You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/22 00:03:32 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@545f8dc927d4dc9fb1394c67c681ea40ec16db8d)
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 0dc36204a4 deploying docs (apache/tvm@545f8dc927d4dc9fb1394c67c681ea40ec16db8d)
0dc36204a4 is described below
commit 0dc36204a4e1d3d909b37c60e5bdf0e18698c792
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 22 00:03:25 2022 +0000
deploying docs (apache/tvm@545f8dc927d4dc9fb1394c67c681ea40ec16db8d)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 322817 -> 327199 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23407 -> 22934 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_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 4 +-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 417 ++++++++++++++++++++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 190 ++++++++--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../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 | 12 +-
.../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 | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 ++-
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 | 14 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 35 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 417 ++++++++++++++++++++-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 190 ++++++++--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 6 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../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 | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
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 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +++---
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 274 +++++++-------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 43 ++-
128 files changed, 1923 insertions(+), 931 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9d7b73ba75..9acba7fd3b 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 9ae7d8cdc5..fb0f49ab60 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 9dd4d05132..9cb08188b9 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.933 seconds)
+ **Total running time of the script:** ( 1 minutes 10.166 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 790b80f493..8d86fe4963 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ 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 955ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 973ms/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 b788fda3ef..4194bf1ade 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7c4f1e49-41ad-45a2-8733-c0e70509ab0b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6b750afc-1efa-4bcf-8409-efe2e0573a2b 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 513c59b84e..9a6b0dafe3 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 44.9MB/s]
27%|##7 | 11.3M/41.5M [00:00<00:00, 48.4MB/s]
38%|###8 | 16.0M/41.5M [00:00<00:00, 44.6MB/s]
49%|####8 | 20.3M/41.5M [00:00<00:00, 40.9MB/s]
58%|#####8 | 24.2M/41.5M [00:00<00:00, 32.6MB/s]
79%|#######8 | 32.6M/41.5M [00:00<00:00, 47.2MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 40.0MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 41.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#8 | 7.79M/41.5M [00:00<00:00, 81.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 65.7MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
69%|######8 | 28.5M/41.5M [00:00<00:00, 60.8MB/s]
83%|########2 | 34.4M/41.5M [00:00<00:00, 50.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 63.2MB/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 9a95b6de24..096e54d425 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ 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]
31%|### | 13.7M/44.7M [00:00<00:00, 144MB/s]
61%|######1 | 27.4M/44.7M [00:00<00:00, 114MB/s]
86%|########6 | 38.6M/44.7M [00:00<00:00, 108MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
19%|#9 | 8.53M/44.7M [00:00<00:00, 89.4MB/s]
49%|####8 | 21.7M/44.7M [00:00<00:00, 118MB/s]
74%|#######3 | 32.9M/44.7M [00:00<00:00, 99.4MB/s]
100%|#########9| 44.7M/44.7M [00:00<00:00, 108MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 7e3f3d912d..4c55d54a50 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.466 seconds)
+ **Total running time of the script:** ( 1 minutes 12.047 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 0c2e7b46d4..9baa5cd523 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:45.291** total execution time for **how_to_compile_models** files:
+**05:43.043** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.933 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.047 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.466 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.166 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.245 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.739 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.094 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.559 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.187 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.503 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.403 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.827 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.476 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.341 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.246 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.386 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 3c1b051d9a..d2e9084033 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5776 15.5712 15.6789 15.4907 0.0566
+ 16.2368 16.1416 17.2407 15.8435 0.3782
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 5f2d11d83a..8bcc49e8aa 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
@@ -127,7 +127,7 @@ 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 | 8.12M/170M [00:00<00:02, 65.8MB/s]
8%|8 | 14.4M/170M [00:00<00:02, 61.7MB/s]
15%|#4 | 24.8M/170M [00:00<00:01, 81.2MB/s]
20%|## | 34.1M/170M [00:00<00:02, 59.0MB/s]
25%|##5 | 42.8M/170M [00:00<00:01, 67.7MB/s]
29%|##9 | 50.1M/170M [00:00<00:02, 56.0MB/s]
38%|###7 | 63.9M/170M [00:00<00:01, 77.3MB/s]
43%|####3 | 73.3M/170M [00:01<00:01, 82.7MB/s]
52%|#####1 | 88.0M/170M [00:01<00:00, 101MB/s]
58%|#####8 | 98.5M/170M [00:01<00:00, 103MB/s]
64%|######4 | 109M/170M [00:01<00:00, 90.2MB/s]
71%|####### | 120M/170M [00:01<00:00, 94.1MB/s]
76%|#######6 | 130M/170M [00:01<00:00, 92.9MB/s]
82%|########1 | 139M/170M [00:01<00:00, 90.9MB/s]
88%|########7 | 149M/170M [00:01<00:00, 94.6MB/s]
93%|#########3| 158M/170M [00:01<00:00, 96.4MB/s]
99%|#########8| 168M/170M [00:02<00:00, 96.5MB/s]
1
00%|##########| 170M/170M [00:02<00:00, 85.9MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 74.6MB/s]
13%|#2 | 21.8M/170M [00:00<00:01, 114MB/s]
19%|#9 | 32.8M/170M [00:00<00:01, 85.1MB/s]
27%|##7 | 46.3M/170M [00:00<00:01, 94.5MB/s]
37%|###6 | 62.3M/170M [00:00<00:01, 112MB/s]
43%|####3 | 73.5M/170M [00:00<00:00, 113MB/s]
50%|####9 | 84.7M/170M [00:00<00:00, 109MB/s]
56%|#####6 | 95.3M/170M [00:00<00:00, 106MB/s]
62%|######2 | 106M/170M [00:01<00:00, 102MB/s]
68%|######8 | 116M/170M [00:01<00:00, 103MB/s]
74%|#######4 | 126M/170M [00:01<00:00, 80.5MB/s]
85%|########5 | 145M/170M [00:01<00:00, 108MB/s]
92%|#########1| 156M/170M [00:01<00:00, 105MB/s]
98%|#########8| 167M/170M [00:01<00:00, 105MB/s]
100%|##########| 170M/170M [00:01<00:00, 102MB/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').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 14.529 seconds)
+ **Total running time of the script:** ( 3 minutes 15.476 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 62531fc463..a097b1a21a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ 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, 40.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 55.8MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
70%|####### | 9.53M/13.6M [00:00<00:00, 99.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 91.7MB/s]
@@ -418,7 +418,7 @@ 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)
- 90.1984 90.1052 94.0109 89.9902 0.4134
+ 90.2577 90.1606 93.6899 90.0567 0.3853
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.082 seconds)
+ **Total running time of the script:** ( 1 minutes 6.518 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 8ffe122263..d5390b9963 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
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3498 120.3131 123.8381 119.5838 0.4810
+ 121.2431 121.1623 127.4660 119.8259 0.8353
@@ -469,7 +469,7 @@ 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 26.751 seconds)
+ **Total running time of the script:** ( 2 minutes 28.050 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 6808d1ecb2..4ae809b2b4 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 37.276 seconds)
+ **Total running time of the script:** ( 1 minutes 22.565 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 3c455c6eed..39bae1d3d7 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
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5411/132723 [00:00<00:02, 54100.89KB/s]
10%|9 | 12638/132723 [00:00<00:01, 64785.81KB/s]
15%|#4 | 19833/132723 [00:00<00:01, 68053.35KB/s]
21%|## | 27539/132723 [00:00<00:01, 71599.50KB/s]
26%|##6 | 34951/132723 [00:00<00:01, 72506.39KB/s]
32%|###2 | 42703/132723 [00:00<00:01, 74208.05KB/s]
38%|###7 | 50335/132723 [00:00<00:01, 74896.12KB/s]
44%|####3 | 57907/132723 [00:00<00:00, 75156.35KB/s]
49%|####9 | 65605/132723 [00:00<00:00, 75722.48KB/s]
55%|#####5 | 73563/132723 [00:01<00:00, 76911.93KB/s]
61%|######1 | 81534/132723 [00:01<00:00, 77766.15KB/s]
67%|######7 | 89507/132723 [00:01<00:00, 78361.45KB/s]
73%|#######3 | 97417/132723 [00:01<00:00, 78583.37KB/s]
79%|#######9 | 105357/132723 [00:01<00:00, 78824.03KB/s]
85%|########5 | 113376/132723 [00:01<00:00, 79232.74KB/s]
91%|#########
1| 121300/132723 [00:01<00:00, 72781.86KB/s]
97%|#########7| 129190/132723 [00:01<00:00, 74512.02KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74823.75KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 989/132723 [00:00<00:13, 9888.29KB/s]
3%|2 | 3888/132723 [00:00<00:06, 21123.09KB/s]
7%|6 | 9047/132723 [00:00<00:03, 35032.89KB/s]
13%|#3 | 17320/132723 [00:00<00:02, 53860.32KB/s]
19%|#9 | 25763/132723 [00:00<00:01, 64879.73KB/s]
26%|##5 | 34195/132723 [00:00<00:01, 71484.05KB/s]
32%|###2 | 42694/132723 [00:00<00:01, 75897.52KB/s]
39%|###8 | 51165/132723 [00:00<00:01, 78700.65KB/s]
45%|####4 | 59722/132723 [00:00<00:00, 80845.81KB/s]
51%|#####1 | 68227/132723 [00:01<00:00, 82137.56KB/s]
58%|#####7 | 76753/132723 [00:01<00:00, 83091.48KB/s]
64%|######4 | 85267/132723 [00:01<00:00, 83711.23KB/s]
71%|####### | 93830/132723 [00:01<00:00, 84290.46KB/s]
77%|#######7 | 102377/132723 [00:01<00:00, 84642.47KB/s]
84%|########3 | 110923/132723 [00:01<00:00, 84886.16KB/s]
90%|########9 | 1
19443/132723 [00:01<00:00, 84978.99KB/s]
96%|#########6| 127944/132723 [00:01<00:00, 84984.99KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75497.61KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 4.034 seconds)
+ **Total running time of the script:** ( 3 minutes 1.538 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 0b4b8b8435..84176d08e8 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:54.499** total execution time for **how_to_deploy_models** files:
+**12:41.659** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:14.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:15.476 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:04.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:01.538 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:26.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:37.276 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.565 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.082 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.518 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.494 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.325 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.723 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.243 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.289 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 de9ea66c11..a571d95c8f 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
@@ -472,7 +472,7 @@ 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.zipd2b7e00a-7fcd-45fd-bcd8-40f93d2e920c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7655373e-66f5-49e7-ab2b-a4d074a21974 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 d9e4692130..c59c17cb73 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
=================
-**00:47.201** total execution time for **how_to_extend_tvm** files:
+**00:47.923** 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``) | 00:43.763 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.417 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.402 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.447 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.052 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index b2ce82d34e..a74b65ec54 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7342us [7342us] (46.82%; 46.82%)
- FoldScaleAxis: 8339us [7us] (53.18%; 53.18%)
- FoldConstant: 8332us [1681us] (53.13%; 99.92%)
- InferType: 6651us [6651us] (42.41%; 79.82%)
+ InferType: 7185us [7185us] (46.20%; 46.20%)
+ FoldScaleAxis: 8366us [6us] (53.80%; 53.80%)
+ FoldConstant: 8360us [1739us] (53.76%; 99.93%)
+ InferType: 6621us [6621us] (42.58%; 79.20%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6713us [6713us] (45.18%; 45.18%)
- FoldScaleAxis: 8144us [5us] (54.82%; 54.82%)
- FoldConstant: 8139us [1661us] (54.78%; 99.94%)
- InferType: 6478us [6478us] (43.60%; 79.59%)
+ InferType: 6635us [6635us] (44.88%; 44.88%)
+ FoldScaleAxis: 8148us [4us] (55.12%; 55.12%)
+ FoldConstant: 8143us [1691us] (55.09%; 99.95%)
+ InferType: 6452us [6452us] (43.65%; 79.23%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index c0beff6ace..400681b777 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 35.155326 ms
+ Convolution: 33.681217 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 b208543cb0..939cf7b270 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.734499 ms
+ conv2d with tensor core: 11.884211 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 d2d10d135d..41ef848da8 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018960
- Baseline: 3.308917
+ Numpy running time: 0.019378
+ Baseline: 3.254845
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.306172
+ Opt1: 0.312445
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.342132
+ Opt2: 0.342553
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117598
+ Opt3: 0.117296
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109279
+ Opt4: 0.109728
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111656
+ Opt5: 0.111531
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146566
+ Opt6: 0.146557
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 e79c95497e..1203457612 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.689** total execution time for **how_to_optimize_operators** files:
+**00:34.641** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.193 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.145 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.422 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.439 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 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 63d3441d89..b9c9054b4a 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
=================
-**08:52.357** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:57.679** 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``) | 05:29.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:31.333 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.889 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.063 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:00.393 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.134 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.365 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.653 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.867 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.065 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.342 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.431 | 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 f610969114..136063a2f0 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
@@ -770,7 +770,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.358 ms
+ Execution time of this operator: 0.357 ms
@@ -1377,7 +1377,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 29.500 seconds)
+ **Total running time of the script:** ( 5 minutes 31.333 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 9626e9d2fd..c271ff3d36 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
@@ -643,7 +643,7 @@ 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)
- 7.8923 7.8930 7.8940 7.8899 0.0017
+ 7.8658 7.8691 7.8719 7.8564 0.0068
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.393 seconds)
+ **Total running time of the script:** ( 1 minutes 1.134 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 60bdc8f627..81451534eb 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
@@ -662,7 +662,7 @@ 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)
- 754.2901 753.4818 758.5127 750.8758 3.1697
+ 763.6102 762.2447 766.9282 761.6576 2.3584
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 31.889 seconds)
+ **Total running time of the script:** ( 1 minutes 32.063 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 1ed4444572..0444867a25 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
@@ -386,29 +386,408 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [256], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ {
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_2] = 0f32
+ compute_4[(cse_var_2 + 1)] = 0f32
+ compute_4[(cse_var_2 + 2)] = 0f32
+ compute_4[(cse_var_2 + 3)] = 0f32
+ compute_4[(cse_var_2 + 4)] = 0f32
+ compute_4[(cse_var_2 + 5)] = 0f32
+ compute_4[(cse_var_2 + 6)] = 0f32
+ compute_4[(cse_var_2 + 7)] = 0f32
+ compute_4[(cse_var_2 + 8)] = 0f32
+ compute_4[(cse_var_2 + 9)] = 0f32
+ compute_4[(cse_var_2 + 10)] = 0f32
+ compute_4[(cse_var_2 + 11)] = 0f32
+ compute_4[(cse_var_2 + 12)] = 0f32
+ compute_4[(cse_var_2 + 13)] = 0f32
+ compute_4[(cse_var_2 + 14)] = 0f32
+ compute_4[(cse_var_2 + 15)] = 0f32
+ compute_4[(cse_var_2 + 32)] = 0f32
+ compute_4[(cse_var_2 + 33)] = 0f32
+ compute_4[(cse_var_2 + 34)] = 0f32
+ compute_4[(cse_var_2 + 35)] = 0f32
+ compute_4[(cse_var_2 + 36)] = 0f32
+ compute_4[(cse_var_2 + 37)] = 0f32
+ compute_4[(cse_var_2 + 38)] = 0f32
+ compute_4[(cse_var_2 + 39)] = 0f32
+ compute_4[(cse_var_2 + 40)] = 0f32
+ compute_4[(cse_var_2 + 41)] = 0f32
+ compute_4[(cse_var_2 + 42)] = 0f32
+ compute_4[(cse_var_2 + 43)] = 0f32
+ compute_4[(cse_var_2 + 44)] = 0f32
+ compute_4[(cse_var_2 + 45)] = 0f32
+ compute_4[(cse_var_2 + 46)] = 0f32
+ compute_4[(cse_var_2 + 47)] = 0f32
+ compute_4[(cse_var_2 + 64)] = 0f32
+ compute_4[(cse_var_2 + 65)] = 0f32
+ compute_4[(cse_var_2 + 66)] = 0f32
+ compute_4[(cse_var_2 + 67)] = 0f32
+ compute_4[(cse_var_2 + 68)] = 0f32
+ compute_4[(cse_var_2 + 69)] = 0f32
+ compute_4[(cse_var_2 + 70)] = 0f32
+ compute_4[(cse_var_2 + 71)] = 0f32
+ compute_4[(cse_var_2 + 72)] = 0f32
+ compute_4[(cse_var_2 + 73)] = 0f32
+ compute_4[(cse_var_2 + 74)] = 0f32
+ compute_4[(cse_var_2 + 75)] = 0f32
+ compute_4[(cse_var_2 + 76)] = 0f32
+ compute_4[(cse_var_2 + 77)] = 0f32
+ compute_4[(cse_var_2 + 78)] = 0f32
+ compute_4[(cse_var_2 + 79)] = 0f32
+ compute_4[(cse_var_2 + 96)] = 0f32
+ compute_4[(cse_var_2 + 97)] = 0f32
+ compute_4[(cse_var_2 + 98)] = 0f32
+ compute_4[(cse_var_2 + 99)] = 0f32
+ compute_4[(cse_var_2 + 100)] = 0f32
+ compute_4[(cse_var_2 + 101)] = 0f32
+ compute_4[(cse_var_2 + 102)] = 0f32
+ compute_4[(cse_var_2 + 103)] = 0f32
+ compute_4[(cse_var_2 + 104)] = 0f32
+ compute_4[(cse_var_2 + 105)] = 0f32
+ compute_4[(cse_var_2 + 106)] = 0f32
+ compute_4[(cse_var_2 + 107)] = 0f32
+ compute_4[(cse_var_2 + 108)] = 0f32
+ compute_4[(cse_var_2 + 109)] = 0f32
+ compute_4[(cse_var_2 + 110)] = 0f32
+ compute_4[(cse_var_2 + 111)] = 0f32
+ compute_4[(cse_var_2 + 128)] = 0f32
+ compute_4[(cse_var_2 + 129)] = 0f32
+ compute_4[(cse_var_2 + 130)] = 0f32
+ compute_4[(cse_var_2 + 131)] = 0f32
+ compute_4[(cse_var_2 + 132)] = 0f32
+ compute_4[(cse_var_2 + 133)] = 0f32
+ compute_4[(cse_var_2 + 134)] = 0f32
+ compute_4[(cse_var_2 + 135)] = 0f32
+ compute_4[(cse_var_2 + 136)] = 0f32
+ compute_4[(cse_var_2 + 137)] = 0f32
+ compute_4[(cse_var_2 + 138)] = 0f32
+ compute_4[(cse_var_2 + 139)] = 0f32
+ compute_4[(cse_var_2 + 140)] = 0f32
+ compute_4[(cse_var_2 + 141)] = 0f32
+ compute_4[(cse_var_2 + 142)] = 0f32
+ compute_4[(cse_var_2 + 143)] = 0f32
+ compute_4[(cse_var_2 + 160)] = 0f32
+ compute_4[(cse_var_2 + 161)] = 0f32
