964 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.101 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.663 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:31.839 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.877 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.408 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.501 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.859 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.850 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.180 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.172 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4479622d9c..f29decfd98 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,7 +285,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000007
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000027
+ vector: 0.000026
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.462599999144004e-06 1.0
- naive 6.9834e-06 0.9357864552302186
- parallel 8.1259e-06 1.0888832311703802
- vector 2.6817299999999998e-05 3.593559885706868
+ numpy 7.680659998641203e-06 1.0
+ naive 6.644600000000001e-06 0.865107946605566
+ parallel 6.9043999999999995e-06 0.8989331647568656
+ vector 2.5740600000000002e-05 3.351352618727272
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019223
+ Numpy running time: 0.018534
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.403328
+ none: 3.258933
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.310085
+ blocking: 0.291995
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.351194
+ vectorization: 0.336260
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118749
+ loop permutation: 0.118644
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108267
+ array packing: 0.109099
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110415
+ block caching: 0.110921
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145990
+ parallelization: 0.146257
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.403327676999999 1.0
- blocking 0.3100849985 0.0911122959436386
- vectorization 0.3511935568 0.10319122639098147
- loop permutation 0.11874873259999999 0.034891948078498235
- array packing 0.1082669506 0.03181208536917499
- block caching 0.1104151313 0.03244328544859068
- parallelization 0.14599012150000001 0.04289628720931418
+ none 3.2589328215999998 1.0
+ blocking 0.2919952335 0.0895984205518672
+ vectorization 0.3362601711 0.10318106862200072
+ loop permutation 0.1186443246 0.036405882261098775
+ array packing 0.10909883219999998 0.0334768582760896
+ block caching 0.1109206511 0.034035881428676584
+ parallelization 0.1462572883 0.04487889020927832
@@ -1594,11 +1594,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.362 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 4115aec4ba..d6e7f9a4a4 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-422ca2855a74bf0d0d88f1aa66343015f4326ac1
+302cee99482a9afae3b4a2b0b396083d66b70577
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8aa75993e1..41f87719f4 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ 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 20.953 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.316 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_keras.html b/docs/how_to/compile_models/from_keras.html
index 1eec4b4e46..d3bbd06d4b 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -511,7 +511,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 977ms/step
+1/1 [==============================] - 1s 948ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index c7ebf6d024..ddc59a13a9 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<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.zip1e231c9e-8342-4f91-a6b7-b3f6ea80cea4 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.zip6b2e4bbc-c6d7-4f8c-b821-f661a6b6ac9d 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 5b80e953c2..3982be9b91 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,11 +454,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<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, 44.8MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 55.4MB/s]
- 58%|#####8 | 24.1M/41.5M [00:00<00:00, 61.6MB/s]
- 78%|#######8 | 32.4M/41.5M [00:00<00:00, 69.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 71.7MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 70.5MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 65.3MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 61.2MB/s]
+ 68%|######7 | 28.2M/41.5M [00:00<00:00, 60.7MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 58.0MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 59.9MB/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 bb1afa41a2..2657ed0d00 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,10 +437,10 @@ be unstable.</p>
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]
- 32%|###1 | 14.3M/44.7M [00:00<00:00, 149MB/s]
- 64%|######3 | 28.5M/44.7M [00:00<00:00, 116MB/s]
- 90%|########9 | 40.0M/44.7M [00:00<00:00, 102MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/s]
+ 19%|#9 | 8.70M/44.7M [00:00<00:00, 91.2MB/s]
+ 53%|#####2 | 23.5M/44.7M [00:00<00:00, 129MB/s]
+ 80%|######## | 35.8M/44.7M [00:00<00:00, 105MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 425bbdeab0..18a236fc13 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -654,7 +654,7 @@ 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 25.414 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.814 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 831a89302f..50177a2586 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>06:47.730</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:39.311</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>01:25.414</p></td>
+<td><p>01:23.814</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>01:20.953</p></td>
+<td><p>01:19.316</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>00:57.711</p></td>
+<td><p>00:56.669</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>00:38.849</p></td>
+<td><p>00:37.769</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>00:33.338</p></td>
+<td><p>00:32.224</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:31.940</p></td>
+<td><p>00:31.142</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:27.719</p></td>
+<td><p>00:27.151</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>00:26.326</p></td>
+<td><p>00:25.944</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>00:22.755</p></td>
+<td><p>00:22.567</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>00:02.726</p></td>
+<td><p>00:02.715</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 544f941f44..7de5030908 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -925,7 +925,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2544.2584 2543.6457 2547.1859 2542.8441 1.4623
+ 2544.7430 2544.4574 2548.6983 2542.6062 1.7976
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 361ce1721a..5c558fc2ba 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3725 16.3763 16.4598 16.2788 0.0573
+ 15.9786 15.9592 16.1951 15.7948 0.1107
</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 c9412320cf..158fd92d5c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,28 +459,28 @@ be unstable.</p>
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]
- 5%|4 | 7.99M/170M [00:00<00:02, 82.5MB/s]
- 9%|9 | 16.0M/170M [00:00<00:02, 69.7MB/s]
- 15%|#4 | 25.2M/170M [00:00<00:01, 80.8MB/s]
- 19%|#9 | 33.1M/170M [00:00<00:01, 72.6MB/s]
- 24%|##3 | 40.5M/170M [00:00<00:01, 74.1MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:01, 73.9MB/s]
- 33%|###2 | 56.0M/170M [00:00<00:01, 75.6MB/s]
- 38%|###7 | 64.0M/170M [00:00<00:01, 73.6MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 72.5MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 71.6MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 68.6MB/s]
- 57%|#####6 | 96.0M/170M [00:01<00:01, 70.5MB/s]
- 61%|######1 | 104M/170M [00:01<00:00, 69.4MB/s]
- 66%|######6 | 112M/170M [00:01<00:00, 70.5MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 71.7MB/s]
- 75%|#######5 | 128M/170M [00:01<00:00, 71.4MB/s]
- 80%|######## | 136M/170M [00:01<00:00, 72.6MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 73.3MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 69.4MB/s]
- 93%|#########3| 159M/170M [00:02<00:00, 69.0MB/s]
- 97%|#########7| 165M/170M [00:02<00:00, 68.3MB/s]
-100%|##########| 170M/170M [00:02<00:00, 70.8MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 60.2MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 67.3MB/s]
+ 16%|#5 | 26.5M/170M [00:00<00:01, 84.5MB/s]
+ 20%|## | 34.8M/170M [00:00<00:01, 83.8MB/s]
+ 25%|##5 | 42.9M/170M [00:00<00:01, 68.3MB/s]
+ 29%|##9 | 49.9M/170M [00:00<00:02, 57.9MB/s]
+ 33%|###2 | 56.0M/170M [00:00<00:02, 59.3MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 61.5MB/s]
+ 43%|####2 | 72.5M/170M [00:01<00:01, 68.7MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 60.6MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 61.0MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 62.6MB/s]
+ 61%|######1 | 104M/170M [00:01<00:01, 62.5MB/s]
+ 66%|######5 | 112M/170M [00:01<00:01, 59.6MB/s]
+ 71%|####### | 120M/170M [00:01<00:00, 63.3MB/s]
+ 74%|#######4 | 126M/170M [00:02<00:00, 59.1MB/s]
+ 79%|#######9 | 134M/170M [00:02<00:00, 64.4MB/s]
+ 84%|########3 | 142M/170M [00:02<00:00, 68.8MB/s]
+ 88%|########8 | 150M/170M [00:02<00:00, 71.1MB/s]
+ 93%|#########2| 157M/170M [00:02<00:00, 70.5MB/s]
+ 97%|#########6| 164M/170M [00:02<00:00, 67.5MB/s]
+100%|##########| 170M/170M [00:02<00:00, 65.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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=& [...]