+ compute_4[(cse_var_2 + 162)] = 0f32
+ compute_4[(cse_var_2 + 163)] = 0f32
+ compute_4[(cse_var_2 + 164)] = 0f32
+ compute_4[(cse_var_2 + 165)] = 0f32
+ compute_4[(cse_var_2 + 166)] = 0f32
+ compute_4[(cse_var_2 + 167)] = 0f32
+ compute_4[(cse_var_2 + 168)] = 0f32
+ compute_4[(cse_var_2 + 169)] = 0f32
+ compute_4[(cse_var_2 + 170)] = 0f32
+ compute_4[(cse_var_2 + 171)] = 0f32
+ compute_4[(cse_var_2 + 172)] = 0f32
+ compute_4[(cse_var_2 + 173)] = 0f32
+ compute_4[(cse_var_2 + 174)] = 0f32
+ compute_4[(cse_var_2 + 175)] = 0f32
+ compute_4[(cse_var_2 + 192)] = 0f32
+ compute_4[(cse_var_2 + 193)] = 0f32
+ compute_4[(cse_var_2 + 194)] = 0f32
+ compute_4[(cse_var_2 + 195)] = 0f32
+ compute_4[(cse_var_2 + 196)] = 0f32
+ compute_4[(cse_var_2 + 197)] = 0f32
+ compute_4[(cse_var_2 + 198)] = 0f32
+ compute_4[(cse_var_2 + 199)] = 0f32
+ compute_4[(cse_var_2 + 200)] = 0f32
+ compute_4[(cse_var_2 + 201)] = 0f32
+ compute_4[(cse_var_2 + 202)] = 0f32
+ compute_4[(cse_var_2 + 203)] = 0f32
+ compute_4[(cse_var_2 + 204)] = 0f32
+ compute_4[(cse_var_2 + 205)] = 0f32
+ compute_4[(cse_var_2 + 206)] = 0f32
+ compute_4[(cse_var_2 + 207)] = 0f32
+ compute_4[(cse_var_2 + 224)] = 0f32
+ compute_4[(cse_var_2 + 225)] = 0f32
+ compute_4[(cse_var_2 + 226)] = 0f32
+ compute_4[(cse_var_2 + 227)] = 0f32
+ compute_4[(cse_var_2 + 228)] = 0f32
+ compute_4[(cse_var_2 + 229)] = 0f32
+ compute_4[(cse_var_2 + 230)] = 0f32
+ compute_4[(cse_var_2 + 231)] = 0f32
+ compute_4[(cse_var_2 + 232)] = 0f32
+ compute_4[(cse_var_2 + 233)] = 0f32
+ compute_4[(cse_var_2 + 234)] = 0f32
+ compute_4[(cse_var_2 + 235)] = 0f32
+ compute_4[(cse_var_2 + 236)] = 0f32
+ compute_4[(cse_var_2 + 237)] = 0f32
+ compute_4[(cse_var_2 + 238)] = 0f32
+ compute_4[(cse_var_2 + 239)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ let cse_var_131: int32 = (elem_idx*16)
+ let cse_var_130: int32 = (cse_var_2 + 99)
+ let cse_var_129: int32 = (cse_var_2 + 98)
+ let cse_var_128: int32 = (cse_var_2 + 97)
+ let cse_var_127: int32 = (cse_var_2 + 96)
+ let cse_var_126: int32 = (cse_var_2 + 9)
+ let cse_var_125: int32 = (cse_var_2 + 8)
+ let cse_var_124: int32 = (cse_var_2 + 79)
+ let cse_var_123: int32 = (cse_var_2 + 78)
+ let cse_var_122: int32 = (cse_var_2 + 77)
+ let cse_var_121: int32 = (cse_var_2 + 76)
+ let cse_var_120: int32 = (cse_var_2 + 75)
+ let cse_var_119: int32 = (cse_var_2 + 74)
+ let cse_var_118: int32 = (cse_var_2 + 73)
+ let cse_var_117: int32 = (cse_var_2 + 72)
+ let cse_var_116: int32 = (cse_var_2 + 71)
+ let cse_var_115: int32 = (cse_var_2 + 70)
+ let cse_var_114: int32 = (cse_var_2 + 7)
+ let cse_var_113: int32 = (cse_var_2 + 69)
+ let cse_var_112: int32 = (cse_var_2 + 68)
+ let cse_var_111: int32 = (cse_var_2 + 67)
+ let cse_var_110: int32 = (cse_var_2 + 66)
+ let cse_var_109: int32 = (cse_var_2 + 65)
+ let cse_var_108: int32 = (cse_var_2 + 64)
+ let cse_var_107: int32 = (cse_var_2 + 6)
+ let cse_var_106: int32 = (cse_var_2 + 5)
+ let cse_var_105: int32 = (cse_var_2 + 47)
+ let cse_var_104: int32 = (cse_var_2 + 46)
+ let cse_var_103: int32 = (cse_var_2 + 45)
+ let cse_var_102: int32 = (cse_var_2 + 44)
+ let cse_var_101: int32 = (cse_var_2 + 43)
+ let cse_var_100: int32 = (cse_var_2 + 42)
+ let cse_var_99: int32 = (cse_var_2 + 41)
+ let cse_var_98: int32 = (cse_var_2 + 40)
+ let cse_var_97: int32 = (cse_var_2 + 4)
+ let cse_var_96: int32 = (cse_var_2 + 39)
+ let cse_var_95: int32 = (cse_var_2 + 38)
+ let cse_var_94: int32 = (cse_var_2 + 37)
+ let cse_var_93: int32 = (cse_var_2 + 36)
+ let cse_var_92: int32 = (cse_var_2 + 35)
+ let cse_var_91: int32 = (cse_var_2 + 34)
+ let cse_var_90: int32 = (cse_var_2 + 33)
+ let cse_var_89: int32 = (cse_var_2 + 32)
+ let cse_var_88: int32 = (cse_var_2 + 3)
+ let cse_var_87: int32 = (cse_var_2 + 239)
+ let cse_var_86: int32 = (cse_var_2 + 238)
+ let cse_var_85: int32 = (cse_var_2 + 237)
+ let cse_var_84: int32 = (cse_var_2 + 236)
+ let cse_var_83: int32 = (cse_var_2 + 235)
+ let cse_var_82: int32 = (cse_var_2 + 234)
+ let cse_var_81: int32 = (cse_var_2 + 233)
+ let cse_var_80: int32 = (cse_var_2 + 232)
+ let cse_var_79: int32 = (cse_var_2 + 231)
+ let cse_var_78: int32 = (cse_var_2 + 230)
+ let cse_var_77: int32 = (cse_var_2 + 229)
+ let cse_var_76: int32 = (cse_var_2 + 228)
+ let cse_var_75: int32 = (cse_var_2 + 227)
+ let cse_var_74: int32 = (cse_var_2 + 226)
+ let cse_var_73: int32 = (cse_var_2 + 225)
+ let cse_var_72: int32 = (cse_var_2 + 224)
+ let cse_var_71: int32 = (cse_var_2 + 207)
+ let cse_var_70: int32 = (cse_var_2 + 206)
+ let cse_var_69: int32 = (cse_var_2 + 205)
+ let cse_var_68: int32 = (cse_var_2 + 204)
+ let cse_var_67: int32 = (cse_var_2 + 203)
+ let cse_var_66: int32 = (cse_var_2 + 202)
+ let cse_var_65: int32 = (cse_var_2 + 201)
+ let cse_var_64: int32 = (cse_var_2 + 200)
+ let cse_var_63: int32 = (cse_var_2 + 2)
+ let cse_var_62: int32 = (cse_var_2 + 199)
+ let cse_var_61: int32 = (cse_var_2 + 198)
+ let cse_var_60: int32 = (cse_var_2 + 197)
+ let cse_var_59: int32 = (cse_var_2 + 196)
+ let cse_var_58: int32 = (cse_var_2 + 195)
+ let cse_var_57: int32 = (cse_var_2 + 194)
+ let cse_var_56: int32 = (cse_var_2 + 193)
+ let cse_var_55: int32 = (cse_var_2 + 192)
+ let cse_var_54: int32 = (cse_var_2 + 175)
+ let cse_var_53: int32 = (cse_var_2 + 174)
+ let cse_var_52: int32 = (cse_var_2 + 173)
+ let cse_var_51: int32 = (cse_var_2 + 172)
+ let cse_var_50: int32 = (cse_var_2 + 171)
+ let cse_var_49: int32 = (cse_var_2 + 170)
+ let cse_var_48: int32 = (cse_var_2 + 169)
+ let cse_var_47: int32 = (cse_var_2 + 168)
+ let cse_var_46: int32 = (cse_var_2 + 167)
+ let cse_var_45: int32 = (cse_var_2 + 166)
+ let cse_var_44: int32 = (cse_var_2 + 165)
+ let cse_var_43: int32 = (cse_var_2 + 164)
+ let cse_var_42: int32 = (cse_var_2 + 163)
+ let cse_var_41: int32 = (cse_var_2 + 162)
+ let cse_var_40: int32 = (cse_var_2 + 161)
+ let cse_var_39: int32 = (cse_var_2 + 160)
+ let cse_var_38: int32 = (cse_var_2 + 15)
+ let cse_var_37: int32 = (cse_var_2 + 143)
+ let cse_var_36: int32 = (cse_var_2 + 142)
+ let cse_var_35: int32 = (cse_var_2 + 141)
+ let cse_var_34: int32 = (cse_var_2 + 140)
+ let cse_var_33: int32 = (cse_var_2 + 14)
+ let cse_var_32: int32 = (cse_var_2 + 139)
+ let cse_var_31: int32 = (cse_var_2 + 138)
+ let cse_var_30: int32 = (cse_var_2 + 137)
+ let cse_var_29: int32 = (cse_var_2 + 136)
+ let cse_var_28: int32 = (cse_var_2 + 135)
+ let cse_var_27: int32 = (cse_var_2 + 134)
+ let cse_var_26: int32 = (cse_var_2 + 133)
+ let cse_var_25: int32 = (cse_var_2 + 132)
+ let cse_var_24: int32 = (cse_var_2 + 131)
+ let cse_var_23: int32 = (cse_var_2 + 130)
+ let cse_var_22: int32 = (cse_var_2 + 13)
+ let cse_var_21: int32 = (cse_var_2 + 129)
+ let cse_var_20: int32 = (cse_var_2 + 128)
+ let cse_var_19: int32 = (cse_var_2 + 12)
+ let cse_var_18: int32 = (cse_var_2 + 111)
+ let cse_var_17: int32 = (cse_var_2 + 110)
+ let cse_var_16: int32 = (cse_var_2 + 11)
+ let cse_var_15: int32 = (cse_var_2 + 109)
+ let cse_var_14: int32 = (cse_var_2 + 108)
+ let cse_var_13: int32 = (cse_var_2 + 107)
+ let cse_var_12: int32 = (cse_var_2 + 106)
+ let cse_var_11: int32 = (cse_var_2 + 105)
+ let cse_var_10: int32 = (cse_var_2 + 104)
+ let cse_var_9: int32 = (cse_var_2 + 103)
+ let cse_var_8: int32 = (cse_var_2 + 102)
+ let cse_var_7: int32 = (cse_var_2 + 101)
+ let cse_var_6: int32 = (cse_var_2 + 100)
+ let cse_var_5: int32 = (cse_var_2 + 10)
+ let cse_var_4: int32 = (cse_var_2 + 1)
+ let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048))
+ {
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_132, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -464,7 +843,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.571 ms
+ Execution time of this operator: 2.742 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 fce6ac05ad..57741335e9 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:31.427** total execution time for **how_to_tune_with_autotvm** files:
+**00:27.982** 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``) | 00:31.390 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:27.947 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index a35e7090ff..efb974c4c1 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
@@ -387,7 +387,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4779333
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5088019
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,8 +510,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8480223
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1002025
+ No: 3 GFLOPS: 210.89/210.89 result: MeasureResult(costs=(0.0010977583070175439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1155447959899902, timestamp=1669070470.1798065) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9009485
+ No: 4 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -633,8 +634,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('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', 0), ('unroll_explicit', 1)],None,6411547
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8004212
+ No: 5 GFLOPS: 5.40/210.89 result: MeasureResult(costs=(0.0429052085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1623175144195557, timestamp=1669070474.4587286) [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2914259
+ No: 6 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -756,8 +758,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,271683
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4973955
+ No: 7 GFLOPS: 64.79/210.89 result: MeasureResult(costs=(0.0035728547142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2142045497894287, timestamp=1669070476.026077) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619975
+ No: 8 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -879,8 +882,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5580492
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1254493
+ No: 9 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1002,9 +1005,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6801912
- No: 7 GFLOPS: 39.89/39.89 result: MeasureResult(costs=(0.005803903074074074,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4635977745056152, timestamp=1669070424.1746726) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5293308
- No: 8 GFLOPS: 0.00/39.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9845277
+ No: 10 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,8 +1128,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6991549
- No: 9 GFLOPS: 0.00/39.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3985151
+ No: 11 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,9 +1251,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3744829
- No: 10 GFLOPS: 102.24/102.24 result: MeasureResult(costs=(0.0022642005492957747,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5608654022216797, timestamp=1669070425.9557855) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3527802
- No: 11 GFLOPS: 0.00/102.24 result: Traceback (most recent call last):
+ 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, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10209975
+ No: 12 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1373,8 +1374,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7661390
- No: 12 GFLOPS: 0.00/102.24 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6657683
+ No: 13 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1496,9 +1497,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6546196
- No: 13 GFLOPS: 154.28/154.28 result: MeasureResult(costs=(0.0015005428249999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.069350719451904, timestamp=1669070431.234598) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8534342
- No: 14 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2118363
+ No: 14 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1620,8 +1620,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6119448
- No: 15 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1917007
+ No: 15 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1743,10 +1743,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,741093
- No: 16 GFLOPS: 1.06/154.28 result: MeasureResult(costs=(0.21919738749999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6823055744171143, timestamp=1669070434.4402187) [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1166206
- No: 17 GFLOPS: 44.35/154.28 result: MeasureResult(costs=(0.00521973455,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1060850620269775, timestamp=1669070435.733415) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5488704
- No: 18 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8925918
+ No: 16 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1868,8 +1866,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6351488
- No: 19 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4734059
+ No: 17 GFLOPS: 306.99/306.99 result: MeasureResult(costs=(0.0007540923517241379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.548452138900757, timestamp=1669070479.167015) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
+ No: 18 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1991,8 +1990,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5106738
- No: 20 GFLOPS: 649.89/649.89 result: MeasureResult(costs=(0.00035621784326710814,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3048932552337646, timestamp=1669070436.6920576) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1230823
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1952737
+ No: 19 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 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:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 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:453
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 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:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 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:453
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934185
+ No: 20 GFLOPS: 39.90/306.99 result: MeasureResult(costs=(0.005802182888888888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9944984912872314, timestamp=1669070479.8508644) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422558
@@ -2047,9 +2169,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1230823
+ [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
Finish loading 20 records
- Time cost of this operator: 0.000670
+ Time cost of this operator: 0.001050
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 d21d9f39a1..75c32cc8d2 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
@@ -327,10 +327,10 @@ 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 311.4 98.726 (1, 2, 10, 10, 3) 2 1 [311.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.037 0.963 (1, 6, 10, 10) 1 1 [3.037]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.312 (1, 1, 10, 10, 3) 1 1 [0.983]
- Total_time - 315.42 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.621 (1, 2, 10, 10, 3) 2 1 [313.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.235 1.019 (1, 6, 10, 10) 1 1 [3.235]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.145 0.361 (1, 1, 10, 10, 3) 1 1 [1.145]
+ Total_time - 317.58 - - - - -
@@ -394,10 +394,10 @@ 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 103.8 97.257 (1, 6, 10, 10, 1) 2 1 [103.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.658 (1, 6, 10, 10) 1 1 [1.77]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.157 1.085 (1, 1, 10, 10, 3) 1 1 [1.157]
- Total_time - 106.727 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.6 98.123 (1, 6, 10, 10, 1) 2 1 [136.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.273 (1, 6, 10, 10) 1 1 [1.772]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.605 (1, 3, 10, 10, 1) 1 1 [0.842]
+ Total_time - 139.213 - - - - -
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 ffa44ec360..a76746a182 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
@@ -109,7 +109,7 @@ 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]
58%|#####8 | 2.00M/3.42M [00:00<00:00, 20.9MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 22.6MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
96%|#########5| 3.28M/3.42M [00:00<00:00, 34.2MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 35.0MB/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.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.761 seconds)
+ **Total running time of the script:** ( 1 minutes 2.963 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 613582f9cb..88cb8c7e86 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpe3629tr1/images/random'
+ '/tmp/tmp59_o2aft/images/random'
@@ -316,7 +316,7 @@ 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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [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], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpe3629tr1/images/target contains 8144 images
- /tmp/tmpe3629tr1/images/random contains 5000 images
+ /tmp/tmp59_o2aft/images/target contains 8144 images
+ /tmp/tmp59_o2aft/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2602 - accuracy: 0.9182 - val_loss: 0.1256 - val_accuracy: 0.9513 - 47s/epoch - 144ms/step
+ 328/328 - 46s - loss: 0.2390 - accuracy: 0.9168 - val_loss: 0.1144 - val_accuracy: 0.9603 - 46s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1059 - accuracy: 0.9631 - val_loss: 0.1065 - val_accuracy: 0.9660 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.1015 - accuracy: 0.9616 - val_loss: 0.0897 - val_accuracy: 0.9683 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0699 - accuracy: 0.9733 - val_loss: 0.1301 - val_accuracy: 0.9668 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0620 - accuracy: 0.9769 - val_loss: 0.1089 - val_accuracy: 0.9641 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7f0173419050>
+ <keras.callbacks.History object at 0x7ff34e46da90>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 30.659 seconds)
+ **Total running time of the script:** ( 4 minutes 4.174 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 af6345aa3a..06b40d1232 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:34.351** total execution time for **how_to_work_with_microtvm** files:
+**06:09.111** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:30.659 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:04.174 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.761 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.963 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.743 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.170 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.421 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.031 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.764 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.770 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 8e4f805282..31a27b19ae 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
=================
-**00:44.375** total execution time for **how_to_work_with_relay** files:
+**00:43.665** 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``) | 00:32.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.924 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.204 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.115 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.619 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index d752087450..cc6f4dd22f 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f014c330830>
+ <function my_cuda_math_rule at 0x7ff34cf0cef0>
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 0c3582e9dd..7fedb8483d 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
=================
-**00:07.952** total execution time for **how_to_work_with_schedules** files:
+**00:06.967** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.492 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.558 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.130 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.081 | 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_reduction.py` (``reduction.py``) | 00:00.568 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.549 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.048 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 4c997588d2..6d367aa1f5 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp0c98d7ly/input0.cc'\nsource_filename = \"/tmp/tmp0c98d7ly/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp7gcvbn52/input0.cc'\nsource_filename = \"/tmp/tmp7gcvbn52/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 20d814d748..6833ff79e3 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
=================
-**00:26.172** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.497** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.166 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.490 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index e60ff2aeb5..f4607b096e 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ 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 28.72s!
+ resnet18_v1 inference graph built in 29.30s!
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 4e82dda886..1a1a13138e 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ 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 19.51s!
+ yolov3-tiny inference graph built in 19.73s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index cc0db1a14a..db5a0f788f 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
=================
-**01:40.543** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.137** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.852 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.095 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.691 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.042 | 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 c24764fdf2..9ecd5c5cc0 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
=================
-**00:03.140** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.128** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.700 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.689 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.440 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.438 | 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 0295b8c9da..13cc883c33 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
=================
-**00:00.798** total execution time for **topic_vta_tutorials** files:
+**00:00.757** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.435 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.399 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.363 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.358 | 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 33c45fc480..56a646ceb6 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ .T
+
@@ -325,7 +332,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 97.717 ms
+ Execution time of this operator: 93.093 ms
@@ -443,7 +450,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.022 seconds)
+ **Total running time of the script:** ( 1 minutes 33.730 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 9f8f57b117..d75c67a003 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 11.09/11.09 result: MeasureResult(costs=(0.0241983496,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5648739337921143, timestamp=1669069044.6963928) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
- No: 2 GFLOPS: 11.16/11.16 result: MeasureResult(costs=(0.024052841,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.57857346534729, timestamp=1669069045.2889998) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
- No: 3 GFLOPS: 10.74/11.16 result: MeasureResult(costs=(0.0249896626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6110608577728271, timestamp=1669069046.6144114) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 4 GFLOPS: 0.49/11.16 result: MeasureResult(costs=(0.545164375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.892568349838257, timestamp=1669069055.530979) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 5 GFLOPS: 0.50/11.16 result: MeasureResult(costs=(0.5354741759999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.735774755477905, timestamp=1669069064.5135775) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
- No: 6 GFLOPS: 12.22/12.22 result: MeasureResult(costs=(0.0219627194,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5442948341369629, timestamp=1669069065.8125002) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
- No: 7 GFLOPS: 9.13/12.22 result: MeasureResult(costs=(0.029392543,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.749305248260498, timestamp=1669069067.1873536) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
- No: 8 GFLOPS: 12.94/12.94 result: MeasureResult(costs=(0.020745803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6637840270996094, timestamp=1669069067.7427788) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
- No: 9 GFLOPS: 1.63/12.94 result: MeasureResult(costs=(0.1644089454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7509829998016357, timestamp=1669069070.641762) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 10 GFLOPS: 3.25/12.94 result: MeasureResult(costs=(0.082471217,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5046789646148682, timestamp=1669069072.1626863) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+ No: 1 GFLOPS: 11.69/11.69 result: MeasureResult(costs=(0.0229614498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.550915002822876, timestamp=1669069093.9232368) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
+ No: 2 GFLOPS: 0.50/11.69 result: MeasureResult(costs=(0.5346515846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.731043100357056, timestamp=1669069102.682373) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+ No: 3 GFLOPS: 1.55/11.69 result: MeasureResult(costs=(0.1727075166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9166369438171387, timestamp=1669069106.362152) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 4 GFLOPS: 8.24/11.69 result: MeasureResult(costs=(0.032565906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.653590202331543, timestamp=1669069107.798683) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 5 GFLOPS: 1.69/11.69 result: MeasureResult(costs=(0.1589572562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.681199312210083, timestamp=1669069110.6333787) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 6 GFLOPS: 12.19/12.19 result: MeasureResult(costs=(0.022028911800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5019567012786865, timestamp=1669069111.910717) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 7 GFLOPS: 13.38/13.38 result: MeasureResult(costs=(0.020057455600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4962158203125, timestamp=1669069112.4011486) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+ No: 8 GFLOPS: 12.85/13.38 result: MeasureResult(costs=(0.020884536399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5327770709991455, timestamp=1669069112.9469588) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+ No: 9 GFLOPS: 0.50/13.38 result: MeasureResult(costs=(0.5390465264000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.724902391433716, timestamp=1669069121.7890291) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 10 GFLOPS: 3.21/13.38 result: MeasureResult(costs=(0.08349640439999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4820079803466797, timestamp=1669069123.291861) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 89ace92697..9be6a17e2c 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 516.8022287300005, 'median': 516.7068863999987, 'std': 3.7927704287204276}
+ {'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
@@ -554,31 +554,31 @@ 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: 7.08/ 16.81 GFLOPS | Progress: (4/20) | 7.13 s
[Task 1/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (8/20) | 10.44 s
[Task 1/25] Current/Best: 14.49/ 21.60 GFLOPS | Progress: (12/20) | 12.74 s
[Task 1/25] Current/Best: 16.06/ 23.22 GFLOPS | Progress: (16/20) | 14.68 s
[Task 1/25] Current/Best: 6.43/ 23.22 GFLOPS | Progress: (20/20) | 17.74 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.33/ 20.90 GFLOPS | Progress: (4/20) | 3.04 s
[Task 2/25] Current/Best: 11.29/ 20.90 GFLOPS | Progress: (8/20) | 4.18 s
[Task 2/25] Current/Best: 11.83/ 20.90 GFLOPS | Progress: (12/20) | 5.57 s
[Task 2/25] Current/Best: 5.62/ 20.90 GFLOPS | Progress: (16/20) | 6.92 s
[Task 2/25] Current/Best: 16.64/ 20.90 GFLOPS | Progress: (20/20) | 8.56 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 13.97/ 13.97 GFLOPS | Progress: (4/20) | 3.96 s
[Task 3/25] Current/Best: 19.73/ 20.05 GFLOPS | Progress: (8/20) | 6.60 s
[Task 3/25] Current/Best: 11.52/ 20.05 GFLOPS | Progress: (12/20) | 9.47 s
[Task 3/25] Current/Best: 16.50/ 21.98 GFLOPS | Progress: (16/20) | 11.32 s
[Task 3/25] Current/Best: 17.77/ 21.98 GFLOPS | Progress: (20/20) | 13.76 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.05/ 22.30 GFLOPS | Progress: (4/20) | 4.52 s
[Task 4/25] Current/Best: 11.05/ 22.30 GFLOPS | Progress: (8/20) | 8.82 s
[Task 4/25] Current/Best: 19.91/ 22.30 GFLOPS | Progress: (12/20) | 10.36 s
[Task 4/25] Current/Best: 17.10/ 22.30 GFLOPS | Progress: (16/20) | 13.45 s
[Task 4/25] Current/Best: 19.40/ 22.30 GFLOPS | Progress: (20/20) | 21.86 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 14.28/ 17.02 GFLOPS | Progress: (4/20) | 3.51 s
[Task 5/25] Current/Best: 16.24/ 17.02 GFLOPS | Progress: (8/20) | 5.17 s
[Task 5/25] Current/Best: 5.73/ 19.65 GFLOPS | Progress: (12/20) | 6.68 s
[Task 5/25] Current/Best: 4.83/ 19.65 GFLOPS | Progress: (16/20) | 8.46 s
[Task 5/25] Current/Best: 5.52/ 19.65 GFLOPS | Progress: (20/20) | 10.64 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.72/ 17.61 GFLOPS | Progress: (4/20) | 4.09 s
[Task 6/25] Current/Best: 9.12/ 20.30 GFLOPS | Progress: (8/20) | 7.20 s
[Task 6/25] Current/Best: 4.54/ 20.30 GFLOPS | Progress: (12/20) | 9.78 s
[Task 6/25] Current/Best: 10.12/ 20.30 GFLOPS | Progress: (16/20) | 12.10 s
[Task 6/25] Current/Best: 4.76/ 20.30 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 3.52 s
[Task 7/25] Current/Best: 15.41/ 17.35 GFLOPS | Progress: (8/20) | 5.88 s
[Task 7/25] Current/Best: 8.75/ 17.35 GFLOPS | Progress: (12/20) | 7.98 s
[Task 7/25] Current/Best: 10.47/ 17.35 GFLOPS | Progress: (16/20) | 10.77 s
[Task 7/25] Current/Best: 17.86/ 18.20 GFLOPS | Progress: (20/20) | 13.06 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.47/ 12.80 GFLOPS | Progress: (4/20) | 6.15 s
[Task 8/25] Current/Best: 11.03/ 16.19 GFLOPS | Progress: (8/20) | 10.72 s
[Task 8/25] Current/Best: 14.34/ 17.23 GFLOPS | Progress: (12/20) | 16.81 s
[Task 8/25] Current/Best: 14.79/ 17.23 GFLOPS | Progress: (16/20) | 19.21 s
[Task 8/25] Current/Best: 2.59/ 17.23 GFLOPS | Progress: (20/20) | 22.14 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.38/ 20.24 GFLOPS | Progress: (4/20) | 2.98 s
[Task 9/25] Current/Best: 14.82/ 20.24 GFLOPS | Progress: (8/20) | 4.39 s
[Task 9/25] Current/Best: 11.85/ 20.24 GFLOPS | Progress: (12/20) | 9.53 s
[Task 9/25] Current/Best: 17.75/ 20.24 GFLOPS | Progress: (16/20) | 14.65 s
[Task 9/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (20/20) | 17.14 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 6.43/ 14.58 GFLOPS | Progress: (4/20) | 4.14 s
[Task 10/25] Current/Best: 14.89/ 14.89 GFLOPS | Progress: (8/20) | 6.51 s
[Task 10/25] Current/Best: 13.96/ 14.89 GFLOPS | Progress: (12/20) | 8.25 s
[Task 10/25] Current/Best: 7.00/ 20.57 GFLOPS | Progress: (16/20) | 9.84 s
[Task 10/25] Current/Best: 4.90/ 20.57 GFLOPS | Progress: (20/20) | 12.12 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 16.65/ 16.84 GFLOPS | Progress: (4/20) | 4.44 s
[Task 11/25] Current/Best: 10.91/ 22.18 GFLOPS | Progress: (8/20) | 7.86 s
[Task 11/25] Current/Best: 23.38/ 23.38 GFLOPS | Progress: (12/20) | 11.35 s
[Task 11/25] Current/Best: 15.33/ 23.38 GFLOPS | Progress: (16/20) | 13.79 s
[Task 11/25] Current/Best: 11.21/ 23.38 GFLOPS | Progress: (20/20) | 16.11 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.38/ 13.38 GFLOPS | Progress: (4/20) | 4.68 s
[Task 12/25] Current/Best: 6.65/ 14.19 GFLOPS | Progress: (8/20) | 8.20 s
[Task 12/25] Current/Best: 4.50/ 14.19 GFLOPS | Progress: (12/20) | 12.35 s
[Task 12/25] Current/Best: 11.95/ 17.74 GFLOPS | Progress: (16/20) | 17.16 s
[Task 12/25] Current/Best: 15.96/ 17.74 GFLOPS | Progress: (20/20) | 19.75 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (4/20) | 5.48 s
[Task 13/25] Current/Best: 12.06/ 18.27 GFLOPS | Progress: (8/20) | 7.33 s
[Task 13/25] Current/Best: 12.22/ 18.27 GFLOPS | Progress: (12/20) | 10.22 s
[Task 13/25] Current/Best: 12.15/ 18.27 GFLOPS | Progress: (16/20) | 13.09 s
[Task 13/25] Current/Best: 10.86/ 18.27 GFLOPS | Progress: (20/20) | 16.90 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.38/ 14.38 GFLOPS | Progress: (4/20) | 4.02 s
[Task 14/25] Current/Best: 13.07/ 18.46 GFLOPS | Progress: (8/20) | 8.15 s
[Task 14/25] Current/Best: 17.57/ 18.46 GFLOPS | Progress: (12/20) | 15.09 s
[Task 14/25] Current/Best: 11.24/ 18.46 GFLOPS | Progress: (16/20) | 18.02 s
[Task 14/25] Current/Best: 10.31/ 18.46 GFLOPS | Progress: (20/20) | 22.58 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.82/ 13.82 GFLOPS | Progress: (4/20) | 3.89 s
[Task 15/25] Current/Best: 8.25/ 13.82 GFLOPS | Progress: (8/20) | 10.56 s
[Task 15/25] Current/Best: 13.95/ 14.43 GFLOPS | Progress: (12/20) | 12.47 s
[Task 15/25] Current/Best: 20.04/ 20.04 GFLOPS | Progress: (16/20) | 15.41 s Done.