@@ -578,7 +578,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 46.261 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 37.562 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 1673214fea..353a70137f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,8 +500,9 @@ training. Other models require a full post training calibration.</p>
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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 67.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 94.8MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 57.2MB/s]
+ 99%|#########9| 13.4M/13.6M [00:00<00:00, 49.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 50.6MB/s]
</pre></div>
</div>
</div>
@@ -592,7 +593,7 @@ 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)
- 90.4631 90.3581 94.5143 90.2003 0.4664
+ 90.4818 90.4405 91.7996 90.0547 0.3539
</pre></div>
</div>
<div class="admonition note">
@@ -631,7 +632,7 @@ 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 19.335 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.105 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 6af2942a90..902ba2212e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ 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)
- 119.2523 119.0169 122.0774 118.0157 0.7747
+ 122.4297 122.4189 124.4351 121.4632 0.4831
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.380 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.228 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 14a0e980c9..eb4269c130 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ 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 28.479 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.640 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 a0de1ed014..663c0425a0 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,23 +468,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|3 | 4517/132723 [00:00<00:02, 44731.61KB/s]
- 9%|8 | 11941/132723 [00:00<00:01, 62010.14KB/s]
- 15%|#5 | 19985/132723 [00:00<00:01, 70401.93KB/s]
- 21%|##1 | 28094/132723 [00:00<00:01, 74611.59KB/s]
- 27%|##7 | 36105/132723 [00:00<00:01, 76589.69KB/s]
- 33%|###3 | 44136/132723 [00:00<00:01, 77847.75KB/s]
- 39%|###9 | 52253/132723 [00:00<00:01, 78931.22KB/s]
- 45%|####5 | 60341/132723 [00:00<00:00, 79549.92KB/s]
- 52%|#####1 | 68444/132723 [00:00<00:00, 80010.67KB/s]
- 58%|#####7 | 76580/132723 [00:01<00:00, 80417.77KB/s]
- 64%|######3 | 84685/132723 [00:01<00:00, 80609.31KB/s]
- 70%|######9 | 92819/132723 [00:01<00:00, 80829.06KB/s]
- 76%|#######6 | 100961/132723 [00:01<00:00, 81002.93KB/s]
- 82%|########2 | 109126/132723 [00:01<00:00, 81195.21KB/s]
- 88%|########8 | 117246/132723 [00:01<00:00, 81133.89KB/s]
- 94%|#########4| 125389/132723 [00:01<00:00, 81221.01KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78453.45KB/s]
+ 4%|4 | 5720/132723 [00:00<00:02, 57183.42KB/s]
+ 11%|# | 14202/132723 [00:00<00:01, 73435.14KB/s]
+ 17%|#7 | 22705/132723 [00:00<00:01, 78721.37KB/s]
+ 24%|##3 | 31281/132723 [00:00<00:01, 81494.03KB/s]
+ 30%|##9 | 39431/132723 [00:00<00:01, 81217.28KB/s]
+ 36%|###6 | 47998/132723 [00:00<00:01, 82724.95KB/s]
+ 43%|####2 | 56567/132723 [00:00<00:00, 83690.62KB/s]
+ 49%|####9 | 65201/132723 [00:00<00:00, 84520.66KB/s]
+ 56%|#####5 | 73809/132723 [00:00<00:00, 85004.95KB/s]
+ 62%|######2 | 82334/132723 [00:01<00:00, 85079.33KB/s]
+ 68%|######8 | 90898/132723 [00:01<00:00, 85244.66KB/s]
+ 75%|#######4 | 99480/132723 [00:01<00:00, 85418.22KB/s]
+ 81%|########1 | 108114/132723 [00:01<00:00, 85694.63KB/s]
+ 88%|########7 | 116704/132723 [00:01<00:00, 85752.47KB/s]
+ 94%|#########4| 125336/132723 [00:01<00:00, 85916.25KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83532.47KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -523,7 +522,7 @@ 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> ( 3 minutes 56.715 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> ( 3 minutes 48.935 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 a8f252d784..a3c879c843 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>15:38.919</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:22.759</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,39 +354,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>03:56.715</p></td>
+<td><p>03:48.935</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:46.261</p></td>
+<td><p>03:37.562</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:30.380</p></td>
+<td><p>02:31.228</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>01:28.479</p></td>
+<td><p>01:32.640</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>01:19.335</p></td>
+<td><p>01:18.105</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.842</p></td>
+<td><p>00:54.817</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:44.415</p></td>
+<td><p>00:43.203</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:29.113</p></td>
+<td><p>00:28.288</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:28.372</p></td>
+<td><p>00:27.975</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
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 793d112f88..839dd03f9e 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ 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.zipa236796f-f216-4846-9111-70494937f353 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.zip790d5b65-7aa6-4013-a8b1-70a8edc6e534 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 c80db3ba13..9257e5b693 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:56.136</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:54.717</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</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>00:52.139</p></td>
+<td><p>00:50.851</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>00:02.863</p></td>
+<td><p>00:02.762</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>00:01.125</p></td>
+<td><p>00:01.096</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>00:00.009</p></td>
+<td><p>00:00.008</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 b7cec0aac6..576ce208b1 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ 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: 23455us [23455us] (49.20%; 49.20%)
-FoldScaleAxis: 24220us [9us] (50.80%; 50.80%)
- FoldConstant: 24210us [1805us] (50.78%; 99.96%)
- InferType: 22405us [22405us] (47.00%; 92.54%)
+InferType: 22334us [22334us] (48.81%; 48.81%)
+FoldScaleAxis: 23420us [8us] (51.19%; 51.19%)
+ FoldConstant: 23412us [1734us] (51.17%; 99.96%)
+ InferType: 21678us [21678us] (47.38%; 92.59%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ 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: 22222us [22222us] (48.17%; 48.17%)
-FoldScaleAxis: 23911us [8us] (51.83%; 51.83%)
- FoldConstant: 23903us [1783us] (51.81%; 99.97%)
- InferType: 22120us [22120us] (47.95%; 92.54%)
+InferType: 21597us [21597us] (48.24%; 48.24%)
+FoldScaleAxis: 23171us [6us] (51.76%; 51.76%)
+ FoldConstant: 23165us [1707us] (51.75%; 99.98%)
+ InferType: 21458us [21458us] (47.93%; 92.63%)
</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 223c60340d..c7f3801084 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.202400 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.153598 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 9e5fb6225f..b44379eed1 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ 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: 6.910198 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.015479 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 2dde3b9b4a..6e81f96406 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ 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: 0.019480
-Baseline: 3.417026
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018795
+Baseline: 3.260761
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ 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: 0.318271
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.301293
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ 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: 0.345521
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339000
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ 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: 0.120954
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117957
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ 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: 0.109566
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109464
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ 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: 0.111945
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111570
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<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: 0.146752
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146677
</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 762a73f80c..ca481ec24b 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:35.482</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.634</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</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>00:32.865</p></td>
+<td><p>00:31.936</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>00:01.501</p></td>
+<td><p>00:01.595</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>00:01.117</p></td>
+<td><p>00:01.102</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 a3d83b67cc..a77f30309d 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>10:11.915</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:49.495</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</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>06:06.585</p></td>
+<td><p>05:58.659</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>01:43.983</p></td>
+<td><p>01:43.537</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>01:08.523</p></td>
+<td><p>01:07.522</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>00:44.353</p></td>
+<td><p>00:31.792</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:14.523</p></td>
+<td><p>00:14.372</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:13.949</p></td>
+<td><p>00:13.614</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 f39a00358c..c1bd8c6828 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
@@ -511,152 +511,31 @@ class Module:
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.launch_thread("blockIdx.x", 32)
- conv2d_nchw = T.allocate([14], "float32", "local")
- pad_temp_shared = T.allocate([6272], "float32", "shared")
- kernel_shared = T.allocate([2048], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 56)
- conv2d_nchw_1 = T.Buffer((49,), data=conv2d_nchw, scope="local", align=16)
- conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[13] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(4, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 1152
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((6272,), data=pad_temp_shared, scope="shared")
- for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(112):
- cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56
- threadIdx_x_1 = T.launch_thread("threadIdx.x", 56)
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 // 7 + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7 and ry_outer_outer + (threadIdx_x_1 // 7 + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 6272 + cse_var_3 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((2048,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 9]
- kernel_shared_1[threadIdx_x_1 * 8 + 2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 18]
- kernel_shared_1[threadIdx_x_1 * 8 + 3] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 27]
- kernel_shared_1[threadIdx_x_1 * 8 + 4] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 36]
- kernel_shared_1[threadIdx_x_1 * 8 + 5] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 45]
- kernel_shared_1[threadIdx_x_1 * 8 + 6] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 54]
- kernel_shared_1[threadIdx_x_1 * 8 + 7] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 63]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 64) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 449] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 65) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 450] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 66) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 451] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 67) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 452] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 68) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 453] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 69) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 454] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 70) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 455] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 56) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 71) % 128 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 896] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32256]
- kernel_shared_1[threadIdx_x_1 * 8 + 897] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32265]
- kernel_shared_1[threadIdx_x_1 * 8 + 898] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32274]
- kernel_shared_1[threadIdx_x_1 * 8 + 899] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32283]
- kernel_shared_1[threadIdx_x_1 * 8 + 900] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32292]
- kernel_shared_1[threadIdx_x_1 * 8 + 901] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32301]
- kernel_shared_1[threadIdx_x_1 * 8 + 902] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32310]
- kernel_shared_1[threadIdx_x_1 * 8 + 903] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 32319]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 * 8 + 1344] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 64) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1345] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 65) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1346] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 66) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1347] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 67) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1348] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 68) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1349] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 69) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1350] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 70) % 128 * 9 + cse_var_1 + rx_outer_outer]
- kernel_shared_1[threadIdx_x_1 * 8 + 1351] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_1 + 168) // 16 * 4608 + cse_var_2 + (threadIdx_x_1 * 8 + 71) % 128 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 56):
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1792] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64512]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1793] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64521]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1794] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64530]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1795] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64539]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1796] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64548]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1797] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64557]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1798] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64566]
- if T.likely(threadIdx_x_1 < 32):
- kernel_shared_1[threadIdx_x_1 * 8 + 1799] = kernel_1[blockIdx_x * 73728 + threadIdx_x_1 // 16 * 4608 + cse_var_2 + threadIdx_x_1 % 16 * 72 + cse_var_1 + rx_outer_outer + 64575]
- for rc_outer_inner in range(32):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1024]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1025]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 133] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 133] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 140] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 2]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 140] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1026]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 147] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 147] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 161] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 161] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 168] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 168] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 175] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 175] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 3]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 128 + rc_outer_inner * 4 + 1027]
- for i2_inner in range(7):
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([324], "float32", "shared")
+ kernel_shared = T.allocate([576], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 392)
+ conv2d_nchw_1 = T.Buffer((2,), data=conv2d_nchw, scope="local", align=8)
+ for ff_outer_inner_init in range(2):
+ conv2d_nchw_1[ff_outer_inner_init] = T.float32(0)
+ for rc_outer_outer in range(128):
+ pad_temp_shared_1 = T.Buffer((324,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 392) as threadIdx_x_1:
+ if T.likely(threadIdx_x_1 < 324):
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 196 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ kernel_shared_1 = T.Buffer((576,), data=kernel_shared, scope="shared")
+ for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(2):
+ threadIdx_x_1 = T.launch_thread("threadIdx.x", 392)
+ if T.likely(ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49 + threadIdx_x_1 // 8 < 72):
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ kernel_shared_1[ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392 + threadIdx_x_1] = kernel_1[blockIdx_x * 73728 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98 + threadIdx_x_1 // 4) // 9 * 4608 + rc_outer_outer * 36 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32 + threadIdx_x_1) % 36 // 3 * 3 + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2 + threadIdx_x_1) % 3]
+ for ry_outer_inner, ff_outer_inner, rc_inner, rx_inner in T.grid(3, 2, 4, 3):
+ conv2d_nchw_1[ff_outer_inner] = conv2d_nchw_1[ff_outer_inner] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + rx_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + ff_outer_inner * 36 + rc_inner * 9 + ry_outer_inner * 3 + rx_inner]
+ for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7 + 392] = T.max(conv2d_nchw_1[i2_inner + 7] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 + 8], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 98 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -690,7 +569,7 @@ class Module:
<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: 0.389 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.335 ms
</pre></div>
</div>
</div>
@@ -720,32 +599,32 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=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_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=2)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+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_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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
-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=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -766,16 +645,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=8)
+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=392)
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=392)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -793,152 +672,36 @@ 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[14];
- __shared__ float pad_temp_shared[6272];
- __shared__ float kernel_shared[2048];
- conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 4; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_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 < 112; ++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 <= (ry_outer_outer + (((((int)threadIdx.x) / 7) + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7))) && ((ry_outer_outer + (((((int)threadIdx.x) / 7) + ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) % 7)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer [...]