-
[Task 15/25] Current/Best: 21.68/ 21.68 GFLOPS | Progress: (20/20) | 22.09 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.89/ 18.89 GFLOPS | Progress: (4/20) | 2.98 s
[Task 16/25] Current/Best: 11.49/ 18.89 GFLOPS | Progress: (8/20) | 5.33 s
[Task 16/25] Current/Best: 11.58/ 18.89 GFLOPS | Progress: (12/20) | 7.97 s
[Task 16/25] Current/Best: 6.39/ 18.89 GFLOPS | Progress: (16/20) | 9.81 s
[Task 16/25] Current/Best: 9.64/ 18.89 GFLOPS | Progress: (20/20) | 12.85 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (4/20) | 3.49 s
[Task 17/25] Current/Best: 7.10/ 22.58 GFLOPS | Progress: (8/20) | 5.58 s
[Task 17/25] Current/Best: 7.01/ 22.58 GFLOPS | Progress: (12/20) | 7.54 s
[Task 17/25] Current/Best: 16.49/ 22.58 GFLOPS | Progress: (16/20) | 9.72 s
[Task 17/25] Current/Best: 15.27/ 22.58 GFLOPS | Progress: (20/20) | 13.45 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.56/ 17.56 GFLOPS | Progress: (4/20) | 3.78 s
[Task 18/25] Current/Best: 16.98/ 17.56 GFLOPS | Progress: (8/20) | 11.51 s
[Task 18/25] Current/Best: 14.08/ 17.92 GFLOPS | Progress: (12/20) | 13.23 s
[Task 18/25] Current/Best: 7.57/ 17.92 GFLOPS | Progress: (16/20) | 17.77 s
[Task 18/25] Current/Best: 3.09/ 17.92 GFLOPS | Progress: (20/20) | 21.71 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 14.80/ 21.37 GFLOPS | Progress: (4/20) | 3.51 s
[Task 19/25] Current/Best: 17.00/ 21.37 GFLOPS | Progress: (8/20) | 7.93 s
[Task 19/25] Current/Best: 10.22/ 21.37 GFLOPS | Progress: (12/20) | 10.17 s
[Task 19/25] Current/Best: 17.57/ 21.37 GFLOPS | Progress: (16/20) | 12.14 s
[Task 19/25] Current/Best: 8.84/ 21.37 GFLOPS | Progress: (20/20) | 16.96 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.29/ 10.29 GFLOPS | Progress: (4/20) | 5.91 s
[Task 20/25] Current/Best: 9.58/ 18.51 GFLOPS | Progress: (8/20) | 7.90 s
[Task 20/25] Current/Best: 10.67/ 19.50 GFLOPS | Progress: (12/20) | 10.60 s
[Task 20/25] Current/Best: 18.25/ 20.33 GFLOPS | Progress: (16/20) | 13.25 s
[Task 20/25] Current/Best: 9.64/ 20.33 GFLOPS | Progress: (20/20) | 14.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (4/20) | 3.90 s
[Task 21/25] Current/Best: 5.20/ 20.73 GFLOPS | Progress: (8/20) | 6.87 s
[Task 21/25] Current/Best: 10.59/ 20.73 GFLOPS | Progress: (12/20) | 8.71 s
[Task 21/25] Current/Best: 15.46/ 20.73 GFLOPS | Progress: (16/20) | 10.89 s
[Task 21/25] Current/Best: 8.37/ 20.73 GFLOPS | Progress: (20/20)
| 15.07 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (4/20) | 3.02 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.02/ 18.79 GFLOPS | Progress: (4/20) | 6.98 s
[Task 1/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (8/20) | 11.43 s
[Task 1/25] Current/Best: 9.25/ 23.48 GFLOPS | Progress: (12/20) | 13.62 s
[Task 1/25] Current/Best: 17.21/ 23.48 GFLOPS | Progress: (16/20) | 16.07 s
[Task 1/25] Current/Best: 15.13/ 23.48 GFLOPS | Progress: (20/20) | 19.10 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.20/ 17.44 GFLOPS | Progress: (4/20) | 3.34 s
[Task 2/25] Current/Best: 14.45/ 17.44 GFLOPS | Progress: (8/20) | 4.54 s
[Task 2/25] Current/Best: 7.49/ 22.85 GFLOPS | Progress: (12/20) | 7.23 s
[Task 2/25] Current/Best: 21.95/ 22.85 GFLOPS | Progress: (16/20) | 8.47 s
[Task 2/25] Current/Best: 12.94/ 22.85 GFLOPS | Progress: (20/20) | 9.89 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.59/ 19.55 GFLOPS | Progress: (4/20) | 3.62 s
[Task 3/25] Current/Best: 10.19/ 19.55 GFLOPS | Progress: (8/20) | 5.39 s
[Task 3/25] Current/Best: 9.87/ 23.40 GFLOPS | Progress: (12/20) | 7.45 s
[Task 3/25] Current/Best: 14.59/ 23.92 GFLOPS | Progress: (16/20) | 9.06 s
[Task 3/25] Current/Best: 14.21/ 23.92 GFLOPS | Progress: (20/20) | 11.41 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.61/ 19.51 GFLOPS | Progress: (4/20) | 3.44 s
[Task 4/25] Current/Best: 12.42/ 19.51 GFLOPS | Progress: (8/20) | 5.20 s
[Task 4/25] Current/Best: 13.90/ 19.51 GFLOPS | Progress: (12/20) | 9.47 s
[Task 4/25] Current/Best: 15.62/ 19.51 GFLOPS | Progress: (16/20) | 17.50 s
[Task 4/25] Current/Best: 15.48/ 19.51 GFLOPS | Progress: (20/20) | 28.36 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 5/25] Current/Best: 19.33/ 23.48 GFLOPS | Progress: (4/20) | 3.62 s
[Task 5/25] Current/Best: 5.28/ 23.48 GFLOPS | Progress: (8/20) | 5.46 s
[Task 5/25] Current/Best: 10.84/ 23.48 GFLOPS | Progress: (12/20) | 7.00 s
[Task 5/25] Current/Best: 17.85/ 23.48 GFLOPS | Progress: (16/20) | 8.88 s
[Task 5/25] Current/Best: 15.50/ 23.48 GFLOPS | Progress: (20/20) | 10.89 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.04/ 19.54 GFLOPS | Progress: (4/20) | 3.43 s
[Task 6/25] Current/Best: 8.14/ 19.54 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 5.86/ 19.54 GFLOPS | Progress: (12/20) | 8.38 s
[Task 6/25] Current/Best: 3.19/ 19.54 GFLOPS | Progress: (16/20) | 11.57 s
[Task 6/25] Current/Best: 11.94/ 19.54 GFLOPS | Progress: (20/20) | 15.23 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.76/ 12.37 GFLOPS | Progress: (4/20) | 4.25 s
[Task 7/25] Current/Best: 14.38/ 16.97 GFLOPS | Progress: (8/20) | 7.34 s
[Task 7/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 9.52 s
[Task 7/25] Current/Best: 18.18/ 19.05 GFLOPS | Progress: (16/20) | 12.42 s
[Task 7/25] Current/Best: 12.08/ 19.05 GFLOPS | Progress: (20/20) | 14.78 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.24/ 10.24 GFLOPS | Progress: (4/20) | 13.36 s
[Task 8/25] Current/Best: 3.19/ 14.15 GFLOPS | Progress: (8/20) | 20.47 s
[Task 8/25] Current/Best: 7.72/ 20.42 GFLOPS | Progress: (12/20) | 24.06 s
[Task 8/25] Current/Best: 7.60/ 20.42 GFLOPS | Progress: (16/20) | 30.65 s
[Task 8/25] Current/Best: 13.17/ 20.42 GFLOPS | Progress: (20/20) | 34.73 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 4.90/ 13.76 GFLOPS | Progress: (4/20) | 7.58 s
[Task 9/25] Current/Best: 12.83/ 13.91 GFLOPS | Progress: (8/20) | 13.01 s
[Task 9/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (12/20) | 21.23 s
[Task 9/25] Current/Best: 18.55/ 22.86 GFLOPS | Progress: (16/20) | 24.05 s
[Task 9/25] Current/Best: 17.66/ 22.86 GFLOPS | Progress: (20
/20) | 34.82 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (4/20) | 4.12 s
[Task 10/25] Current/Best: 8.93/ 17.93 GFLOPS | Progress: (8/20) | 5.88 s
[Task 10/25] Current/Best: 16.89/ 17.93 GFLOPS | Progress: (12/20) | 7.58 s
[Task 10/25] Current/Best: 18.07/ 20.24 GFLOPS | Progress: (16/20) | 9.20 s
[Task 10/25] Current/Best: 6.70/ 20.24 GFLOPS | Progress: (20/20) | 11.15 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.11/ 12.69 GFLOPS | Progress: (4/20) | 3.72 s
[Task 11/25] Current/Best: 8.33/ 21.59 GFLOPS | Progress: (8/20) | 6.60 s
[Task 11/25] Current/Best: 7.72/ 23.63 GFLOPS | Progress: (12/20) | 9.20 s
[Task 11/25] Current/Best: 7.79/ 23.63 GFLOPS | Progress: (16/20) | 11.85 s
[Task 11/25] Current/Best: 7.12/ 23.63 GFLOPS | Progress: (20/20) | 13.96 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.44/ 12.43 GFLOPS | Progress: (4/20) | 4.98 s
[Task 12/25] Current/Best: 7.29/ 16.16 GFLOPS | Progress: (8/20) | 9.93 s
[Task 12/25] Current/Best: 9.17/ 18.54 GFLOPS | Progress: (12/20) | 14.06 s
[Task 12/25] Current/Best: 11.69/ 18.54 GFLOPS | Progress: (16/20) | 18.09 s
[Task 12/25] Current/Best: 8.27/ 18.54 GFLOPS | Progress: (20/20) | 21.96 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 6.03/ 12.06 GFLOPS | Progress: (4/20) | 4.63 s
[Task 13/25] Current/Best: 9.98/ 12.06 GFLOPS | Progress: (8/20) | 7.53 s
[Task 13/25] Current/Best: 17.34/ 17.48 GFLOPS | Progress: (12/20) | 10.26 s
[Task 13/25] Current/Best: 7.00/ 18.85 GFLOPS | Progress: (16/20) | 12.87 s
[Task 13/25] Current/Best: 1.57/ 19.19 GFLOPS | Progress: (20/20) | 17.32 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 3.23 s
[Task 14/25] Current/Best: 16.98/ 20.07 GFLOPS | Progress: (8/20) | 5.26 s
[Task 14/25] Current/Best: 10.49/ 20.07 GFLOPS | Progress: (12/20) | 11.04 s
[Task 14/25] Current/Best: 15.40/ 20.07 GFLOPS | Progress: (16/20) | 12.95 s
[Task 14/25] Current/Best: 4.84/ 20.07 GFLOPS | Progress: (20/20) | 15.20 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.13/ 19.20 GFLOPS | Progress: (4/20) | 5.62 s
[Task 15/25] Current/Best: 8.56/ 19.20 GFLOPS | Progress: (8/20) | 8.88 s
[Task 15/25] Current/Best: 11.80/ 19.20 GFLOPS | Progress: (12/20) | 12.71 s
[Task 15/25] Current/Best: 12.40/ 19.20 GFLOPS | Progress: (16/20) | 14.23 s
[Task 15/25] Current/Best: 19.01/ 19.20 GFLOPS | Progress: (20/20) | 20.36 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.27/ 16.36 GFLOPS | Progress: (4/20) | 3.61 s
[Task 16/25] Current/Best: 5.38/ 19.49 GFLOPS | Progress: (8/20) | 5.20 s Done.
Done.
-
[Task 22/25] Current/Best: 18.29/ 21.35 GFLOPS | Progress: (8/20) | 4.65 s
[Task 22/25] Current/Best: 18.33/ 21.35 GFLOPS | Progress: (12/20) | 6.08 s
[Task 22/25] Current/Best: 11.05/ 21.35 GFLOPS | Progress: (16/20) | 8.38 s
[Task 22/25] Current/Best: 11.10/ 21.35 GFLOPS | Progress: (20/20) | 10.31 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 1.55/ 14.72 GFLOPS | Progress: (4/20) | 5.53 s
[Task 23/25] Current/Best: 9.48/ 21.76 GFLOPS | Progress: (8/20) | 8.33 s
[Task 23/25] Current/Best: 3.08/ 21.76 GFLOPS | Progress: (12/20) | 11.54 s
[Task 23/25] Current/Best: 8.45/ 21.76 GFLOPS | Progress: (16/20) | 14.54 s
[Task 23/25] Current/Best: 20.25/ 21.76 GFLOPS | Progress: (20/20) | 18.45 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.55/ 4.55 GFLOPS | Progress: (4/20) | 12.23 s
[Task 24/25] Current/Best: 4.02/ 5.32 GFLOPS | Progress: (8/20) | 14.92 s
[Task 24/25] Current/Best: 2.52/ 9.45 GFLOPS | Progress: (12/20) | 25.66 s
[Task 24/25] Current/Best: 3.00/ 9.45 GFLOPS | Progress: (16/20) | 36.36 s
[Task 24/25] Current/Best: 6.43/ 9.45 GFLOPS | Progress: (20/20) | 46.84 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 7.10/ 7.29 GFLOPS | Progress: (4/20) | 8.37 s
[Task 25/25] Current/Best: 7.89/ 9.57 GFLOPS | Progress: (8/20) | 19.08 s
[Task 25/25] Current/Best: 5.88/ 9.57 GFLOPS | Progress: (12/20) | 20.84 s
[Task 25/25] Current/Best: 2.84/ 9.57 GFLOPS | Progress: (16/20) | 31.54 s
[Task 25/25] Current/Best: 7.41/ 9.57 GFLOPS | Progress: (20/20) | 42.32 s
+
[Task 16/25] Current/Best: 17.93/ 19.49 GFLOPS | Progress: (12/20) | 7.27 s
[Task 16/25] Current/Best: 13.82/ 19.49 GFLOPS | Progress: (16/20) | 8.72 s
[Task 16/25] Current/Best: 12.03/ 20.68 GFLOPS | Progress: (20/20) | 10.37 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.68/ 20.05 GFLOPS | Progress: (4/20) | 3.37 s
[Task 17/25] Current/Best: 11.62/ 20.05 GFLOPS | Progress: (8/20) | 7.16 s
[Task 17/25] Current/Best: 6.16/ 22.46 GFLOPS | Progress: (12/20) | 10.55 s
[Task 17/25] Current/Best: 14.59/ 23.13 GFLOPS | Progress: (16/20) | 12.38 s
[Task 17/25] Current/Best: 10.42/ 23.13 GFLOPS | Progress: (20/20) | 14.50 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (4/20) | 3.47 s
[Task 18/25] Current/Best: 3.11/ 21.21 GFLOPS | Progress: (8/20) | 5.68 s
[Task 18/25] Current/Best: 14.80/ 21.21 GFLOPS | Progress: (12/20) | 7.84 s
[Task 18/25] Current/Best: 10.90/ 21.21 GFLOPS | Progress: (16/20) | 11.63 s
[Task 18/25] Current/Best: 15.51/ 21.21 GFLOPS | Progress: (20/20) | 13.85 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 5.31 s
[Task 19/25] Current/Best: 10.28/ 21.30 GFLOPS | Progress: (8/20) | 10.31 s
[Task 19/25] Current/Best: 17.77/ 21.30 GFLOPS | Progress: (12/20) | 13.93 s
[Task 19/25] Current/Best: 11.87/ 21.30 GFLOPS | Progress: (16/20) | 16.63 s
[Task 19/25] Current/Best: 10.07/ 21.30 GFLOPS | Progress: (20/20) | 18.59 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.30/ 16.52 GFLOPS | Progress: (4/20) | 3.39 s
[Task 20/25] Current/Best: 15.42/ 17.94 GFLOPS | Progress: (8/20) | 5.39 s
[Task 20/25] Current/Best: 15.57/ 18.82 GFLOPS | Progress: (12/20) | 8.01 s
[Task 20/25] Current/Best: 16.59/ 18.82 GFLOPS | Progress: (16/20) | 10.84 s
[Task 20/25] Current/Best: 2.24/ 18.82 GFLOPS | Progress: (20/20) | 13.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.22/ 11.16 GFLOPS | Progress: (4/20) | 4.28 s
[Task 21/25] Current/Best: 8.84/ 14.51 GFLOPS | Progress: (8/20) | 6.79 s
[Task 21/25] Current/Best: 16.30/ 16.30 GFLOPS | Progress: (12/20) | 9.53 s Done.
+
[Task 21/25] Current/Best: 11.45/ 20.16 GFLOPS | Progress: (16/20) | 11.91 s
[Task 21/25] Current/Best: 9.53/ 20.16 GFLOPS | Progress: (20/20) | 14.02 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.60/ 11.59 GFLOPS | Progress: (4/20) | 3.54 s
[Task 22/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.39 s
[Task 22/25] Current/Best: 4.46/ 17.28 GFLOPS | Progress: (12/20) | 6.87 s
[Task 22/25] Current/Best: 16.47/ 17.28 GFLOPS | Progress: (16/20) | 8.19 s
[Task 22/25] Current/Best: 11.96/ 17.28 GFLOPS | Progress: (20/20) | 10.24 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (4/20) | 4.67 s
[Task 23/25] Current/Best: 13.42/ 16.38 GFLOPS | Progress: (8/20) | 7.15 s
[Task 23/25] Current/Best: 9.81/ 16.38 GFLOPS | Progress: (12/20) | 10.47 s
[Task 23/25] Current/Best: 9.80/ 18.98 GFLOPS | Progress: (16/20) | 12.89 s
[Task 23/25] Current/Best: 8.33/ 18.98 GFLOPS | Progress: (20/20) | 15.21 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.90/ 8.24 GFLOPS | Progress: (4/20) | 12.27 s
[Task 24/25] Current/Best: 9.93/ 9.93 GFLOPS | Progress: (8/20) | 22.97 s
[Task 24/25] Current/Best: 3.74/ 9.93 GFLOPS | Progress: (12/20) | 33.71 s
[Task 24/25] Current/Best: 3.94/ 9.93 GFLOPS | Progress: (16/20) | 44.41 s
[Task 24/25] Current/Best: 1.71/ 9.93 GFLOPS | Progress: (20/20) | 54.91 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 3.02/ 3.02 GFLOPS | Progress: (4/20) | 12.98 s
[Task 25/25] Current/Best: 3.04/ 9.07 GFLOPS | Progress: (8/20) | 18.78 s
[Task 25/25] Current/Best: 7.75/ 9.07 GFLOPS | Progress: (12/20) | 19.82 s
[Task 25/25] Current/Best: 1.54/ 9.07 GFLOPS | Progress: (16/20) | 30.55 s
[Task 25/25] Current/Best: 1.55/ 9.29 GFLOPS | Progress: (20/20) | 35.59 s
@@ -675,7 +675,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 420.22287448999805, 'median': 418.76673499999697, 'std': 3.0618863299389014}
- unoptimized: {'mean': 516.8022287300005, 'median': 516.7068863999987, 'std': 3.7927704287204276}
+ optimized: {'mean': 416.1014501600016, 'median': 415.50952905000713, 'std': 4.321109686634458}
+ unoptimized: {'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 10.288 seconds)
+ **Total running time of the script:** ( 11 minutes 28.828 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 7e6f88edbc..5bd5893e5a 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.257e-07 secs/op
+ 1.25e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 60810e2d7a..b2e47ba4c5 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x12be1250)), stage(b, placeholder(b, 0x70eb700)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x8a10b00)), stage(b, placeholder(b, 0x2399d1b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 90a85a4c85..bea1da69ea 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:39.951** total execution time for **tutorial** files:
+**15:11.609** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:10.288 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:28.828 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.022 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.730 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.982 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.170 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.596 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:33.794 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:32.521 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.784 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.591 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.355 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.760 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.761 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.183 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4e7bef7c06..c22e762e2d 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000008
+ naive: 0.000007
@@ -448,7 +448,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000024
+ vector: 0.000046
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [n: int32], [stride: int32], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.635360000222135e-06 1.0
- naive 7.793600000000001e-06 1.0207246285405354
- parallel 7.0009e-06 0.9169050313012516
- vector 2.4484700000000003e-05 3.2067512205433237
+ numpy 7.813590000296245e-06 1.0
+ naive 6.7472e-06 0.8635211215003842
+ parallel 6.9564e-06 0.8902949860097925
+ vector 4.60098e-05 5.888432845626093
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.020652
+ Numpy running time: 0.018505
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.321090
+ none: 3.251925
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.310711
+ blocking: 0.306264
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.334473
+ vectorization: 0.341208
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.140346
+ loop permutation: 0.119167
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.127151
+ array packing: 0.110721
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.118909
+ block caching: 0.111180
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.150095
+ parallelization: 0.146938
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3210900419 1.0
- blocking 0.31071136 0.0935570418386614
- vectorization 0.33447345679999996 0.10071195076922614
- loop permutation 0.14034593560000003 0.04225899744642513
- array packing 0.1271508498 0.0382858784904419
- block caching 0.1189094664 0.03580434884324056
- parallelization 0.1500954634 0.04519463835859451
+ none 3.2519253935 1.0
+ blocking 0.30626426110000005 0.09417936269760858
+ vectorization 0.3412077699 0.10492484562592103
+ loop permutation 0.1191673078 0.036645154294804395
+ array packing 0.1107214522 0.034047968142600006
+ block caching 0.11117954749999999 0.03418883708778419
+ parallelization 0.1469377231 0.04518483830954469
@@ -1652,11 +1652,6 @@ 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 0.982 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index fe0781ff64..d832c0dcd9 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-3ccc3009a6a4f3cce4cbe9e24e6fa18cc1247f87
+545f8dc927d4dc9fb1394c67c681ea40ec16db8d
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index fb6b204653..b12b4f1596 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 12.933 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.166 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 6852fe7b67..7a05342014 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<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 955ms/step
+1/1 [==============================] - 1s 973ms/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 a6c5f870d2..1205ebefdb 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7c4f1e49-41ad-45a2-8733-c0e70509ab0b 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.zip6b750afc-1efa-4bcf-8409-efe2e0573a2b 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 314d942496..35b57c890f 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,14 +448,12 @@ 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]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 44.9MB/s]
- 27%|##7 | 11.3M/41.5M [00:00<00:00, 48.4MB/s]
- 38%|###8 | 16.0M/41.5M [00:00<00:00, 44.6MB/s]
- 49%|####8 | 20.3M/41.5M [00:00<00:00, 40.9MB/s]
- 58%|#####8 | 24.2M/41.5M [00:00<00:00, 32.6MB/s]
- 79%|#######8 | 32.6M/41.5M [00:00<00:00, 47.2MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 40.0MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 41.0MB/s]
+ 19%|#8 | 7.79M/41.5M [00:00<00:00, 81.7MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 65.7MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
+ 69%|######8 | 28.5M/41.5M [00:00<00:00, 60.8MB/s]
+ 83%|########2 | 34.4M/41.5M [00:00<00:00, 50.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 63.2MB/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 ccb0309ff0..15aedda7ee 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,11 @@ 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]
- 31%|### | 13.7M/44.7M [00:00<00:00, 144MB/s]
- 61%|######1 | 27.4M/44.7M [00:00<00:00, 114MB/s]
- 86%|########6 | 38.6M/44.7M [00:00<00:00, 108MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+ 19%|#9 | 8.53M/44.7M [00:00<00:00, 89.4MB/s]
+ 49%|####8 | 21.7M/44.7M [00:00<00:00, 118MB/s]
+ 74%|#######3 | 32.9M/44.7M [00:00<00:00, 99.4MB/s]
+100%|#########9| 44.7M/44.7M [00:00<00:00, 108MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/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 34f8a7c295..14dcefa05b 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 11.466 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.047 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 4125d91626..9e1d0d7bd3 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:45.291</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:43.043</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:12.933</p></td>
+<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>01:12.047</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:11.466</p></td>
+<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>01:10.166</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>00:46.245</p></td>
+<td><p>00:46.739</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.370</p></td>
+<td><p>00:32.094</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:28.419</p></td>
+<td><p>00:28.559</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.187</p></td>
+<td><p>00:26.503</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>00:25.403</p></td>
+<td><p>00:24.827</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>00:22.558</p></td>
+<td><p>00:22.476</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>00:17.341</p></td>
+<td><p>00:17.246</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>00:02.370</p></td>
+<td><p>00:02.386</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 46e840d08e..7f57cca972 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5776 15.5712 15.6789 15.4907 0.0566
+ 16.2368 16.1416 17.2407 15.8435 0.3782
</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 616921888d..526b95f9e0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,24 +453,21 @@ 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 | 8.12M/170M [00:00<00:02, 65.8MB/s]
- 8%|8 | 14.4M/170M [00:00<00:02, 61.7MB/s]
- 15%|#4 | 24.8M/170M [00:00<00:01, 81.2MB/s]
- 20%|## | 34.1M/170M [00:00<00:02, 59.0MB/s]
- 25%|##5 | 42.8M/170M [00:00<00:01, 67.7MB/s]
- 29%|##9 | 50.1M/170M [00:00<00:02, 56.0MB/s]
- 38%|###7 | 63.9M/170M [00:00<00:01, 77.3MB/s]
- 43%|####3 | 73.3M/170M [00:01<00:01, 82.7MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:00, 101MB/s]
- 58%|#####8 | 98.5M/170M [00:01<00:00, 103MB/s]
- 64%|######4 | 109M/170M [00:01<00:00, 90.2MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 94.1MB/s]
- 76%|#######6 | 130M/170M [00:01<00:00, 92.9MB/s]
- 82%|########1 | 139M/170M [00:01<00:00, 90.9MB/s]
- 88%|########7 | 149M/170M [00:01<00:00, 94.6MB/s]
- 93%|#########3| 158M/170M [00:01<00:00, 96.4MB/s]
- 99%|#########8| 168M/170M [00:02<00:00, 96.5MB/s]
-100%|##########| 170M/170M [00:02<00:00, 85.9MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 74.6MB/s]
+ 13%|#2 | 21.8M/170M [00:00<00:01, 114MB/s]
+ 19%|#9 | 32.8M/170M [00:00<00:01, 85.1MB/s]
+ 27%|##7 | 46.3M/170M [00:00<00:01, 94.5MB/s]
+ 37%|###6 | 62.3M/170M [00:00<00:01, 112MB/s]
+ 43%|####3 | 73.5M/170M [00:00<00:00, 113MB/s]
+ 50%|####9 | 84.7M/170M [00:00<00:00, 109MB/s]
+ 56%|#####6 | 95.3M/170M [00:00<00:00, 106MB/s]
+ 62%|######2 | 106M/170M [00:01<00:00, 102MB/s]
+ 68%|######8 | 116M/170M [00:01<00:00, 103MB/s]
+ 74%|#######4 | 126M/170M [00:01<00:00, 80.5MB/s]
+ 85%|########5 | 145M/170M [00:01<00:00, 108MB/s]
+ 92%|#########1| 156M/170M [00:01<00:00, 105MB/s]
+ 98%|#########8| 167M/170M [00:01<00:00, 105MB/s]
+100%|##########| 170M/170M [00:01<00:00, 102MB/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=& [...]
@@ -568,7 +565,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 14.529 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 15.476 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 d5a118594f..29a8638c66 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ 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, 40.7MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 55.8MB/s]
+ 70%|####### | 9.53M/13.6M [00:00<00:00, 99.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 91.7MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ 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)
- 90.1984 90.1052 94.0109 89.9902 0.4134
+ 90.2577 90.1606 93.6899 90.0567 0.3853
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.082 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.518 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 54d013f30e..b0d09679e2 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3498 120.3131 123.8381 119.5838 0.4810
+ 121.2431 121.1623 127.4660 119.8259 0.8353
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ 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 26.751 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.050 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 28a88afac6..7ad85744d9 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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 37.276 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.565 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 c8f91cb5e3..d3149c6249 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,24 +462,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5411/132723 [00:00<00:02, 54100.89KB/s]
- 10%|9 | 12638/132723 [00:00<00:01, 64785.81KB/s]
- 15%|#4 | 19833/132723 [00:00<00:01, 68053.35KB/s]
- 21%|## | 27539/132723 [00:00<00:01, 71599.50KB/s]
- 26%|##6 | 34951/132723 [00:00<00:01, 72506.39KB/s]
- 32%|###2 | 42703/132723 [00:00<00:01, 74208.05KB/s]
- 38%|###7 | 50335/132723 [00:00<00:01, 74896.12KB/s]
- 44%|####3 | 57907/132723 [00:00<00:00, 75156.35KB/s]
- 49%|####9 | 65605/132723 [00:00<00:00, 75722.48KB/s]
- 55%|#####5 | 73563/132723 [00:01<00:00, 76911.93KB/s]
- 61%|######1 | 81534/132723 [00:01<00:00, 77766.15KB/s]
- 67%|######7 | 89507/132723 [00:01<00:00, 78361.45KB/s]
- 73%|#######3 | 97417/132723 [00:01<00:00, 78583.37KB/s]
- 79%|#######9 | 105357/132723 [00:01<00:00, 78824.03KB/s]
- 85%|########5 | 113376/132723 [00:01<00:00, 79232.74KB/s]
- 91%|#########1| 121300/132723 [00:01<00:00, 72781.86KB/s]
- 97%|#########7| 129190/132723 [00:01<00:00, 74512.02KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74823.75KB/s]
+ 1%| | 989/132723 [00:00<00:13, 9888.29KB/s]
+ 3%|2 | 3888/132723 [00:00<00:06, 21123.09KB/s]
+ 7%|6 | 9047/132723 [00:00<00:03, 35032.89KB/s]
+ 13%|#3 | 17320/132723 [00:00<00:02, 53860.32KB/s]
+ 19%|#9 | 25763/132723 [00:00<00:01, 64879.73KB/s]
+ 26%|##5 | 34195/132723 [00:00<00:01, 71484.05KB/s]
+ 32%|###2 | 42694/132723 [00:00<00:01, 75897.52KB/s]
+ 39%|###8 | 51165/132723 [00:00<00:01, 78700.65KB/s]
+ 45%|####4 | 59722/132723 [00:00<00:00, 80845.81KB/s]
+ 51%|#####1 | 68227/132723 [00:01<00:00, 82137.56KB/s]
+ 58%|#####7 | 76753/132723 [00:01<00:00, 83091.48KB/s]
+ 64%|######4 | 85267/132723 [00:01<00:00, 83711.23KB/s]
+ 71%|####### | 93830/132723 [00:01<00:00, 84290.46KB/s]
+ 77%|#######7 | 102377/132723 [00:01<00:00, 84642.47KB/s]
+ 84%|########3 | 110923/132723 [00:01<00:00, 84886.16KB/s]
+ 90%|########9 | 119443/132723 [00:01<00:00, 84978.99KB/s]
+ 96%|#########6| 127944/132723 [00:01<00:00, 84984.99KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 75497.61KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -518,7 +518,7 @@ 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 4.034 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 1.538 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 cff017a00e..6e1aa96623 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>12:54.499</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:41.659</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:14.529</p></td>
+<td><p>03:15.476</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:04.034</p></td>
+<td><p>03:01.538</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>02:26.751</p></td>
+<td><p>02:28.050</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>01:37.276</p></td>
+<td><p>01:22.565</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:06.082</p></td>
+<td><p>01:06.518</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:35.250</p></td>
+<td><p>00:36.494</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.325</p></td>
+<td><p>00:25.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.243</p></td>
+<td><p>00:25.289</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 35e9558b56..7b77debb24 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zipd2b7e00a-7fcd-45fd-bcd8-40f93d2e920c 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.zip7655373e-66f5-49e7-ab2b-a4d074a21974 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 37ab583c6c..76f313a4b2 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:47.201</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:47.923</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</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>00:43.763</p></td>
+<td><p>00:44.417</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>00:02.402</p></td>
+<td><p>00:02.447</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>00:01.027</p></td>
+<td><p>00:01.052</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 529d534ee1..1b22e6ab46 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 7342us [7342us] (46.82%; 46.82%)
-FoldScaleAxis: 8339us [7us] (53.18%; 53.18%)
- FoldConstant: 8332us [1681us] (53.13%; 99.92%)
- InferType: 6651us [6651us] (42.41%; 79.82%)
+InferType: 7185us [7185us] (46.20%; 46.20%)
+FoldScaleAxis: 8366us [6us] (53.80%; 53.80%)
+ FoldConstant: 8360us [1739us] (53.76%; 99.93%)
+ InferType: 6621us [6621us] (42.58%; 79.20%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ 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: 6713us [6713us] (45.18%; 45.18%)
-FoldScaleAxis: 8144us [5us] (54.82%; 54.82%)
- FoldConstant: 8139us [1661us] (54.78%; 99.94%)
- InferType: 6478us [6478us] (43.60%; 79.59%)
+InferType: 6635us [6635us] (44.88%; 44.88%)
+FoldScaleAxis: 8148us [4us] (55.12%; 55.12%)
+ FoldConstant: 8143us [1691us] (55.09%; 99.95%)
+ InferType: 6452us [6452us] (43.65%; 79.23%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 7f30e47945..ff0be5c608 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 35.155326 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.681217 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 8280466552..9e1da1a766 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ 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: 12.734499 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.884211 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 286b603f9a..cef6101619 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.018960
-Baseline: 3.308917
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019378
+Baseline: 3.254845
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.306172
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.312445
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.342132
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.342553
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.117598
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117296
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.109279
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109728
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.111656
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111531
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146566
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146557
</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 7dba0e7aad..6f84252a0e 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.689</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.641</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</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>00:32.193</p></td>