- }
- kernel_shared[(((int)threadIdx.x) * 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 9)];
- kernel_shared[((((int)threadIdx.x) * 8) + 2)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 18)];
- kernel_shared[((((int)threadIdx.x) * 8) + 3)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 27)];
- kernel_shared[((((int)threadIdx.x) * 8) + 4)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
- kernel_shared[((((int)threadIdx.x) * 8) + 5)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 45)];
- kernel_shared[((((int)threadIdx.x) * 8) + 6)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 54)];
- kernel_shared[((((int)threadIdx.x) * 8) + 7)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 63)];
- kernel_shared[((((int)threadIdx.x) * 8) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 64) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 449)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 65) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 450)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 66) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 451)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 67) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 452)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 68) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 453)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 69) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 454)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 70) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 455)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 71) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 896)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32256)];
- kernel_shared[((((int)threadIdx.x) * 8) + 897)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32265)];
- kernel_shared[((((int)threadIdx.x) * 8) + 898)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32274)];
- kernel_shared[((((int)threadIdx.x) * 8) + 899)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32283)];
- kernel_shared[((((int)threadIdx.x) * 8) + 900)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32292)];
- kernel_shared[((((int)threadIdx.x) * 8) + 901)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32301)];
- kernel_shared[((((int)threadIdx.x) * 8) + 902)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32310)];
- kernel_shared[((((int)threadIdx.x) * 8) + 903)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 32319)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 64) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1345)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 65) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1346)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 66) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1347)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 67) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1348)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 68) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1349)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 69) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1350)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 70) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[((((int)threadIdx.x) * 8) + 1351)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((((int)threadIdx.x) * 8) + 71) & 127) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1792)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64512)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1793)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64521)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1794)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64530)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1795)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64539)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1796)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64548)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1797)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64557)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1798)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64566)];
- }
- if (((int)threadIdx.x) < 32) {
- kernel_shared[((((int)threadIdx.x) * 8) + 1799)] = kernel[(((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 1152)) + ((((int)threadIdx.x) & 15) * 72)) + (ry_outer_outer * 3)) + rx_outer_outer) + 64575)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 196) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 196) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4))]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1024)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1025)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1026)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 196) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 128) + (rc_outer_inner * 4)) + 1027)]));
+extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[324];
+ __shared__ float kernel_shared[576];
+ for (int ff_outer_inner_init = 0; ff_outer_inner_init < 2; ++ff_outer_inner_init) {
+ conv2d_nchw[ff_outer_inner_init] = 0.000000e+00f;
+ }
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 324) {
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ }
+ for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
+ if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + (((int)threadIdx.x) >> 3)) < 72) {
+ kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 392) + ((int)threadIdx.x))] = kernel[(((((((int)blockIdx.x) * 73728) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 98) + (((int)threadIdx.x) >> 2)) / 9) * 4608)) + (rc_outer_outer * 36)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + ((int)threadIdx.x)) % 36) / 3) * 3)) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3))];
+ }
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ for (int rc_inner = 0; rc_inner < 4; ++rc_inner) {
+ for (int rx_inner = 0; rx_inner < 3; ++rx_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((((rc_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 72) + (ff_outer_inner * 36)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_inner)]));
+ }
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 392)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7)) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -973,7 +736,7 @@ 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> ( 6 minutes 6.585 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 58.659 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 d1105efd6f..736824b55c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ 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)
- 7.8837 7.8934 7.8969 7.8606 0.0164
+ 7.8926 7.8922 7.8973 7.8883 0.0037
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ 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 8.523 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.522 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 4a5c3808b4..0403047bf3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ 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)
- 771.8443 773.2231 773.2783 769.0315 1.9891
+ 754.7036 754.2461 756.1573 753.7073 1.0512
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ 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 43.983 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.537 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 2d35a6e66f..2526883b28 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,116 +637,26 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(2048):
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 128 // 4
+ for i0_outer in T.parallel(128):
compute_1 = T.allocate([32], "float32", "global")
- compute_2 = T.Buffer((32,), data=compute_1)
- compute_2[0] = T.float32(0)
- compute_2[1] = T.float32(0)
- compute_2[2] = T.float32(0)
- compute_2[3] = T.float32(0)
- compute_2[4] = T.float32(0)
- compute_2[5] = T.float32(0)
- compute_2[6] = T.float32(0)
- compute_2[7] = T.float32(0)
- compute_2[8] = T.float32(0)
- compute_2[9] = T.float32(0)
- compute_2[10] = T.float32(0)
- compute_2[11] = T.float32(0)
- compute_2[12] = T.float32(0)
- compute_2[13] = T.float32(0)
- compute_2[14] = T.float32(0)
- compute_2[15] = T.float32(0)
- compute_2[16] = T.float32(0)
- compute_2[17] = T.float32(0)
- compute_2[18] = T.float32(0)
- compute_2[19] = T.float32(0)
- compute_2[20] = T.float32(0)
- compute_2[21] = T.float32(0)
- compute_2[22] = T.float32(0)
- compute_2[23] = T.float32(0)
- compute_2[24] = T.float32(0)
- compute_2[25] = T.float32(0)
- compute_2[26] = T.float32(0)
- compute_2[27] = T.float32(0)
- compute_2[28] = T.float32(0)
- compute_2[29] = T.float32(0)
- compute_2[30] = T.float32(0)
- compute_2[31] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
- placeholder_7 = T.Buffer((32768,), data=placeholder.data)
- placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[0] = compute_2[0] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[1] = compute_2[1] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[2] = compute_2[2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[3] = compute_2[3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[4] = compute_2[4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[5] = compute_2[5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[6] = compute_2[6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[7] = compute_2[7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[8] = compute_2[8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[9] = compute_2[9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[10] = compute_2[10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[11] = compute_2[11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[12] = compute_2[12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[13] = compute_2[13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[14] = compute_2[14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[15] = compute_2[15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[16] = compute_2[16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[17] = compute_2[17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[18] = compute_2[18] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[19] = compute_2[19] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[20] = compute_2[20] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[21] = compute_2[21] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[22] = compute_2[22] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[23] = compute_2[23] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[24] = compute_2[24] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[25] = compute_2[25] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[26] = compute_2[26] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[27] = compute_2[27] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[28] = compute_2[28] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[29] = compute_2[29] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[30] = compute_2[30] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[31] = compute_2[31] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 4 * 4 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 128 * 2048 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- for i0_inner in range(8):
- cse_var_2: T.int32 = i0_outer_i1_outer_fused // 128 * 4096 + i0_inner * 512 + i0_outer_i1_outer_fused % 128 * 4
+ for i1_outer in range(16):
+ cse_var_1: T.int32 = i0_outer * 512 + i1_outer * 32
+ compute_2 = T.Buffer((32,), data=compute_1)
+ for nb_j_inner in range(2):
+ for j_init in range(16):
+ compute_2[nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, j in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 16):
+ cse_var_2 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_4: T.int32 = nb_j_inner * 16 + j
+ cse_var_3: T.int32 = i1_outer * 2 + nb_j_inner
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_2:cse_var_2 + 4] = T.max(compute_2[i0_inner * 4:i0_inner * 4 + 4] + placeholder_5[cse_var_2:cse_var_2 + 4], T.Broadcast(T.float32(0), 4))
+ compute_3[cse_var_1:cse_var_1 + 32] = T.max(compute_2[0:32] + placeholder_5[cse_var_1:cse_var_1 + 32], T.Broadcast(T.float32(0), 32))
</pre></div>
</div>
</div>
@@ -780,7 +690,7 @@ class Module:
<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: 2.094 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.927 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 4ad002c12d..b2d1ed39fb 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.947</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.419</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.913</p></td>
+<td><p>00:44.385</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 58ed94a2a0..769bdca377 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,7 +695,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4495725
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1415250
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -818,7 +818,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3190031
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4947620
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -941,7 +941,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5446445
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6863977
No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1064,7 +1064,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10409873
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8191978
No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1187,7 +1187,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 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', 0), ('unroll_explicit', 1)],None,5966615
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3636310
No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1310,8 +1310,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5969846
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,428879
No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8366442
+No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1433,9 +1451,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 1, 128]), ('tile_y', [-1, 7, 1, 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', 0)],None,4968032
-No: 8 GFLOPS: 205.61/205.61 result: MeasureResult(costs=(0.0011259272327586208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4645109176635742, timestamp=1678428272.7521389) [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2206066
-No: 9 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3069985
+No: 9 GFLOPS: 1.13/1.13 result: MeasureResult(costs=(0.20414002975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.034067392349243, timestamp=1678448430.429522) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7395507
+No: 10 GFLOPS: 0.00/1.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1557,8 +1575,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187417
-No: 10 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5009849
+No: 11 GFLOPS: 0.00/1.13 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1680,9 +1698,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10199138
-No: 11 GFLOPS: 2.36/205.61 result: MeasureResult(costs=(0.097943878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2757134437561035, timestamp=1678428275.2391717) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5934905
-No: 12 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2926766
+No: 12 GFLOPS: 439.95/439.95 result: MeasureResult(costs=(0.0005261959246231155,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3744254112243652, timestamp=1678448431.1799793) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6204121
+No: 13 GFLOPS: 11.71/439.95 result: MeasureResult(costs=(0.01977544016666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9113430976867676, timestamp=1678448433.2637806) [('tile_f', [-1, 2, 2, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3306929
+No: 14 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1804,8 +1823,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1548188
-No: 13 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3706601
+No: 15 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1927,29 +1946,255 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6379277
-No: 14 GFLOPS: 58.57/205.61 result: MeasureResult(costs=(0.003952753666666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6202030181884766, timestamp=1678428286.3232596) [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1977963
-No: 15 GFLOPS: 44.12/205.61 result: MeasureResult(costs=(0.005246554533333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5721538066864014, timestamp=1678428287.3428786) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,797395
-No: 16 GFLOPS: 0.00/205.61 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
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4006394
+No: 16 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,437413
+No: 17 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, 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, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1829314
-No: 17 GFLOPS: 21.13/205.61 result: MeasureResult(costs=(0.010954393699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.659226655960083, timestamp=1678428290.7535312) [('tile_f', [-1, 2, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,99611
-No: 18 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1506156
+No: 18 GFLOPS: 63.28/439.95 result: MeasureResult(costs=(0.0036581668571428576,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.190415859222412, timestamp=1678448434.683022) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5817431
+No: 19 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2071,9 +2316,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6173079
-No: 19 GFLOPS: 2.30/205.61 result: MeasureResult(costs=(0.10057411949999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.698042631149292, timestamp=1678428292.497313) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8267700
-No: 20 GFLOPS: 0.00/205.61 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5989628
+No: 20 GFLOPS: 0.00/439.95 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2195,7 +2439,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1524872