+<td><p>00:32.145</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>00:01.422</p></td>
+<td><p>00:01.439</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>00:01.074</p></td>
+<td><p>00:01.057</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 31856d79e0..b169ad76b5 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>08:52.357</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:57.679</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</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>05:29.500</p></td>
+<td><p>05:31.333</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>01:31.889</p></td>
+<td><p>01:32.063</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>01:00.393</p></td>
+<td><p>01:01.134</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>00:27.365</p></td>
+<td><p>00:29.653</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>00:11.867</p></td>
+<td><p>00:12.065</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>00:11.342</p></td>
+<td><p>00:11.431</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 4d1cb7a6bc..44b5d91805 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
@@ -1016,7 +1016,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.358 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.357 ms
</pre></div>
</div>
</div>
@@ -1579,7 +1579,7 @@ 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> ( 5 minutes 29.500 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 31.333 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 5be59b3957..32c3aafba4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
- 7.8923 7.8930 7.8940 7.8899 0.0017
+ 7.8658 7.8691 7.8719 7.8564 0.0068
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 0.393 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.134 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 e6be05949e..18ae7c6135 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
- 754.2901 753.4818 758.5127 750.8758 3.1697
+ 763.6102 762.2447 766.9282 761.6576 2.3584
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ 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 31.889 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.063 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 d959deab34..5c7ce6b272 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,29 +632,408 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [256], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ {
+ compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_2] = 0f32
+ compute_4[(cse_var_2 + 1)] = 0f32
+ compute_4[(cse_var_2 + 2)] = 0f32
+ compute_4[(cse_var_2 + 3)] = 0f32
+ compute_4[(cse_var_2 + 4)] = 0f32
+ compute_4[(cse_var_2 + 5)] = 0f32
+ compute_4[(cse_var_2 + 6)] = 0f32
+ compute_4[(cse_var_2 + 7)] = 0f32
+ compute_4[(cse_var_2 + 8)] = 0f32
+ compute_4[(cse_var_2 + 9)] = 0f32
+ compute_4[(cse_var_2 + 10)] = 0f32
+ compute_4[(cse_var_2 + 11)] = 0f32
+ compute_4[(cse_var_2 + 12)] = 0f32
+ compute_4[(cse_var_2 + 13)] = 0f32
+ compute_4[(cse_var_2 + 14)] = 0f32
+ compute_4[(cse_var_2 + 15)] = 0f32
+ compute_4[(cse_var_2 + 32)] = 0f32
+ compute_4[(cse_var_2 + 33)] = 0f32
+ compute_4[(cse_var_2 + 34)] = 0f32
+ compute_4[(cse_var_2 + 35)] = 0f32
+ compute_4[(cse_var_2 + 36)] = 0f32
+ compute_4[(cse_var_2 + 37)] = 0f32
+ compute_4[(cse_var_2 + 38)] = 0f32
+ compute_4[(cse_var_2 + 39)] = 0f32
+ compute_4[(cse_var_2 + 40)] = 0f32
+ compute_4[(cse_var_2 + 41)] = 0f32
+ compute_4[(cse_var_2 + 42)] = 0f32
+ compute_4[(cse_var_2 + 43)] = 0f32
+ compute_4[(cse_var_2 + 44)] = 0f32
+ compute_4[(cse_var_2 + 45)] = 0f32
+ compute_4[(cse_var_2 + 46)] = 0f32
+ compute_4[(cse_var_2 + 47)] = 0f32
+ compute_4[(cse_var_2 + 64)] = 0f32
+ compute_4[(cse_var_2 + 65)] = 0f32
+ compute_4[(cse_var_2 + 66)] = 0f32
+ compute_4[(cse_var_2 + 67)] = 0f32
+ compute_4[(cse_var_2 + 68)] = 0f32
+ compute_4[(cse_var_2 + 69)] = 0f32
+ compute_4[(cse_var_2 + 70)] = 0f32
+ compute_4[(cse_var_2 + 71)] = 0f32
+ compute_4[(cse_var_2 + 72)] = 0f32
+ compute_4[(cse_var_2 + 73)] = 0f32
+ compute_4[(cse_var_2 + 74)] = 0f32
+ compute_4[(cse_var_2 + 75)] = 0f32
+ compute_4[(cse_var_2 + 76)] = 0f32
+ compute_4[(cse_var_2 + 77)] = 0f32
+ compute_4[(cse_var_2 + 78)] = 0f32
+ compute_4[(cse_var_2 + 79)] = 0f32
+ compute_4[(cse_var_2 + 96)] = 0f32
+ compute_4[(cse_var_2 + 97)] = 0f32
+ compute_4[(cse_var_2 + 98)] = 0f32
+ compute_4[(cse_var_2 + 99)] = 0f32
+ compute_4[(cse_var_2 + 100)] = 0f32
+ compute_4[(cse_var_2 + 101)] = 0f32
+ compute_4[(cse_var_2 + 102)] = 0f32
+ compute_4[(cse_var_2 + 103)] = 0f32
+ compute_4[(cse_var_2 + 104)] = 0f32
+ compute_4[(cse_var_2 + 105)] = 0f32
+ compute_4[(cse_var_2 + 106)] = 0f32
+ compute_4[(cse_var_2 + 107)] = 0f32
+ compute_4[(cse_var_2 + 108)] = 0f32
+ compute_4[(cse_var_2 + 109)] = 0f32
+ compute_4[(cse_var_2 + 110)] = 0f32
+ compute_4[(cse_var_2 + 111)] = 0f32
+ compute_4[(cse_var_2 + 128)] = 0f32
+ compute_4[(cse_var_2 + 129)] = 0f32
+ compute_4[(cse_var_2 + 130)] = 0f32
+ compute_4[(cse_var_2 + 131)] = 0f32
+ compute_4[(cse_var_2 + 132)] = 0f32
+ compute_4[(cse_var_2 + 133)] = 0f32
+ compute_4[(cse_var_2 + 134)] = 0f32
+ compute_4[(cse_var_2 + 135)] = 0f32
+ compute_4[(cse_var_2 + 136)] = 0f32
+ compute_4[(cse_var_2 + 137)] = 0f32
+ compute_4[(cse_var_2 + 138)] = 0f32
+ compute_4[(cse_var_2 + 139)] = 0f32
+ compute_4[(cse_var_2 + 140)] = 0f32
+ compute_4[(cse_var_2 + 141)] = 0f32
+ compute_4[(cse_var_2 + 142)] = 0f32
+ compute_4[(cse_var_2 + 143)] = 0f32
+ compute_4[(cse_var_2 + 160)] = 0f32
+ compute_4[(cse_var_2 + 161)] = 0f32
+ compute_4[(cse_var_2 + 162)] = 0f32
+ compute_4[(cse_var_2 + 163)] = 0f32
+ compute_4[(cse_var_2 + 164)] = 0f32
+ compute_4[(cse_var_2 + 165)] = 0f32
+ compute_4[(cse_var_2 + 166)] = 0f32
+ compute_4[(cse_var_2 + 167)] = 0f32
+ compute_4[(cse_var_2 + 168)] = 0f32
+ compute_4[(cse_var_2 + 169)] = 0f32
+ compute_4[(cse_var_2 + 170)] = 0f32
+ compute_4[(cse_var_2 + 171)] = 0f32
+ compute_4[(cse_var_2 + 172)] = 0f32
+ compute_4[(cse_var_2 + 173)] = 0f32
+ compute_4[(cse_var_2 + 174)] = 0f32
+ compute_4[(cse_var_2 + 175)] = 0f32
+ compute_4[(cse_var_2 + 192)] = 0f32
+ compute_4[(cse_var_2 + 193)] = 0f32
+ compute_4[(cse_var_2 + 194)] = 0f32
+ compute_4[(cse_var_2 + 195)] = 0f32
+ compute_4[(cse_var_2 + 196)] = 0f32
+ compute_4[(cse_var_2 + 197)] = 0f32
+ compute_4[(cse_var_2 + 198)] = 0f32
+ compute_4[(cse_var_2 + 199)] = 0f32
+ compute_4[(cse_var_2 + 200)] = 0f32
+ compute_4[(cse_var_2 + 201)] = 0f32
+ compute_4[(cse_var_2 + 202)] = 0f32
+ compute_4[(cse_var_2 + 203)] = 0f32
+ compute_4[(cse_var_2 + 204)] = 0f32
+ compute_4[(cse_var_2 + 205)] = 0f32
+ compute_4[(cse_var_2 + 206)] = 0f32
+ compute_4[(cse_var_2 + 207)] = 0f32
+ compute_4[(cse_var_2 + 224)] = 0f32
+ compute_4[(cse_var_2 + 225)] = 0f32
+ compute_4[(cse_var_2 + 226)] = 0f32
+ compute_4[(cse_var_2 + 227)] = 0f32
+ compute_4[(cse_var_2 + 228)] = 0f32
+ compute_4[(cse_var_2 + 229)] = 0f32
+ compute_4[(cse_var_2 + 230)] = 0f32
+ compute_4[(cse_var_2 + 231)] = 0f32
+ compute_4[(cse_var_2 + 232)] = 0f32
+ compute_4[(cse_var_2 + 233)] = 0f32
+ compute_4[(cse_var_2 + 234)] = 0f32
+ compute_4[(cse_var_2 + 235)] = 0f32
+ compute_4[(cse_var_2 + 236)] = 0f32
+ compute_4[(cse_var_2 + 237)] = 0f32
+ compute_4[(cse_var_2 + 238)] = 0f32
+ compute_4[(cse_var_2 + 239)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ let cse_var_131: int32 = (elem_idx*16)
+ let cse_var_130: int32 = (cse_var_2 + 99)
+ let cse_var_129: int32 = (cse_var_2 + 98)
+ let cse_var_128: int32 = (cse_var_2 + 97)
+ let cse_var_127: int32 = (cse_var_2 + 96)
+ let cse_var_126: int32 = (cse_var_2 + 9)
+ let cse_var_125: int32 = (cse_var_2 + 8)
+ let cse_var_124: int32 = (cse_var_2 + 79)
+ let cse_var_123: int32 = (cse_var_2 + 78)
+ let cse_var_122: int32 = (cse_var_2 + 77)
+ let cse_var_121: int32 = (cse_var_2 + 76)
+ let cse_var_120: int32 = (cse_var_2 + 75)
+ let cse_var_119: int32 = (cse_var_2 + 74)
+ let cse_var_118: int32 = (cse_var_2 + 73)
+ let cse_var_117: int32 = (cse_var_2 + 72)
+ let cse_var_116: int32 = (cse_var_2 + 71)
+ let cse_var_115: int32 = (cse_var_2 + 70)
+ let cse_var_114: int32 = (cse_var_2 + 7)
+ let cse_var_113: int32 = (cse_var_2 + 69)
+ let cse_var_112: int32 = (cse_var_2 + 68)
+ let cse_var_111: int32 = (cse_var_2 + 67)
+ let cse_var_110: int32 = (cse_var_2 + 66)
+ let cse_var_109: int32 = (cse_var_2 + 65)
+ let cse_var_108: int32 = (cse_var_2 + 64)
+ let cse_var_107: int32 = (cse_var_2 + 6)
+ let cse_var_106: int32 = (cse_var_2 + 5)
+ let cse_var_105: int32 = (cse_var_2 + 47)
+ let cse_var_104: int32 = (cse_var_2 + 46)
+ let cse_var_103: int32 = (cse_var_2 + 45)
+ let cse_var_102: int32 = (cse_var_2 + 44)
+ let cse_var_101: int32 = (cse_var_2 + 43)
+ let cse_var_100: int32 = (cse_var_2 + 42)
+ let cse_var_99: int32 = (cse_var_2 + 41)
+ let cse_var_98: int32 = (cse_var_2 + 40)
+ let cse_var_97: int32 = (cse_var_2 + 4)
+ let cse_var_96: int32 = (cse_var_2 + 39)
+ let cse_var_95: int32 = (cse_var_2 + 38)
+ let cse_var_94: int32 = (cse_var_2 + 37)
+ let cse_var_93: int32 = (cse_var_2 + 36)
+ let cse_var_92: int32 = (cse_var_2 + 35)
+ let cse_var_91: int32 = (cse_var_2 + 34)
+ let cse_var_90: int32 = (cse_var_2 + 33)
+ let cse_var_89: int32 = (cse_var_2 + 32)
+ let cse_var_88: int32 = (cse_var_2 + 3)
+ let cse_var_87: int32 = (cse_var_2 + 239)
+ let cse_var_86: int32 = (cse_var_2 + 238)
+ let cse_var_85: int32 = (cse_var_2 + 237)
+ let cse_var_84: int32 = (cse_var_2 + 236)
+ let cse_var_83: int32 = (cse_var_2 + 235)
+ let cse_var_82: int32 = (cse_var_2 + 234)
+ let cse_var_81: int32 = (cse_var_2 + 233)
+ let cse_var_80: int32 = (cse_var_2 + 232)
+ let cse_var_79: int32 = (cse_var_2 + 231)
+ let cse_var_78: int32 = (cse_var_2 + 230)
+ let cse_var_77: int32 = (cse_var_2 + 229)
+ let cse_var_76: int32 = (cse_var_2 + 228)
+ let cse_var_75: int32 = (cse_var_2 + 227)
+ let cse_var_74: int32 = (cse_var_2 + 226)
+ let cse_var_73: int32 = (cse_var_2 + 225)
+ let cse_var_72: int32 = (cse_var_2 + 224)
+ let cse_var_71: int32 = (cse_var_2 + 207)
+ let cse_var_70: int32 = (cse_var_2 + 206)
+ let cse_var_69: int32 = (cse_var_2 + 205)
+ let cse_var_68: int32 = (cse_var_2 + 204)
+ let cse_var_67: int32 = (cse_var_2 + 203)
+ let cse_var_66: int32 = (cse_var_2 + 202)
+ let cse_var_65: int32 = (cse_var_2 + 201)
+ let cse_var_64: int32 = (cse_var_2 + 200)
+ let cse_var_63: int32 = (cse_var_2 + 2)
+ let cse_var_62: int32 = (cse_var_2 + 199)
+ let cse_var_61: int32 = (cse_var_2 + 198)
+ let cse_var_60: int32 = (cse_var_2 + 197)
+ let cse_var_59: int32 = (cse_var_2 + 196)
+ let cse_var_58: int32 = (cse_var_2 + 195)
+ let cse_var_57: int32 = (cse_var_2 + 194)
+ let cse_var_56: int32 = (cse_var_2 + 193)
+ let cse_var_55: int32 = (cse_var_2 + 192)
+ let cse_var_54: int32 = (cse_var_2 + 175)
+ let cse_var_53: int32 = (cse_var_2 + 174)
+ let cse_var_52: int32 = (cse_var_2 + 173)
+ let cse_var_51: int32 = (cse_var_2 + 172)
+ let cse_var_50: int32 = (cse_var_2 + 171)
+ let cse_var_49: int32 = (cse_var_2 + 170)
+ let cse_var_48: int32 = (cse_var_2 + 169)
+ let cse_var_47: int32 = (cse_var_2 + 168)
+ let cse_var_46: int32 = (cse_var_2 + 167)
+ let cse_var_45: int32 = (cse_var_2 + 166)
+ let cse_var_44: int32 = (cse_var_2 + 165)
+ let cse_var_43: int32 = (cse_var_2 + 164)
+ let cse_var_42: int32 = (cse_var_2 + 163)
+ let cse_var_41: int32 = (cse_var_2 + 162)
+ let cse_var_40: int32 = (cse_var_2 + 161)
+ let cse_var_39: int32 = (cse_var_2 + 160)
+ let cse_var_38: int32 = (cse_var_2 + 15)
+ let cse_var_37: int32 = (cse_var_2 + 143)
+ let cse_var_36: int32 = (cse_var_2 + 142)
+ let cse_var_35: int32 = (cse_var_2 + 141)
+ let cse_var_34: int32 = (cse_var_2 + 140)
+ let cse_var_33: int32 = (cse_var_2 + 14)
+ let cse_var_32: int32 = (cse_var_2 + 139)
+ let cse_var_31: int32 = (cse_var_2 + 138)
+ let cse_var_30: int32 = (cse_var_2 + 137)
+ let cse_var_29: int32 = (cse_var_2 + 136)
+ let cse_var_28: int32 = (cse_var_2 + 135)
+ let cse_var_27: int32 = (cse_var_2 + 134)
+ let cse_var_26: int32 = (cse_var_2 + 133)
+ let cse_var_25: int32 = (cse_var_2 + 132)
+ let cse_var_24: int32 = (cse_var_2 + 131)
+ let cse_var_23: int32 = (cse_var_2 + 130)
+ let cse_var_22: int32 = (cse_var_2 + 13)
+ let cse_var_21: int32 = (cse_var_2 + 129)
+ let cse_var_20: int32 = (cse_var_2 + 128)
+ let cse_var_19: int32 = (cse_var_2 + 12)
+ let cse_var_18: int32 = (cse_var_2 + 111)
+ let cse_var_17: int32 = (cse_var_2 + 110)
+ let cse_var_16: int32 = (cse_var_2 + 11)
+ let cse_var_15: int32 = (cse_var_2 + 109)
+ let cse_var_14: int32 = (cse_var_2 + 108)
+ let cse_var_13: int32 = (cse_var_2 + 107)
+ let cse_var_12: int32 = (cse_var_2 + 106)
+ let cse_var_11: int32 = (cse_var_2 + 105)
+ let cse_var_10: int32 = (cse_var_2 + 104)
+ let cse_var_9: int32 = (cse_var_2 + 103)
+ let cse_var_8: int32 = (cse_var_2 + 102)
+ let cse_var_7: int32 = (cse_var_2 + 101)
+ let cse_var_6: int32 = (cse_var_2 + 100)
+ let cse_var_5: int32 = (cse_var_2 + 10)
+ let cse_var_4: int32 = (cse_var_2 + 1)
+ let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048))
+ {
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
+ compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
+ compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
+ compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
+ compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
+ compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_132, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -692,7 +1071,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.571 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.742 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 6a9d3f0484..5589f75a5c 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:31.427</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:27.982</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:31.390</p></td>
+<td><p>00:27.947</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index ba703bda8f..75b319fae8 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,7 +689,7 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4779333
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5088019
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -812,8 +812,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8480223
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1002025
+No: 3 GFLOPS: 210.89/210.89 result: MeasureResult(costs=(0.0010977583070175439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1155447959899902, timestamp=1669070470.1798065) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9009485
+No: 4 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -935,8 +936,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('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', 0), ('unroll_explicit', 1)],None,6411547
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8004212
+No: 5 GFLOPS: 5.40/210.89 result: MeasureResult(costs=(0.0429052085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1623175144195557, timestamp=1669070474.4587286) [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2914259
+No: 6 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1058,8 +1060,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,271683
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4973955
+No: 7 GFLOPS: 64.79/210.89 result: MeasureResult(costs=(0.0035728547142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2142045497894287, timestamp=1669070476.026077) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619975
+No: 8 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1181,8 +1184,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5580492
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1254493
+No: 9 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1304,9 +1307,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6801912
-No: 7 GFLOPS: 39.89/39.89 result: MeasureResult(costs=(0.005803903074074074,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4635977745056152, timestamp=1669070424.1746726) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5293308
-No: 8 GFLOPS: 0.00/39.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9845277
+No: 10 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1428,8 +1430,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6991549
-No: 9 GFLOPS: 0.00/39.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3985151
+No: 11 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1551,9 +1553,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3744829
-No: 10 GFLOPS: 102.24/102.24 result: MeasureResult(costs=(0.0022642005492957747,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5608654022216797, timestamp=1669070425.9557855) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3527802
-No: 11 GFLOPS: 0.00/102.24 result: Traceback (most recent call last):
+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, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10209975
+No: 12 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1675,8 +1676,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7661390
-No: 12 GFLOPS: 0.00/102.24 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6657683
+No: 13 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1798,9 +1799,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6546196
-No: 13 GFLOPS: 154.28/154.28 result: MeasureResult(costs=(0.0015005428249999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.069350719451904, timestamp=1669070431.234598) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8534342
-No: 14 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2118363
+No: 14 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1922,8 +1922,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6119448
-No: 15 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1917007
+No: 15 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2045,10 +2045,8 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,741093
-No: 16 GFLOPS: 1.06/154.28 result: MeasureResult(costs=(0.21919738749999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.6823055744171143, timestamp=1669070434.4402187) [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1166206
-No: 17 GFLOPS: 44.35/154.28 result: MeasureResult(costs=(0.00521973455,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1060850620269775, timestamp=1669070435.733415) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5488704
-No: 18 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8925918
+No: 16 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2170,8 +2168,9 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6351488
-No: 19 GFLOPS: 0.00/154.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4734059
+No: 17 GFLOPS: 306.99/306.99 result: MeasureResult(costs=(0.0007540923517241379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.548452138900757, timestamp=1669070479.167015) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
+No: 18 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2293,8 +2292,131 @@ 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 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5106738
-No: 20 GFLOPS: 649.89/649.89 result: MeasureResult(costs=(0.00035621784326710814,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3048932552337646, timestamp=1669070436.6920576) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1230823
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1952737
+No: 19 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 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:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 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:453
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, 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:1731
+ 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:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 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:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 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:453
+ 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:1750
+ 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:1694
+ 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:1618
+ 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 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934185
+No: 20 GFLOPS: 39.90/306.99 result: MeasureResult(costs=(0.005802182888888888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9944984912872314, timestamp=1669070479.8508644) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422558
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2333,9 +2455,9 @@ 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, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1230823
+[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
Finish loading 20 records
-Time cost of this operator: 0.000670
+Time cost of this operator: 0.001050
</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 7cd536762e..cd6f978aa4 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ 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 311.4 98.726 (1, 2, 10, 10, 3) 2 1 [311.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.037 0.963 (1, 6, 10, 10) 1 1 [3.037]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.983 0.312 (1, 1, 10, 10, 3) 1 1 [0.983]
-Total_time - 315.42 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.2 98.621 (1, 2, 10, 10, 3) 2 1 [313.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.235 1.019 (1, 6, 10, 10) 1 1 [3.235]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.145 0.361 (1, 1, 10, 10, 3) 1 1 [1.145]
+Total_time - 317.58 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.8 97.257 (1, 6, 10, 10, 1) 2 1 [103.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.658 (1, 6, 10, 10) 1 1 [1.77]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.157 1.085 (1, 1, 10, 10, 3) 1 1 [1.157]
-Total_time - 106.727 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.6 98.123 (1, 6, 10, 10, 1) 2 1 [136.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.273 (1, 6, 10, 10) 1 1 [1.772]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.605 (1, 3, 10, 10, 1) 1 1 [0.842]
+Total_time - 139.213 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 835f2151fe..450372afa1 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,8 @@ 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]
- 58%|#####8 | 2.00M/3.42M [00:00<00:00, 20.9MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 22.6MB/s]
+ 96%|#########5| 3.28M/3.42M [00:00<00:00, 34.2MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 35.0MB/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.
@@ -565,7 +565,7 @@ 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 1.761 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.963 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 c435a147c9..d68d02a7ef 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ 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/tmpe3629tr1/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp59_o2aft/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ 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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpe3629tr1/images/target contains 8144 images
-/tmp/tmpe3629tr1/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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [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/tmp59_o2aft/images/target contains 8144 images
+/tmp/tmp59_o2aft/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ 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 - 47s - loss: 0.2602 - accuracy: 0.9182 - val_loss: 0.1256 - val_accuracy: 0.9513 - 47s/epoch - 144ms/step
+328/328 - 46s - loss: 0.2390 - accuracy: 0.9168 - val_loss: 0.1144 - val_accuracy: 0.9603 - 46s/epoch - 142ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1059 - accuracy: 0.9631 - val_loss: 0.1065 - val_accuracy: 0.9660 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.1015 - accuracy: 0.9616 - val_loss: 0.0897 - val_accuracy: 0.9683 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0699 - accuracy: 0.9733 - val_loss: 0.1301 - val_accuracy: 0.9668 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0620 - accuracy: 0.9769 - val_loss: 0.1089 - val_accuracy: 0.9641 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7f0173419050>
+<keras.callbacks.History object at 0x7ff34e46da90>
</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 30.659 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 4.174 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 30b0bf1193..edd02607ab 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:34.351</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:09.111</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:30.659</p></td>
+<td><p>04:04.174</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:01.761</p></td>
+<td><p>01:02.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.743</p></td>
+<td><p>00:50.170</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">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.421</p></td>
+<td><p>00:08.031</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.764</p></td>
+<td><p>00:03.770</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 282e8e6490..ef0f196c35 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:44.375</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.665</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</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>00:32.500</p></td>
+<td><p>00:31.924</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>00:10.204</p></td>
+<td><p>00:10.115</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>00:01.663</p></td>
+<td><p>00:01.619</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 e1c8e1184b..0c6ffa5646 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ 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 0x7f014c330830>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7ff34cf0cef0>
</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 3b9296bee0..25081a6d2c 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:07.952</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.967</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,31 +349,31 @@
</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>00:05.492</p></td>
+<td><p>00:04.558</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>00:01.130</p></td>
+<td><p>00:01.081</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>00:00.573</p></td>
+<td><p>00:00.568</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>00:00.546</p></td>
+<td><p>00:00.549</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>00:00.114</p></td>
+<td><p>00:00.116</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.049</p></td>
+<td><p>00:00.048</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.029</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/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 11392b1b6f..fe5f3f7ecd 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp0c98d7ly/input0.cc'\nsource_filename = \"/tmp/tmp0c98d7ly/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp7gcvbn52/input0.cc'\nsource_filename = \"/tmp/tmp7gcvbn52/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<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 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="from_source.html">Install from Source</a></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 277837578a..df086300f1 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ 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>
@@ -1899,7 +1899,7 @@ 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 fff272e8a2..b08b395f7c 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/3ccc3009a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index b523a13109..35dd81dcb7 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/3ccc3009a/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 a7f456d3b2..5e093eb2d5 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/3ccc3009a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index fad73eb8d4..7512ca0c6a 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/3ccc3009a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index eb38e913a3..9a064549d0 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/3ccc3009a/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 48f533cc24..27cf6a205d 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/3ccc3009a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 29fa5827fd..552d83c66e 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 2cb76aa3dc..79f1c8996b 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 3dbf25cdfb..7e08e7e0fa 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/3ccc3009a/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 6f130a73f7..e0e7f46d6e 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index ff28a59742..f86b0e3995 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/3ccc3009a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 15cd25b468..65d92ce69c 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 1a2064b0d3..cadaf0d282 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/3ccc3009a/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index d150079d70..71db3623bb 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/3ccc3009a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 24a6b24c03..6190fe5e7f 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/3ccc3009a/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 6d549482fd..f0a96baf95 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/3ccc3009a/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 4161f3658e..b010d47335 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/3ccc3009a/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 04ca37b7f8..b9f3799eda 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/3ccc3009a/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 2acca29c80..cb0fde64b6 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/3ccc3009a/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 1fe6af7957..7d4c1d28ca 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/3ccc3009a/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 2fdec2e9f7..9a0b6e124e 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 9e7237e95e..7e9f2ce948 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/3ccc3009a/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 2d76af7b3a..5eea978144 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/3ccc3009a/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 8672bc8219..e57ddd0993 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/3ccc3009a/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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/3ccc3009a/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/545f8dc92/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 86db371f80..6ea9bf9c60 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 ba33767c17..c0177b36d2 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:26.172</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.497</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.166</p></td>
+<td><p>00:26.490</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index a46dafd438..4a71179fa4 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ 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 28.72s!
+resnet18_v1 inference graph built in 29.30s!
</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 b07f80dfe9..c3755c11c2 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ 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 19.51s!
+yolov3-tiny inference graph built in 19.73s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 7be4561e16..24f02d8d74 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>01:40.543</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.137</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:51.852</p></td>
+<td><p>00:51.095</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:48.691</p></td>
+<td><p>00:49.042</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 c3884f648c..58dafe6958 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:03.140</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.128</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</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>00:02.700</p></td>
+<td><p>00:02.689</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>00:00.440</p></td>
+<td><p>00:00.438</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 af2597d5cd..e3bcfe6bb8 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>00:00.798</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.757</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</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>00:00.435</p></td>
+<td><p>00:00.399</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>00:00.363</p></td>
+<td><p>00:00.358</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 b914b9ed98..c100e8cf46 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,6 +491,9 @@ 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>.T
+</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>
@@ -577,7 +580,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.717 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.093 ms
</pre></div>
</div>
</div>
@@ -651,7 +654,7 @@ 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 20.022 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.730 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 2241e2cbf9..950023279c 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ 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: 11.09/11.09 result: MeasureResult(costs=(0.0241983496,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5648739337921143, timestamp=1669069044.6963928) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-No: 2 GFLOPS: 11.16/11.16 result: MeasureResult(costs=(0.024052841,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.57857346534729, timestamp=1669069045.2889998) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
-No: 3 GFLOPS: 10.74/11.16 result: MeasureResult(costs=(0.0249896626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6110608577728271, timestamp=1669069046.6144114) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
-No: 4 GFLOPS: 0.49/11.16 result: MeasureResult(costs=(0.545164375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.892568349838257, timestamp=1669069055.530979) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 5 GFLOPS: 0.50/11.16 result: MeasureResult(costs=(0.5354741759999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.735774755477905, timestamp=1669069064.5135775) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
-No: 6 GFLOPS: 12.22/12.22 result: MeasureResult(costs=(0.0219627194,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5442948341369629, timestamp=1669069065.8125002) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-No: 7 GFLOPS: 9.13/12.22 result: MeasureResult(costs=(0.029392543,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.749305248260498, timestamp=1669069067.1873536) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
-No: 8 GFLOPS: 12.94/12.94 result: MeasureResult(costs=(0.020745803,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6637840270996094, timestamp=1669069067.7427788) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
-No: 9 GFLOPS: 1.63/12.94 result: MeasureResult(costs=(0.1644089454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7509829998016357, timestamp=1669069070.641762) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
-No: 10 GFLOPS: 3.25/12.94 result: MeasureResult(costs=(0.082471217,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5046789646148682, timestamp=1669069072.1626863) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+No: 1 GFLOPS: 11.69/11.69 result: MeasureResult(costs=(0.0229614498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.550915002822876, timestamp=1669069093.9232368) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
+No: 2 GFLOPS: 0.50/11.69 result: MeasureResult(costs=(0.5346515846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.731043100357056, timestamp=1669069102.682373) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+No: 3 GFLOPS: 1.55/11.69 result: MeasureResult(costs=(0.1727075166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9166369438171387, timestamp=1669069106.362152) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+No: 4 GFLOPS: 8.24/11.69 result: MeasureResult(costs=(0.032565906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.653590202331543, timestamp=1669069107.798683) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+No: 5 GFLOPS: 1.69/11.69 result: MeasureResult(costs=(0.1589572562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.681199312210083, timestamp=1669069110.6333787) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+No: 6 GFLOPS: 12.19/12.19 result: MeasureResult(costs=(0.022028911800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5019567012786865, timestamp=1669069111.910717) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 7 GFLOPS: 13.38/13.38 result: MeasureResult(costs=(0.020057455600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4962158203125, timestamp=1669069112.4011486) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
+No: 8 GFLOPS: 12.85/13.38 result: MeasureResult(costs=(0.020884536399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5327770709991455, timestamp=1669069112.9469588) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
+No: 9 GFLOPS: 0.50/13.38 result: MeasureResult(costs=(0.5390465264000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.724902391433716, timestamp=1669069121.7890291) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+No: 10 GFLOPS: 3.21/13.38 result: MeasureResult(costs=(0.08349640439999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4820079803466797, timestamp=1669069123.291861) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
</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 38e56b769b..a825f6b228 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ 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': 516.8022287300005, 'median': 516.7068863999987, 'std': 3.7927704287204276}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
</pre></div>
</div>
</div>
@@ -712,179 +712,179 @@ 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: 7.08/ 16.81 GFLOPS | Progress: (4/20) | 7.13 s
-[Task 1/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (8/20) | 10.44 s
-[Task 1/25] Current/Best: 14.49/ 21.60 GFLOPS | Progress: (12/20) | 12.74 s
-[Task 1/25] Current/Best: 16.06/ 23.22 GFLOPS | Progress: (16/20) | 14.68 s
-[Task 1/25] Current/Best: 6.43/ 23.22 GFLOPS | Progress: (20/20) | 17.74 s Done.
+[Task 1/25] Current/Best: 14.02/ 18.79 GFLOPS | Progress: (4/20) | 6.98 s
+[Task 1/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (8/20) | 11.43 s
+[Task 1/25] Current/Best: 9.25/ 23.48 GFLOPS | Progress: (12/20) | 13.62 s
+[Task 1/25] Current/Best: 17.21/ 23.48 GFLOPS | Progress: (16/20) | 16.07 s
+[Task 1/25] Current/Best: 15.13/ 23.48 GFLOPS | Progress: (20/20) | 19.10 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 20.33/ 20.90 GFLOPS | Progress: (4/20) | 3.04 s
-[Task 2/25] Current/Best: 11.29/ 20.90 GFLOPS | Progress: (8/20) | 4.18 s
-[Task 2/25] Current/Best: 11.83/ 20.90 GFLOPS | Progress: (12/20) | 5.57 s
-[Task 2/25] Current/Best: 5.62/ 20.90 GFLOPS | Progress: (16/20) | 6.92 s
-[Task 2/25] Current/Best: 16.64/ 20.90 GFLOPS | Progress: (20/20) | 8.56 s Done.