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9599607
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2234,9 +2478,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2206066
+[('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6204121
Finish loading 20 records
-Time cost of this operator: 0.001298
+Time cost of this operator: 0.000954
</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 02ef3512df..0f9976f67b 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -648,10 +648,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.8 98.736 (1, 2, 10, 10, 3) 2 1 [313.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.965 (1, 6, 10, 10) 1 1 [3.066]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.3 (1, 1, 10, 10, 3) 1 1 [0.952]
-Total_time - 317.818 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.8 98.731 (1, 2, 10, 10, 3) 2 1 [315.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.971 (1, 6, 10, 10) 1 1 [3.106]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.298 (1, 1, 10, 10, 3) 1 1 [0.953]
+Total_time - 319.86 - - - - -
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.1 97.518 (1, 6, 10, 10, 1) 2 1 [104.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.791 1.678 (1, 6, 10, 10) 1 1 [1.791]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.859 0.804 (1, 3, 10, 10, 1) 1 1 [0.859]
-Total_time - 106.75 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 137.6 98.104 (1, 6, 10, 10, 1) 2 1 [137.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.8 1.284 (1, 6, 10, 10) 1 1 [1.8]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.859 0.613 (1, 3, 10, 10, 1) 1 1 [0.859]
+Total_time - 140.26 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.917 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.347 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.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_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 9fa68b99a5..a2a5ae707c 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -459,7 +459,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 35.9MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 205MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -585,7 +585,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.445 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.360 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_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">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 0a9044c895..298cb6f16b 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ 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/tmpgqqr5530/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpt0pz0bwf/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ 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="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpgqqr5530/images/target contains 8144 images
-/tmp/tmpgqqr5530/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpt0pz0bwf/images/target contains 8144 images
+/tmp/tmpt0pz0bwf/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ 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 - 48s - loss: 0.2011 - accuracy: 0.9298 - val_loss: 0.1062 - val_accuracy: 0.9630 - 48s/epoch - 145ms/step
+328/328 - 47s - loss: 0.2256 - accuracy: 0.9233 - val_loss: 0.1240 - val_accuracy: 0.9577 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0984 - accuracy: 0.9643 - val_loss: 0.1690 - val_accuracy: 0.9449 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0982 - accuracy: 0.9631 - val_loss: 0.1112 - val_accuracy: 0.9668 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0622 - accuracy: 0.9763 - val_loss: 0.1043 - val_accuracy: 0.9660 - 43s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0624 - accuracy: 0.9777 - val_loss: 0.1148 - val_accuracy: 0.9645 - 43s/epoch - 130ms/step
-<keras.callbacks.History object at 0x7f8a6d7b6ad0>
+<keras.callbacks.History object at 0x7f13d07c2b50>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ 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 31.228 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 18.132 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 2f8318da15..50dc9dc0f7 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>07:33.595</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:15.271</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,30 +354,30 @@
</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">5. 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>04:31.228</p></td>
+<td><p>04:18.132</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">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:23.917</p></td>
+<td><p>01:21.347</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:20.445</p></td>
+<td><p>01:18.360</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.511</p></td>
+<td><p>00:10.202</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.494</p></td>
+<td><p>00:07.230</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">1. microTVM CLI Tool</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. 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>
<td><p>00:00.000</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">7. 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>
+<tr class="row-odd"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">1. microTVM CLI Tool</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 5379fbd833..3066aa6aac 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:47.150</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.725</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</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>00:34.871</p></td>
+<td><p>00:33.718</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>00:10.645</p></td>
+<td><p>00:10.384</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>00:01.628</p></td>
+<td><p>00:01.618</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 7c4ac6b123..589ca30d23 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -540,7 +540,7 @@ 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 0x7f891bf9d9e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f141332d290>
</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 de0fe5b2e5..2b9f9fe212 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:07.231</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.854</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,23 +354,23 @@
</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>00:04.655</p></td>
+<td><p>00:05.401</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>00:01.174</p></td>
+<td><p>00:01.102</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>00:00.593</p></td>
+<td><p>00:00.573</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>00:00.578</p></td>
+<td><p>00:00.551</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>00:00.119</p></td>
+<td><p>00:00.117</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>
@@ -378,7 +378,7 @@
<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>
-<td><p>00:00.033</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 1515c4b747..e285b427a5 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -234,7 +234,17 @@
<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/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 572408c15c..e9c20ee659 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ 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>
@@ -1905,7 +1905,7 @@ 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/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 15a635645f..ce8d94d94b 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/422ca2855/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/422ca2855/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L45">rpc_server.ts:45</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/422ca2855/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L44">rpc_server.ts:44</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/422ca2855/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L65">rpc_server.ts:65</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/422ca2855/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L51">rpc_server.ts:51</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/422ca2855/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L59">rpc_server.ts:59</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 6b331e678a..79326e88eb 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/422ca2855/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 d063a0f055..40642a4459 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/422ca2855/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L359">runtime.ts:359</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/422ca2855/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L357">runtime.ts:357</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/422ca2855/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L355">runtime.ts:355</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/422ca2855/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L359">runtime.ts:359</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/422ca2855/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L376">runtime.ts:376</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/422ca2855/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L367">runtime.ts:367</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 d0fdaf08cd..884b1a67ed 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/422ca2855/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L299">runtime.ts:299</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/422ca2855/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L297">runtime.ts:297</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/422ca2855/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L295">runtime.ts:295</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/422ca2855/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L320">runtime.ts:320</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/422ca2855/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L327">runtime.ts:327</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 abe276e3d1..3e6b457722 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/422ca2855/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 b97bc7a4ec..4ac933425a 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/422ca2855/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L50">runtime.ts:50</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/422ca2855/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L47">runtime.ts:47</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/422ca2855/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L46">runtime.ts:46</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/422ca2855/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L45">runtime.ts:45</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/422ca2855/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L48">runtime.ts:48</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/422ca2855/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L77">runtime.ts:77</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/422ca2855/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L67">runtime.ts:67</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/422ca2855/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L85">runtime.ts:85</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/422ca2855/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L96">runtime.ts:96</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/422ca2855/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L73">runtime.ts:73</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/instance.html b/docs/reference/api/typedoc/classes/instance.html
index cb2e0cb8fd..a7219b3bad 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/422ca2855/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<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/422ca2855/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L957">runtime.ts:957</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 346c64abfd..5448bf4ce9 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/422ca2855/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 241a4a252e..10367dca9d 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.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/422ca2855/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L641">runtime.ts:641</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/422ca2855/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L687">runtime.ts:687</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 b242554633..474874a452 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/422ca2855/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L401">runtime.ts:401</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/422ca2855/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L394">runtime.ts:394</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/422ca2855/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<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/422ca2855/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<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/422ca2855/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L553">runtime.ts:553</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 aaeb3d8b7c..5c059fa310 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index e17dee8743..f31d19d794 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/422ca2855/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L95">rpc_server.ts:95</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/422ca2855/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L84">rpc_server.ts:84</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/422ca2855/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L80">rpc_server.ts:80</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/422ca2855/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L83">rpc_server.ts:83</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/422ca2855/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L81">rpc_server.ts:81</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/422ca2855/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L82">rpc_server.ts:82</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/422ca2855/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 350302c659..8388c07f0d 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 6098621b07..d64712c924 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/422ca2855/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L235">runtime.ts:235</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/422ca2855/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L235">runtime.ts:235</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/422ca2855/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index 3d22231cb9..1ca8c2a239 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L730">runtime.ts:730</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/422ca2855/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 682485f30f..dabe8cd917 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.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/422ca2855/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L730">runtime.ts:730</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/422ca2855/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L758">runtime.ts:758</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 12f18b10df..2d7b88a89f 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/422ca2855/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/webgpu.ts#L172">webgpu.ts:172</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/422ca2855/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 e2f2b83799..c9ff137948 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/422ca2855/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L242">ctypes.ts:242</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/422ca2855/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L238">ctypes.ts:238</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/422ca2855/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L236">ctypes.ts:236</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/422ca2855/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L240">ctypes.ts:240</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/422ca2855/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L248">ctypes.ts:248</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/422ca2855/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L243">ctypes.ts:243</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/422ca2855/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L241">ctypes.ts:241</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/422ca2855/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L245">ctypes.ts:245</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/422ca2855/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L249">ctypes.ts:249</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/422ca2855/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L244">ctypes.ts:244</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/422ca2855/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L250">ctypes.ts:250</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/422ca2855/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L239">ctypes.ts:239</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/422ca2855/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L246">ctypes.ts:246</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/422ca2855/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L247">ctypes.ts:247</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/422ca2855/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 6d3a1c0e47..fbe9017b9c 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/422ca2855/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L812">runtime.ts:812</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/422ca2855/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index bf2a0d2058..e492d03cb0 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/422ca2855/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L339">runtime.ts:339</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/422ca2855/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L337">runtime.ts:337</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/422ca2855/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L340">runtime.ts:340</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/422ca2855/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index febf292dba..4f23647608 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/422ca2855/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L29">rpc_server.ts:29</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/422ca2855/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L30">rpc_server.ts:30</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/422ca2855/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L31">rpc_server.ts:31</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/422ca2855/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L34">rpc_server.ts:34</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/422ca2855/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L33">rpc_server.ts:33</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/422ca2855/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index f9d24c5ffd..a68d10d317 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/422ca2855/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L228">ctypes.ts:228</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/422ca2855/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L229">ctypes.ts:229</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/422ca2855/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L225">ctypes.ts:225</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/422ca2855/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L226">ctypes.ts:226</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/422ca2855/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L223">ctypes.ts:223</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/422ca2855/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L224">ctypes.ts:224</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/422ca2855/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L227">ctypes.ts:227</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/422ca2855/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L222">ctypes.ts:222</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/422ca2855/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 4a95e17d5b..4109156e99 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<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>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<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/422ca2855/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<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/422ca2855/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<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/422ca2855/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<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/422ca2855/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<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/422ca2855/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<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/422ca2855/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<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/422ca2855/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<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/422ca2855/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<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/422ca2855/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<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/422ca2855/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<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/422ca2855/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<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/422ca2855/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<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/422ca2855/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<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/422ca2855/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<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/422ca2855/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<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/422ca2855/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<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/422ca2855/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<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/422ca2855/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<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><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<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"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<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/422ca2855/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<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/422ca2855/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<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/422ca2855/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<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/422ca2855/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<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/422ca2855/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<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/422ca2855/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<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/422ca2855/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<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/422ca2855/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<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/422ca2855/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<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/422ca2855/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<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/422ca2855/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/422ca2855/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<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/422ca2855/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<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/422ca2855/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<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/422ca2855/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<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/422ca2855/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<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/422ca2855/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<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/422ca2855/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<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/422ca2855/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<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/422ca2855/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<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/422ca2855/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<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/422ca2855/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<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/422ca2855/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<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/422ca2855/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<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/422ca2855/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<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/422ca2855/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<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/422ca2855/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<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/422ca2855/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<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/422ca2855/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<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/422ca2855/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<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/422ca2855/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 697e387e9a..c684a4d2e9 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<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/422ca2855/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 bf55c74706..13a6394e05 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/422ca2855/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 23588570ea..1f06fae56c 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/422ca2855/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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/422ca2855/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/302cee994/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 fd9eec08ca..635018bcba 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 b1e0707a46..d47bcf83c3 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:32.905</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:31.661</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,7 +354,7 @@
</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>00:32.899</p></td>
+<td><p>00:31.655</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>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 3db7ad9371..31e610975f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ 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 35.13s!
+resnet18_v1 inference graph built in 33.70s!
</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 339ac3d201..3fb35990ff 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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 23.63s!
+yolov3-tiny inference graph built in 23.00s!
</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 8bc42e5448..60a2b26423 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>01:42.484</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.032</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>00:52.010</p></td>
+<td><p>00:50.483</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:50.474</p></td>
+<td><p>00:49.549</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 6fa1915b8b..49662bece8 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:03.182</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.163</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</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>00:02.709</p></td>
+<td><p>00:02.705</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>00:00.474</p></td>
+<td><p>00:00.458</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 6c180879be..fbc3669ef3 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>00:00.776</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.756</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,11 +354,11 @@
</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>00:00.400</p></td>
+<td><p>00:00.392</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>00:00.376</p></td>
+<td><p>00:00.364</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 2219517a8d..e0d0f44991 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -497,6 +497,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><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">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -574,7 +577,7 @@ class Module:
<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: 95.062 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.464 ms
</pre></div>
</div>
</div>
@@ -646,7 +649,7 @@ 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 20.802 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 45.783 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 aa3d9b1539..c7c521895a 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ 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: 10.20/10.20 result: MeasureResult(costs=(0.026328871600000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6988813877105713, timestamp=1678426663.706219) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-No: 2 GFLOPS: 11.93/11.93 result: MeasureResult(costs=(0.022504498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6487886905670166, timestamp=1678426664.3307338) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
-No: 3 GFLOPS: 2.60/11.93 result: MeasureResult(costs=(0.10327460799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8966200351715088, timestamp=1678426667.5236785) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
-No: 4 GFLOPS: 3.05/11.93 result: MeasureResult(costs=(0.0878680908,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6547558307647705, timestamp=1678426670.46842) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
-No: 5 GFLOPS: 10.44/11.93 result: MeasureResult(costs=(0.025708404600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6992964744567871, timestamp=1678426671.3154767) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
-No: 6 GFLOPS: 0.50/11.93 result: MeasureResult(costs=(0.5373314396,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.858155727386475, timestamp=1678426680.1892262) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 7 GFLOPS: 1.97/11.93 result: MeasureResult(costs=(0.1360990762,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4152307510375977, timestamp=1678426683.9060924) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
-No: 8 GFLOPS: 14.33/14.33 result: MeasureResult(costs=(0.0187316278,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6062562465667725, timestamp=1678426684.4665697) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
-No: 9 GFLOPS: 13.72/14.33 result: MeasureResult(costs=(0.019561779,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5515782833099365, timestamp=1678426685.1321933) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
-No: 10 GFLOPS: 1.52/14.33 result: MeasureResult(costs=(0.1768868496,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.027825117111206, timestamp=1678426688.2163513) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+No: 1 GFLOPS: 2.10/2.10 result: MeasureResult(costs=(0.1280552958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.290757417678833, timestamp=1678446816.224587) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 2 GFLOPS: 10.37/10.37 result: MeasureResult(costs=(0.025887476400000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.661827802658081, timestamp=1678446816.8975248) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
+No: 3 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.0213346208,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6048679351806641, timestamp=1678446818.7509968) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+No: 4 GFLOPS: 11.47/12.58 result: MeasureResult(costs=(0.023393145400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6308467388153076, timestamp=1678446820.635989) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+No: 5 GFLOPS: 2.70/12.58 result: MeasureResult(costs=(0.0992693184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.853567361831665, timestamp=1678446823.9130473) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+No: 6 GFLOPS: 0.95/12.58 result: MeasureResult(costs=(0.28228105919999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.76443076133728, timestamp=1678446828.6901522) [('tile_y', [-1, 32]), ('tile_x', [-1, 2])],None,15
+No: 7 GFLOPS: 11.93/12.58 result: MeasureResult(costs=(0.022503239400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6788883209228516, timestamp=1678446829.3152707) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 8 GFLOPS: 9.16/12.58 result: MeasureResult(costs=(0.0293137744,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7261197566986084, timestamp=1678446830.045977) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
+No: 9 GFLOPS: 11.63/12.58 result: MeasureResult(costs=(0.0230815666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.598088264465332, timestamp=1678446830.7595081) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+No: 10 GFLOPS: 3.36/12.58 result: MeasureResult(costs=(0.079912539,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4955024719238281, timestamp=1678446832.2990744) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
</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 3f2597ad0c..2e309415c2 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ 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': 521.825519730005, 'median': 521.9138121500066, 'std': 3.297140399641487}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.9942594399997, 'median': 513.6630722999996, 'std': 1.3362884486950066}
</pre></div>
</div>
</div>
@@ -715,178 +715,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 13.36/ 17.42 GFLOPS | Progress: (4/20) | 10.26 s
-[Task 1/25] Current/Best: 14.26/ 22.17 GFLOPS | Progress: (8/20) | 16.49 s
-[Task 1/25] Current/Best: 6.39/ 22.17 GFLOPS | Progress: (12/20) | 20.47 s
-[Task 1/25] Current/Best: 10.52/ 22.82 GFLOPS | Progress: (16/20) | 23.27 s
-[Task 1/25] Current/Best: 23.53/ 23.53 GFLOPS | Progress: (20/20) | 25.15 s Done.
+[Task 1/25] Current/Best: 13.50/ 13.50 GFLOPS | Progress: (4/20) | 14.82 s
+[Task 1/25] Current/Best: 19.14/ 21.96 GFLOPS | Progress: (8/20) | 18.59 s
+[Task 1/25] Current/Best: 21.98/ 21.98 GFLOPS | Progress: (12/20) | 21.27 s
+[Task 1/25] Current/Best: 17.72/ 21.98 GFLOPS | Progress: (16/20) | 24.37 s
+[Task 1/25] Current/Best: 11.49/ 22.46 GFLOPS | Progress: (20/20) | 27.19 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 11.21/ 16.97 GFLOPS | Progress: (4/20) | 4.43 s
-[Task 2/25] Current/Best: 7.11/ 16.97 GFLOPS | Progress: (8/20) | 6.38 s
-[Task 2/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (12/20) | 7.80 s
-[Task 2/25] Current/Best: 15.12/ 19.06 GFLOPS | Progress: (16/20) | 9.29 s
-[Task 2/25] Current/Best: 11.24/ 19.06 GFLOPS | Progress: (20/20) | 11.10 s Done.
+[Task 2/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (4/20) | 4.94 s
+[Task 2/25] Current/Best: 9.02/ 21.55 GFLOPS | Progress: (8/20) | 6.70 s
+[Task 2/25] Current/Best: 16.59/ 21.55 GFLOPS | Progress: (12/20) | 8.33 s
+[Task 2/25] Current/Best: 8.58/ 21.55 GFLOPS | Progress: (16/20) | 10.39 s
+[Task 2/25] Current/Best: 13.02/ 21.55 GFLOPS | Progress: (20/20) | 12.22 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 9.98/ 17.96 GFLOPS | Progress: (4/20) | 5.42 s
-[Task 3/25] Current/Best: 14.47/ 23.59 GFLOPS | Progress: (8/20) | 7.67 s
-[Task 3/25] Current/Best: 11.39/ 23.59 GFLOPS | Progress: (12/20) | 11.27 s
-[Task 3/25] Current/Best: 5.78/ 23.59 GFLOPS | Progress: (16/20) | 14.52 s
-[Task 3/25] Current/Best: 15.00/ 23.59 GFLOPS | Progress: (20/20) | 17.30 s Done.
+[Task 3/25] Current/Best: 15.87/ 20.10 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 3/25] Current/Best: 6.78/ 20.10 GFLOPS | Progress: (8/20) | 7.21 s
+[Task 3/25] Current/Best: 16.18/ 20.10 GFLOPS | Progress: (12/20) | 9.58 s
+[Task 3/25] Current/Best: 18.10/ 20.10 GFLOPS | Progress: (16/20) | 12.23 s
+[Task 3/25] Current/Best: 11.60/ 20.10 GFLOPS | Progress: (20/20) | 15.24 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (4/20) | 5.04 s
-[Task 4/25] Current/Best: 6.73/ 21.98 GFLOPS | Progress: (8/20) | 7.42 s
-[Task 4/25] Current/Best: 9.06/ 21.98 GFLOPS | Progress: (12/20) | 12.16 s
-[Task 4/25] Current/Best: 9.63/ 21.98 GFLOPS | Progress: (16/20) | 18.40 s
-[Task 4/25] Current/Best: 8.37/ 21.98 GFLOPS | Progress: (20/20) | 29.56 s
+[Task 4/25] Current/Best: 9.57/ 16.63 GFLOPS | Progress: (4/20) | 10.62 s
+[Task 4/25] Current/Best: 17.03/ 17.03 GFLOPS | Progress: (8/20) | 14.14 s
+[Task 4/25] Current/Best: 12.13/ 17.03 GFLOPS | Progress: (12/20) | 18.53 s
+[Task 4/25] Current/Best: 8.43/ 17.03 GFLOPS | Progress: (16/20) | 23.55 s
+[Task 4/25] Current/Best: 15.59/ 20.72 GFLOPS | Progress: (20/20) | 28.25 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 5.86/ 19.40 GFLOPS | Progress: (4/20) | 5.87 s
-[Task 5/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (8/20) | 8.08 s
-[Task 5/25] Current/Best: 5.27/ 20.43 GFLOPS | Progress: (12/20) | 10.59 s
-[Task 5/25] Current/Best: 8.58/ 20.43 GFLOPS | Progress: (16/20) | 12.75 s
-[Task 5/25] Current/Best: 20.19/ 20.43 GFLOPS | Progress: (20/20) | 15.11 s Done.
+[Task 5/25] Current/Best: 4.35/ 16.33 GFLOPS | Progress: (4/20) | 5.11 s
+[Task 5/25] Current/Best: 14.39/ 16.33 GFLOPS | Progress: (8/20) | 7.74 s
+[Task 5/25] Current/Best: 15.92/ 17.54 GFLOPS | Progress: (12/20) | 9.59 s
+[Task 5/25] Current/Best: 13.70/ 19.13 GFLOPS | Progress: (16/20) | 11.51 s
+[Task 5/25] Current/Best: 5.27/ 22.19 GFLOPS | Progress: (20/20) | 13.61 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 4.03/ 17.52 GFLOPS | Progress: (4/20) | 5.51 s
-[Task 6/25] Current/Best: 7.89/ 17.52 GFLOPS | Progress: (8/20) | 9.00 s
-[Task 6/25] Current/Best: 14.11/ 18.07 GFLOPS | Progress: (12/20) | 11.37 s
-[Task 6/25] Current/Best: 8.93/ 18.07 GFLOPS | Progress: (16/20) | 15.10 s
-[Task 6/25] Current/Best: 8.85/ 20.02 GFLOPS | Progress: (20/20) | 18.43 s Done.
+[Task 6/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (4/20) | 5.01 s
+[Task 6/25] Current/Best: 15.97/ 22.63 GFLOPS | Progress: (8/20) | 7.84 s
+[Task 6/25] Current/Best: 10.69/ 22.63 GFLOPS | Progress: (12/20) | 10.35 s
+[Task 6/25] Current/Best: 14.41/ 22.63 GFLOPS | Progress: (16/20) | 14.70 s
+[Task 6/25] Current/Best: 11.42/ 22.63 GFLOPS | Progress: (20/20) | 17.86 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 14.53/ 20.70 GFLOPS | Progress: (4/20) | 5.19 s
-[Task 7/25] Current/Best: 10.77/ 20.70 GFLOPS | Progress: (8/20) | 7.90 s
-[Task 7/25] Current/Best: 1.58/ 20.70 GFLOPS | Progress: (12/20) | 11.96 s
-[Task 7/25] Current/Best: 12.73/ 20.70 GFLOPS | Progress: (16/20) | 14.67 s
-[Task 7/25] Current/Best: 13.30/ 20.70 GFLOPS | Progress: (20/20) | 16.87 s Done.
+[Task 7/25] Current/Best: 12.55/ 15.22 GFLOPS | Progress: (4/20) | 5.13 s
+[Task 7/25] Current/Best: 12.31/ 18.10 GFLOPS | Progress: (8/20) | 7.33 s
+[Task 7/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (12/20) | 9.95 s
+[Task 7/25] Current/Best: 5.78/ 20.74 GFLOPS | Progress: (16/20) | 12.19 s
+[Task 7/25] Current/Best: 11.28/ 20.74 GFLOPS | Progress: (20/20) | 15.17 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (4/20) | 6.60 s
-[Task 8/25] Current/Best: 12.97/ 15.74 GFLOPS | Progress: (8/20) | 9.85 s
-[Task 8/25] Current/Best: 13.52/ 15.74 GFLOPS | Progress: (12/20) | 12.86 s
-[Task 8/25] Current/Best: 6.19/ 15.74 GFLOPS | Progress: (16/20) | 15.97 s
-[Task 8/25] Current/Best: 11.50/ 15.74 GFLOPS | Progress: (20/20) | 22.36 s Done.
+[Task 8/25] Current/Best: 15.59/ 15.69 GFLOPS | Progress: (4/20) | 5.04 s
+[Task 8/25] Current/Best: 11.00/ 18.29 GFLOPS | Progress: (8/20) | 10.34 s
+[Task 8/25] Current/Best: 12.41/ 18.29 GFLOPS | Progress: (12/20) | 14.86 s
+[Task 8/25] Current/Best: 14.38/ 21.68 GFLOPS | Progress: (16/20) | 21.06 s
+[Task 8/25] Current/Best: 11.42/ 21.68 GFLOPS | Progress: (20/20) | 26.77 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (4/20) | 4.49 s
-[Task 9/25] Current/Best: 15.96/ 21.85 GFLOPS | Progress: (8/20) | 6.53 s
-[Task 9/25] Current/Best: 10.08/ 21.85 GFLOPS | Progress: (12/20) | 8.84 s Done.
-
-[Task 9/25] Current/Best: 12.93/ 21.85 GFLOPS | Progress: (16/20) | 10.70 s
-[Task 9/25] Current/Best: 13.99/ 21.85 GFLOPS | Progress: (20/20) | 13.21 s Done.
+[Task 9/25] Current/Best: 13.81/ 13.81 GFLOPS | Progress: (4/20) | 10.88 s
+[Task 9/25] Current/Best: 15.06/ 15.13 GFLOPS | Progress: (8/20) | 13.58 s
+[Task 9/25] Current/Best: 3.40/ 15.13 GFLOPS | Progress: (12/20) | 19.61 s
+[Task 9/25] Current/Best: 7.19/ 20.32 GFLOPS | Progress: (16/20) | 22.49 s
+[Task 9/25] Current/Best: 15.25/ 20.32 GFLOPS | Progress: (20/20) | 30.24 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 9.78/ 14.57 GFLOPS | Progress: (4/20) | 4.90 s
-[Task 10/25] Current/Best: 14.00/ 14.57 GFLOPS | Progress: (8/20) | 9.67 s
-[Task 10/25] Current/Best: 11.79/ 14.57 GFLOPS | Progress: (12/20) | 11.70 s
-[Task 10/25] Current/Best: 14.34/ 14.57 GFLOPS | Progress: (16/20) | 14.54 s
-[Task 10/25] Current/Best: 13.16/ 14.57 GFLOPS | Progress: (20/20) | 16.98 s Done.
+[Task 10/25] Current/Best: 10.50/ 15.36 GFLOPS | Progress: (4/20) | 5.19 s
+[Task 10/25] Current/Best: 18.83/ 18.83 GFLOPS | Progress: (8/20) | 6.95 s
+[Task 10/25] Current/Best: 9.21/ 18.83 GFLOPS | Progress: (12/20) | 9.13 s
+[Task 10/25] Current/Best: 9.07/ 20.37 GFLOPS | Progress: (16/20) | 11.34 s
+[Task 10/25] Current/Best: 7.25/ 20.37 GFLOPS | Progress: (20/20) | 14.11 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 18.66/ 22.69 GFLOPS | Progress: (4/20) | 4.99 s
-[Task 11/25] Current/Best: 15.77/ 22.69 GFLOPS | Progress: (8/20) | 7.15 s
-[Task 11/25] Current/Best: 17.95/ 22.69 GFLOPS | Progress: (12/20) | 9.13 s
-[Task 11/25] Current/Best: 13.74/ 22.69 GFLOPS | Progress: (16/20) | 11.49 s
-[Task 11/25] Current/Best: 15.90/ 22.69 GFLOPS | Progress: (20/20) | 13.76 s Done.
+[Task 11/25] Current/Best: 17.09/ 19.36 GFLOPS | Progress: (4/20) | 5.05 s
+[Task 11/25] Current/Best: 3.10/ 19.36 GFLOPS | Progress: (8/20) | 8.12 s
+[Task 11/25] Current/Best: 18.97/ 19.36 GFLOPS | Progress: (12/20) | 11.28 s
+[Task 11/25] Current/Best: 5.82/ 19.36 GFLOPS | Progress: (16/20) | 14.51 s
+[Task 11/25] Current/Best: 16.43/ 19.36 GFLOPS | Progress: (20/20) | 16.84 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 9.56/ 19.99 GFLOPS | Progress: (4/20) | 5.40 s
-[Task 12/25] Current/Best: 7.92/ 19.99 GFLOPS | Progress: (8/20) | 10.28 s
-[Task 12/25] Current/Best: 10.10/ 19.99 GFLOPS | Progress: (12/20) | 12.47 s
-[Task 12/25] Current/Best: 12.15/ 19.99 GFLOPS | Progress: (16/20) | 15.16 s
-[Task 12/25] Current/Best: 11.05/ 19.99 GFLOPS | Progress: (20/20) | 19.22 s Done.
+[Task 12/25] Current/Best: 14.48/ 14.48 GFLOPS | Progress: (4/20) | 9.16 s
+[Task 12/25] Current/Best: 9.02/ 15.05 GFLOPS | Progress: (8/20) | 17.76 s
+[Task 12/25] Current/Best: 10.84/ 17.23 GFLOPS | Progress: (12/20) | 20.19 s
+[Task 12/25] Current/Best: 17.81/ 20.84 GFLOPS | Progress: (16/20) | 22.40 s
+[Task 12/25] Current/Best: 21.09/ 21.53 GFLOPS | Progress: (20/20) | 27.31 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (4/20) | 6.19 s
-[Task 13/25] Current/Best: 14.33/ 19.00 GFLOPS | Progress: (8/20) | 9.35 s
-[Task 13/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (12/20) | 12.52 s
-[Task 13/25] Current/Best: 5.12/ 20.83 GFLOPS | Progress: (16/20) | 16.45 s
-[Task 13/25] Current/Best: 19.31/ 22.09 GFLOPS | Progress: (20/20) | 18.82 s Done.
+[Task 13/25] Current/Best: 11.75/ 16.69 GFLOPS | Progress: (4/20) | 6.22 s
+[Task 13/25] Current/Best: 21.25/ 22.23 GFLOPS | Progress: (8/20) | 9.45 s
+[Task 13/25] Current/Best: 16.87/ 22.23 GFLOPS | Progress: (12/20) | 12.35 s
+[Task 13/25] Current/Best: 6.98/ 22.23 GFLOPS | Progress: (16/20) | 14.88 s
+[Task 13/25] Current/Best: 16.40/ 22.23 GFLOPS | Progress: (20/20) | 17.42 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.13/ 13.13 GFLOPS | Progress: (4/20) | 6.30 s
-[Task 14/25] Current/Best: 8.56/ 16.26 GFLOPS | Progress: (8/20) | 12.35 s
-[Task 14/25] Current/Best: 8.34/ 16.26 GFLOPS | Progress: (12/20) | 15.93 s
-[Task 14/25] Current/Best: 16.31/ 17.95 GFLOPS | Progress: (16/20) | 21.72 s
-[Task 14/25] Current/Best: 13.56/ 17.95 GFLOPS | Progress: (20/20) | 24.79 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 14.26/ 20.27 GFLOPS | Progress: (4/20) | 4.64 s
-[Task 15/25] Current/Best: 3.19/ 20.27 GFLOPS | Progress: (8/20) | 7.54 s
-[Task 15/25] Current/Best: 19.90/ 20.27 GFLOPS | Progress: (12/20) | 10.25 s
-[Task 15/25] Current/Best: 4.86/ 20.27 GFLOPS | Progress: (16/20) | 12.94 s Done.
-
-[Task 15/25] Current/Best: 18.89/ 20.27 GFLOPS | Progress: (20/20) | 15.85 s Done.
-
+[Task 14/25] Current/Best: 5.07/ 18.99 GFLOPS | Progress: (4/20) | 8.57 s
+[Task 14/25] Current/Best: 8.59/ 18.99 GFLOPS | Progress: (8/20) | 12.66 s
+[Task 14/25] Current/Best: 12.83/ 18.99 GFLOPS | Progress: (12/20) | 15.49 s
+[Task 14/25] Current/Best: 15.10/ 18.99 GFLOPS | Progress: (16/20) | 19.15 s
+[Task 14/25] Current/Best: 11.03/ 18.99 GFLOPS | Progress: (20/20) | 21.57 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 15/25] Current/Best: 18.91/ 18.97 GFLOPS | Progress: (4/20) | 5.58 s
+[Task 15/25] Current/Best: 6.37/ 18.97 GFLOPS | Progress: (8/20) | 7.44 s
+[Task 15/25] Current/Best: 15.92/ 20.11 GFLOPS | Progress: (12/20) | 11.65 s
+[Task 15/25] Current/Best: 12.43/ 20.11 GFLOPS | Progress: (16/20) | 13.53 s
+[Task 15/25] Current/Best: 12.27/ 24.03 GFLOPS | Progress: (20/20) | 16.79 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 3.08/ 11.52 GFLOPS | Progress: (4/20) | 6.41 s
-[Task 16/25] Current/Best: 12.18/ 18.67 GFLOPS | Progress: (8/20) | 7.93 s
-[Task 16/25] Current/Best: 10.66/ 22.75 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 16/25] Current/Best: 14.94/ 22.75 GFLOPS | Progress: (16/20) | 11.16 s
-[Task 16/25] Current/Best: 16.18/ 22.75 GFLOPS | Progress: (20/20) | 12.99 s Done.
+[Task 16/25] Current/Best: 14.20/ 16.10 GFLOPS | Progress: (4/20) | 4.96 s
+[Task 16/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (8/20) | 8.63 s
+[Task 16/25] Current/Best: 15.98/ 18.43 GFLOPS | Progress: (12/20) | 11.60 s
+[Task 16/25] Current/Best: 15.40/ 18.43 GFLOPS | Progress: (16/20) | 13.28 s
+[Task 16/25] Current/Best: 18.61/ 18.61 GFLOPS | Progress: (20/20) | 15.79 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 1.56/ 19.46 GFLOPS | Progress: (4/20) | 6.65 s
-[Task 17/25] Current/Best: 12.86/ 19.46 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 17/25] Current/Best: 13.15/ 19.46 GFLOPS | Progress: (12/20) | 11.52 s
-[Task 17/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (16/20) | 13.97 s
-[Task 17/25] Current/Best: 9.71/ 20.68 GFLOPS | Progress: (20/20) | 16.97 s Done.
+[Task 17/25] Current/Best: 18.72/ 19.79 GFLOPS | Progress: (4/20) | 5.35 s
+[Task 17/25] Current/Best: 15.43/ 19.79 GFLOPS | Progress: (8/20) | 8.02 s
+[Task 17/25] Current/Best: 17.99/ 19.79 GFLOPS | Progress: (12/20) | 10.53 s
+[Task 17/25] Current/Best: 13.36/ 22.92 GFLOPS | Progress: (16/20) | 13.91 s
+[Task 17/25] Current/Best: 4.94/ 22.92 GFLOPS | Progress: (20/20) | 16.66 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 9.23/ 15.08 GFLOPS | Progress: (4/20) | 5.64 s
-[Task 18/25] Current/Best: 19.16/ 19.16 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 18/25] Current/Best: 15.10/ 19.16 GFLOPS | Progress: (12/20) | 11.15 s
-[Task 18/25] Current/Best: 7.76/ 19.16 GFLOPS | Progress: (16/20) | 17.23 s
-[Task 18/25] Current/Best: 16.92/ 19.16 GFLOPS | Progress: (20/20) | 22.91 s Done.
+[Task 18/25] Current/Best: 6.11/ 13.31 GFLOPS | Progress: (4/20) | 5.39 s
+[Task 18/25] Current/Best: 11.73/ 13.31 GFLOPS | Progress: (8/20) | 9.04 s
+[Task 18/25] Current/Best: 18.36/ 18.36 GFLOPS | Progress: (12/20) | 11.37 s
+[Task 18/25] Current/Best: 17.46/ 18.36 GFLOPS | Progress: (16/20) | 13.44 s
+[Task 18/25] Current/Best: 7.50/ 19.58 GFLOPS | Progress: (20/20) | 16.95 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 9.59/ 11.77 GFLOPS | Progress: (4/20) | 7.90 s
-[Task 19/25] Current/Best: 3.08/ 22.86 GFLOPS | Progress: (8/20) | 11.61 s
-[Task 19/25] Current/Best: 9.69/ 22.86 GFLOPS | Progress: (12/20) | 15.61 s
-[Task 19/25] Current/Best: 10.67/ 22.86 GFLOPS | Progress: (16/20) | 19.14 s
-[Task 19/25] Current/Best: 8.75/ 22.86 GFLOPS | Progress: (20/20) | 21.56 s Done.
+[Task 19/25] Current/Best: 9.65/ 18.52 GFLOPS | Progress: (4/20) | 6.02 s
+[Task 19/25] Current/Best: 17.34/ 18.52 GFLOPS | Progress: (8/20) | 9.41 s
+[Task 19/25] Current/Best: 7.30/ 18.66 GFLOPS | Progress: (12/20) | 14.42 s
+[Task 19/25] Current/Best: 19.19/ 19.19 GFLOPS | Progress: (16/20) | 17.06 s
+[Task 19/25] Current/Best: 12.08/ 21.80 GFLOPS | Progress: (20/20) | 20.63 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 13.41/ 18.34 GFLOPS | Progress: (4/20) | 5.97 s
-[Task 20/25] Current/Best: 9.69/ 18.34 GFLOPS | Progress: (8/20) | 8.46 s
-[Task 20/25] Current/Best: 12.91/ 18.34 GFLOPS | Progress: (12/20) | 11.39 s
-[Task 20/25] Current/Best: 14.83/ 18.34 GFLOPS | Progress: (16/20) | 14.31 s
-[Task 20/25] Current/Best: 11.21/ 18.34 GFLOPS | Progress: (20/20) | 17.38 s
+[Task 20/25] Current/Best: 6.60/ 19.94 GFLOPS | Progress: (4/20) | 5.21 s
+[Task 20/25] Current/Best: 6.17/ 19.94 GFLOPS | Progress: (8/20) | 7.66 s
+[Task 20/25] Current/Best: 9.92/ 19.94 GFLOPS | Progress: (12/20) | 9.92 s
+[Task 20/25] Current/Best: 11.28/ 19.94 GFLOPS | Progress: (16/20) | 12.35 s
+[Task 20/25] Current/Best: 10.73/ 19.94 GFLOPS | Progress: (20/20) | 14.77 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.33/ 18.09 GFLOPS | Progress: (4/20) | 5.58 s Done.
+[Task 21/25] Current/Best: 13.68/ 15.40 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 21/25] Current/Best: 4.80/ 18.57 GFLOPS | Progress: (8/20) | 7.69 s Done.
+ Done.
-[Task 21/25] Current/Best: 8.17/ 18.09 GFLOPS | Progress: (8/20) | 9.20 s
-[Task 21/25] Current/Best: 15.60/ 18.09 GFLOPS | Progress: (12/20) | 11.93 s
-[Task 21/25] Current/Best: 14.55/ 18.09 GFLOPS | Progress: (16/20) | 14.79 s
-[Task 21/25] Current/Best: 18.70/ 18.70 GFLOPS | Progress: (20/20) | 17.63 s
+[Task 21/25] Current/Best: 20.35/ 20.89 GFLOPS | Progress: (12/20) | 10.65 s
+[Task 21/25] Current/Best: 18.04/ 22.03 GFLOPS | Progress: (16/20) | 12.41 s
+[Task 21/25] Current/Best: 9.66/ 22.03 GFLOPS | Progress: (20/20) | 14.43 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 12.93/ 18.10 GFLOPS | Progress: (4/20) | 5.75 s
-[Task 22/25] Current/Best: 9.25/ 18.73 GFLOPS | Progress: (8/20) | 7.62 s
-[Task 22/25] Current/Best: 13.30/ 18.73 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 22/25] Current/Best: 6.74/ 18.73 GFLOPS | Progress: (16/20) | 11.43 s
-[Task 22/25] Current/Best: 5.31/ 18.73 GFLOPS | Progress: (20/20) | 14.93 s Done.
+[Task 22/25] Current/Best: 19.75/ 19.75 GFLOPS | Progress: (4/20) | 6.34 s
+[Task 22/25] Current/Best: 8.95/ 19.75 GFLOPS | Progress: (8/20) | 8.40 s
+[Task 22/25] Current/Best: 6.53/ 19.75 GFLOPS | Progress: (12/20) | 10.19 s
+[Task 22/25] Current/Best: 17.83/ 19.75 GFLOPS | Progress: (16/20) | 12.09 s
+[Task 22/25] Current/Best: 18.54/ 19.75 GFLOPS | Progress: (20/20) | 14.80 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (4/20) | 5.21 s
-[Task 23/25] Current/Best: 10.33/ 21.85 GFLOPS | Progress: (8/20) | 8.50 s
-[Task 23/25] Current/Best: 9.08/ 21.85 GFLOPS | Progress: (12/20) | 12.46 s
-[Task 23/25] Current/Best: 3.09/ 22.39 GFLOPS | Progress: (16/20) | 16.58 s
-[Task 23/25] Current/Best: 18.00/ 22.39 GFLOPS | Progress: (20/20) | 21.11 s Done.
+[Task 23/25] Current/Best: 16.21/ 22.92 GFLOPS | Progress: (4/20) | 5.08 s
+[Task 23/25] Current/Best: 18.41/ 22.92 GFLOPS | Progress: (8/20) | 7.55 s
+[Task 23/25] Current/Best: 22.40/ 23.83 GFLOPS | Progress: (12/20) | 10.19 s
+[Task 23/25] Current/Best: 17.32/ 23.83 GFLOPS | Progress: (16/20) | 14.18 s
+[Task 23/25] Current/Best: 2.67/ 23.83 GFLOPS | Progress: (20/20) | 20.46 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 6.12/ 6.98 GFLOPS | Progress: (4/20) | 13.82 s
-[Task 24/25] Current/Best: 9.22/ 9.22 GFLOPS | Progress: (8/20) | 23.00 s
-[Task 24/25] Current/Best: 9.81/ 9.81 GFLOPS | Progress: (12/20) | 33.97 s Done.
-
-[Task 24/25] Current/Best: 3.05/ 9.81 GFLOPS | Progress: (16/20) | 46.26 s
-[Task 24/25] Current/Best: 3.47/ 9.81 GFLOPS | Progress: (20/20) | 58.89 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 3.44/ 8.54 GFLOPS | Progress: (4/20) | 9.27 s
-[Task 25/25] Current/Best: 8.86/ 8.86 GFLOPS | Progress: (8/20) | 12.79 s
-[Task 25/25] Current/Best: 8.54/ 8.86 GFLOPS | Progress: (12/20) | 23.75 s
-[Task 25/25] Current/Best: 3.00/ 8.99 GFLOPS | Progress: (16/20) | 34.73 s
-[Task 25/25] Current/Best: 1.54/ 8.99 GFLOPS | Progress: (20/20) | 41.82 s
+[Task 24/25] Current/Best: 1.79/ 8.46 GFLOPS | Progress: (4/20) | 8.29 s
+[Task 24/25] Current/Best: 3.57/ 10.52 GFLOPS | Progress: (8/20) | 19.25 s
+[Task 24/25] Current/Best: 8.26/ 10.52 GFLOPS | Progress: (12/20) | 30.21 s
+[Task 24/25] Current/Best: 0.54/ 10.52 GFLOPS | Progress: (16/20) | 40.93 s
+[Task 24/25] Current/Best: 2.28/ 10.52 GFLOPS | Progress: (20/20) | 53.51 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 25/25] Current/Best: 8.88/ 8.88 GFLOPS | Progress: (4/20) | 11.40 s
+[Task 25/25] Current/Best: 4.12/ 8.88 GFLOPS | Progress: (8/20) | 22.34 s
+[Task 25/25] Current/Best: 3.02/ 8.88 GFLOPS | Progress: (12/20) | 33.31 s
+[Task 25/25] Current/Best: 8.67/ 8.88 GFLOPS | Progress: (16/20) | 44.29 s
+[Task 25/25] Current/Best: 8.01/ 8.88 GFLOPS | Progress: (20/20) | 55.22 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -985,8 +986,8 @@ 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': 414.7175817000016, 'median': 414.696313449997, 'std': 4.941491717033467}
-unoptimized: {'mean': 521.825519730005, 'median': 521.9138121500066, 'std': 3.297140399641487}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 422.6275845400028, 'median': 421.9335912000133, 'std': 3.3812746177135073}
+unoptimized: {'mean': 513.9942594399997, 'median': 513.6630722999996, 'std': 1.3362884486950066}
</pre></div>
</div>
</div>
@@ -1000,7 +1001,7 @@ 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> ( 12 minutes 39.114 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 56.615 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 7a168e19ac..6da44802fb 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ 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>1.253e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.237e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index e1fa984537..affc2c85ea 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<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, 0xfc94d60)), stage(b, placeholder(b, 0x668a470)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs= [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x23ff03c0)), stage(b, placeholder(b, 0x931f590)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</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 2802796c76..7a9884c6ce 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<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>16:12.665</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:45.426</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</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>12:39.114</p></td>
+<td><p>12:56.615</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>01:20.802</p></td>
+<td><p>01:45.783</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>01:01.362</p></td>
+<td><p>00:58.964</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>00:37.101</p></td>
+<td><p>00:36.663</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>00:31.839</p></td>
+<td><p>00:24.877</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.408</p></td>
+<td><p>00:01.501</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.859</p></td>
+<td><p>00:00.850</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>00:00.180</p></td>
+<td><p>00:00.172</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index c3cb08acb7..1cd39ecf23 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -554,7 +554,7 @@ 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: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
naive: 0.000007
</pre></div>
</div>
@@ -610,7 +610,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</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">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
</pre></div>
</div>
</div>
@@ -649,7 +649,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000027
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000026
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.462599999144004e-06 1.0
- naive 6.9834e-06 0.9357864552302186
-parallel 8.1259e-06 1.0888832311703802
- vector 2.6817299999999998e-05 3.593559885706868
+ numpy 7.680659998641203e-06 1.0
+ naive 6.644600000000001e-06 0.865107946605566
+parallel 6.9043999999999995e-06 0.8989331647568656
+ vector 2.5740600000000002e-05 3.351352618727272
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ 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: 0.019223
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018534
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.403328
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.258933
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.310085
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.291995
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.351194
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336260
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.118749
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.118644
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108267
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109099
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110415
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110921
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145990
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146257
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ 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 3.403327676999999 1.0
- blocking 0.3100849985 0.0911122959436386
- vectorization 0.3511935568 0.10319122639098147
-loop permutation 0.11874873259999999 0.034891948078498235
- array packing 0.1082669506 0.03181208536917499
- block caching 0.1104151313 0.03244328544859068
- parallelization 0.14599012150000001 0.04289628720931418
+ none 3.2589328215999998 1.0
+ blocking 0.2919952335 0.0895984205518672
+ vectorization 0.3362601711 0.10318106862200072
+loop permutation 0.1186443246 0.036405882261098775
+ array packing 0.10909883219999998 0.0334768582760896
+ block caching 0.1109206511 0.034035881428676584
+ parallelization 0.1462572883 0.04487889020927832
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,6 @@ 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 1.362 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>