+[Task 2/25] Current/Best: 11.20/ 17.44 GFLOPS | Progress: (4/20) | 3.34 s
+[Task 2/25] Current/Best: 14.45/ 17.44 GFLOPS | Progress: (8/20) | 4.54 s
+[Task 2/25] Current/Best: 7.49/ 22.85 GFLOPS | Progress: (12/20) | 7.23 s
+[Task 2/25] Current/Best: 21.95/ 22.85 GFLOPS | Progress: (16/20) | 8.47 s
+[Task 2/25] Current/Best: 12.94/ 22.85 GFLOPS | Progress: (20/20) | 9.89 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 13.97/ 13.97 GFLOPS | Progress: (4/20) | 3.96 s
-[Task 3/25] Current/Best: 19.73/ 20.05 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 3/25] Current/Best: 11.52/ 20.05 GFLOPS | Progress: (12/20) | 9.47 s
-[Task 3/25] Current/Best: 16.50/ 21.98 GFLOPS | Progress: (16/20) | 11.32 s
-[Task 3/25] Current/Best: 17.77/ 21.98 GFLOPS | Progress: (20/20) | 13.76 s Done.
+[Task 3/25] Current/Best: 12.59/ 19.55 GFLOPS | Progress: (4/20) | 3.62 s
+[Task 3/25] Current/Best: 10.19/ 19.55 GFLOPS | Progress: (8/20) | 5.39 s
+[Task 3/25] Current/Best: 9.87/ 23.40 GFLOPS | Progress: (12/20) | 7.45 s
+[Task 3/25] Current/Best: 14.59/ 23.92 GFLOPS | Progress: (16/20) | 9.06 s
+[Task 3/25] Current/Best: 14.21/ 23.92 GFLOPS | Progress: (20/20) | 11.41 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 12.05/ 22.30 GFLOPS | Progress: (4/20) | 4.52 s
-[Task 4/25] Current/Best: 11.05/ 22.30 GFLOPS | Progress: (8/20) | 8.82 s
-[Task 4/25] Current/Best: 19.91/ 22.30 GFLOPS | Progress: (12/20) | 10.36 s
-[Task 4/25] Current/Best: 17.10/ 22.30 GFLOPS | Progress: (16/20) | 13.45 s
-[Task 4/25] Current/Best: 19.40/ 22.30 GFLOPS | Progress: (20/20) | 21.86 s Done.
-
-[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 14.28/ 17.02 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 5/25] Current/Best: 16.24/ 17.02 GFLOPS | Progress: (8/20) | 5.17 s
-[Task 5/25] Current/Best: 5.73/ 19.65 GFLOPS | Progress: (12/20) | 6.68 s
-[Task 5/25] Current/Best: 4.83/ 19.65 GFLOPS | Progress: (16/20) | 8.46 s
-[Task 5/25] Current/Best: 5.52/ 19.65 GFLOPS | Progress: (20/20) | 10.64 s Done.
+[Task 4/25] Current/Best: 11.61/ 19.51 GFLOPS | Progress: (4/20) | 3.44 s
+[Task 4/25] Current/Best: 12.42/ 19.51 GFLOPS | Progress: (8/20) | 5.20 s
+[Task 4/25] Current/Best: 13.90/ 19.51 GFLOPS | Progress: (12/20) | 9.47 s
+[Task 4/25] Current/Best: 15.62/ 19.51 GFLOPS | Progress: (16/20) | 17.50 s
+[Task 4/25] Current/Best: 15.48/ 19.51 GFLOPS | Progress: (20/20) | 28.36 s
+[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 5/25] Current/Best: 19.33/ 23.48 GFLOPS | Progress: (4/20) | 3.62 s
+[Task 5/25] Current/Best: 5.28/ 23.48 GFLOPS | Progress: (8/20) | 5.46 s
+[Task 5/25] Current/Best: 10.84/ 23.48 GFLOPS | Progress: (12/20) | 7.00 s
+[Task 5/25] Current/Best: 17.85/ 23.48 GFLOPS | Progress: (16/20) | 8.88 s
+[Task 5/25] Current/Best: 15.50/ 23.48 GFLOPS | Progress: (20/20) | 10.89 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 14.72/ 17.61 GFLOPS | Progress: (4/20) | 4.09 s
-[Task 6/25] Current/Best: 9.12/ 20.30 GFLOPS | Progress: (8/20) | 7.20 s
-[Task 6/25] Current/Best: 4.54/ 20.30 GFLOPS | Progress: (12/20) | 9.78 s
-[Task 6/25] Current/Best: 10.12/ 20.30 GFLOPS | Progress: (16/20) | 12.10 s
-[Task 6/25] Current/Best: 4.76/ 20.30 GFLOPS | Progress: (20/20) | 14.79 s Done.
+[Task 6/25] Current/Best: 14.04/ 19.54 GFLOPS | Progress: (4/20) | 3.43 s
+[Task 6/25] Current/Best: 8.14/ 19.54 GFLOPS | Progress: (8/20) | 5.86 s
+[Task 6/25] Current/Best: 5.86/ 19.54 GFLOPS | Progress: (12/20) | 8.38 s
+[Task 6/25] Current/Best: 3.19/ 19.54 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 6/25] Current/Best: 11.94/ 19.54 GFLOPS | Progress: (20/20) | 15.23 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 3.52 s
-[Task 7/25] Current/Best: 15.41/ 17.35 GFLOPS | Progress: (8/20) | 5.88 s
-[Task 7/25] Current/Best: 8.75/ 17.35 GFLOPS | Progress: (12/20) | 7.98 s
-[Task 7/25] Current/Best: 10.47/ 17.35 GFLOPS | Progress: (16/20) | 10.77 s
-[Task 7/25] Current/Best: 17.86/ 18.20 GFLOPS | Progress: (20/20) | 13.06 s Done.
+[Task 7/25] Current/Best: 11.76/ 12.37 GFLOPS | Progress: (4/20) | 4.25 s
+[Task 7/25] Current/Best: 14.38/ 16.97 GFLOPS | Progress: (8/20) | 7.34 s
+[Task 7/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 9.52 s
+[Task 7/25] Current/Best: 18.18/ 19.05 GFLOPS | Progress: (16/20) | 12.42 s
+[Task 7/25] Current/Best: 12.08/ 19.05 GFLOPS | Progress: (20/20) | 14.78 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 12.47/ 12.80 GFLOPS | Progress: (4/20) | 6.15 s
-[Task 8/25] Current/Best: 11.03/ 16.19 GFLOPS | Progress: (8/20) | 10.72 s
-[Task 8/25] Current/Best: 14.34/ 17.23 GFLOPS | Progress: (12/20) | 16.81 s
-[Task 8/25] Current/Best: 14.79/ 17.23 GFLOPS | Progress: (16/20) | 19.21 s
-[Task 8/25] Current/Best: 2.59/ 17.23 GFLOPS | Progress: (20/20) | 22.14 s Done.
-
+[Task 8/25] Current/Best: 10.24/ 10.24 GFLOPS | Progress: (4/20) | 13.36 s
+[Task 8/25] Current/Best: 3.19/ 14.15 GFLOPS | Progress: (8/20) | 20.47 s
+[Task 8/25] Current/Best: 7.72/ 20.42 GFLOPS | Progress: (12/20) | 24.06 s
+[Task 8/25] Current/Best: 7.60/ 20.42 GFLOPS | Progress: (16/20) | 30.65 s
+[Task 8/25] Current/Best: 13.17/ 20.42 GFLOPS | Progress: (20/20) | 34.73 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.38/ 20.24 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 9/25] Current/Best: 14.82/ 20.24 GFLOPS | Progress: (8/20) | 4.39 s
-[Task 9/25] Current/Best: 11.85/ 20.24 GFLOPS | Progress: (12/20) | 9.53 s
-[Task 9/25] Current/Best: 17.75/ 20.24 GFLOPS | Progress: (16/20) | 14.65 s
-[Task 9/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (20/20) | 17.14 s Done.
-
+[Task 9/25] Current/Best: 4.90/ 13.76 GFLOPS | Progress: (4/20) | 7.58 s
+[Task 9/25] Current/Best: 12.83/ 13.91 GFLOPS | Progress: (8/20) | 13.01 s
+[Task 9/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (12/20) | 21.23 s
+[Task 9/25] Current/Best: 18.55/ 22.86 GFLOPS | Progress: (16/20) | 24.05 s
+[Task 9/25] Current/Best: 17.66/ 22.86 GFLOPS | Progress: (20/20) | 34.82 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 6.43/ 14.58 GFLOPS | Progress: (4/20) | 4.14 s
-[Task 10/25] Current/Best: 14.89/ 14.89 GFLOPS | Progress: (8/20) | 6.51 s
-[Task 10/25] Current/Best: 13.96/ 14.89 GFLOPS | Progress: (12/20) | 8.25 s
-[Task 10/25] Current/Best: 7.00/ 20.57 GFLOPS | Progress: (16/20) | 9.84 s
-[Task 10/25] Current/Best: 4.90/ 20.57 GFLOPS | Progress: (20/20) | 12.12 s Done.
+[Task 10/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (4/20) | 4.12 s
+[Task 10/25] Current/Best: 8.93/ 17.93 GFLOPS | Progress: (8/20) | 5.88 s
+[Task 10/25] Current/Best: 16.89/ 17.93 GFLOPS | Progress: (12/20) | 7.58 s
+[Task 10/25] Current/Best: 18.07/ 20.24 GFLOPS | Progress: (16/20) | 9.20 s
+[Task 10/25] Current/Best: 6.70/ 20.24 GFLOPS | Progress: (20/20) | 11.15 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 16.65/ 16.84 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 11/25] Current/Best: 10.91/ 22.18 GFLOPS | Progress: (8/20) | 7.86 s
-[Task 11/25] Current/Best: 23.38/ 23.38 GFLOPS | Progress: (12/20) | 11.35 s
-[Task 11/25] Current/Best: 15.33/ 23.38 GFLOPS | Progress: (16/20) | 13.79 s
-[Task 11/25] Current/Best: 11.21/ 23.38 GFLOPS | Progress: (20/20) | 16.11 s Done.
+[Task 11/25] Current/Best: 9.11/ 12.69 GFLOPS | Progress: (4/20) | 3.72 s
+[Task 11/25] Current/Best: 8.33/ 21.59 GFLOPS | Progress: (8/20) | 6.60 s
+[Task 11/25] Current/Best: 7.72/ 23.63 GFLOPS | Progress: (12/20) | 9.20 s
+[Task 11/25] Current/Best: 7.79/ 23.63 GFLOPS | Progress: (16/20) | 11.85 s
+[Task 11/25] Current/Best: 7.12/ 23.63 GFLOPS | Progress: (20/20) | 13.96 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 13.38/ 13.38 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 12/25] Current/Best: 6.65/ 14.19 GFLOPS | Progress: (8/20) | 8.20 s
-[Task 12/25] Current/Best: 4.50/ 14.19 GFLOPS | Progress: (12/20) | 12.35 s
-[Task 12/25] Current/Best: 11.95/ 17.74 GFLOPS | Progress: (16/20) | 17.16 s
-[Task 12/25] Current/Best: 15.96/ 17.74 GFLOPS | Progress: (20/20) | 19.75 s Done.
+[Task 12/25] Current/Best: 9.44/ 12.43 GFLOPS | Progress: (4/20) | 4.98 s
+[Task 12/25] Current/Best: 7.29/ 16.16 GFLOPS | Progress: (8/20) | 9.93 s
+[Task 12/25] Current/Best: 9.17/ 18.54 GFLOPS | Progress: (12/20) | 14.06 s
+[Task 12/25] Current/Best: 11.69/ 18.54 GFLOPS | Progress: (16/20) | 18.09 s
+[Task 12/25] Current/Best: 8.27/ 18.54 GFLOPS | Progress: (20/20) | 21.96 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (4/20) | 5.48 s
-[Task 13/25] Current/Best: 12.06/ 18.27 GFLOPS | Progress: (8/20) | 7.33 s
-[Task 13/25] Current/Best: 12.22/ 18.27 GFLOPS | Progress: (12/20) | 10.22 s
-[Task 13/25] Current/Best: 12.15/ 18.27 GFLOPS | Progress: (16/20) | 13.09 s
-[Task 13/25] Current/Best: 10.86/ 18.27 GFLOPS | Progress: (20/20) | 16.90 s Done.
+[Task 13/25] Current/Best: 6.03/ 12.06 GFLOPS | Progress: (4/20) | 4.63 s
+[Task 13/25] Current/Best: 9.98/ 12.06 GFLOPS | Progress: (8/20) | 7.53 s
+[Task 13/25] Current/Best: 17.34/ 17.48 GFLOPS | Progress: (12/20) | 10.26 s
+[Task 13/25] Current/Best: 7.00/ 18.85 GFLOPS | Progress: (16/20) | 12.87 s
+[Task 13/25] Current/Best: 1.57/ 19.19 GFLOPS | Progress: (20/20) | 17.32 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 14.38/ 14.38 GFLOPS | Progress: (4/20) | 4.02 s
-[Task 14/25] Current/Best: 13.07/ 18.46 GFLOPS | Progress: (8/20) | 8.15 s
-[Task 14/25] Current/Best: 17.57/ 18.46 GFLOPS | Progress: (12/20) | 15.09 s
-[Task 14/25] Current/Best: 11.24/ 18.46 GFLOPS | Progress: (16/20) | 18.02 s
-[Task 14/25] Current/Best: 10.31/ 18.46 GFLOPS | Progress: (20/20) | 22.58 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 13.82/ 13.82 GFLOPS | Progress: (4/20) | 3.89 s
-[Task 15/25] Current/Best: 8.25/ 13.82 GFLOPS | Progress: (8/20) | 10.56 s
-[Task 15/25] Current/Best: 13.95/ 14.43 GFLOPS | Progress: (12/20) | 12.47 s
-[Task 15/25] Current/Best: 20.04/ 20.04 GFLOPS | Progress: (16/20) | 15.41 s Done.
+[Task 14/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 14/25] Current/Best: 16.98/ 20.07 GFLOPS | Progress: (8/20) | 5.26 s
+[Task 14/25] Current/Best: 10.49/ 20.07 GFLOPS | Progress: (12/20) | 11.04 s
+[Task 14/25] Current/Best: 15.40/ 20.07 GFLOPS | Progress: (16/20) | 12.95 s
+[Task 14/25] Current/Best: 4.84/ 20.07 GFLOPS | Progress: (20/20) | 15.20 s Done.
-[Task 15/25] Current/Best: 21.68/ 21.68 GFLOPS | Progress: (20/20) | 22.09 s Done.
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 3.13/ 19.20 GFLOPS | Progress: (4/20) | 5.62 s
+[Task 15/25] Current/Best: 8.56/ 19.20 GFLOPS | Progress: (8/20) | 8.88 s
+[Task 15/25] Current/Best: 11.80/ 19.20 GFLOPS | Progress: (12/20) | 12.71 s
+[Task 15/25] Current/Best: 12.40/ 19.20 GFLOPS | Progress: (16/20) | 14.23 s
+[Task 15/25] Current/Best: 19.01/ 19.20 GFLOPS | Progress: (20/20) | 20.36 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 18.89/ 18.89 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 16/25] Current/Best: 11.49/ 18.89 GFLOPS | Progress: (8/20) | 5.33 s
-[Task 16/25] Current/Best: 11.58/ 18.89 GFLOPS | Progress: (12/20) | 7.97 s
-[Task 16/25] Current/Best: 6.39/ 18.89 GFLOPS | Progress: (16/20) | 9.81 s
-[Task 16/25] Current/Best: 9.64/ 18.89 GFLOPS | Progress: (20/20) | 12.85 s Done.
+[Task 16/25] Current/Best: 16.27/ 16.36 GFLOPS | Progress: (4/20) | 3.61 s
+[Task 16/25] Current/Best: 5.38/ 19.49 GFLOPS | Progress: (8/20) | 5.20 s Done.
+ Done.
+
+[Task 16/25] Current/Best: 17.93/ 19.49 GFLOPS | Progress: (12/20) | 7.27 s
+[Task 16/25] Current/Best: 13.82/ 19.49 GFLOPS | Progress: (16/20) | 8.72 s
+[Task 16/25] Current/Best: 12.03/ 20.68 GFLOPS | Progress: (20/20) | 10.37 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (4/20) | 3.49 s
-[Task 17/25] Current/Best: 7.10/ 22.58 GFLOPS | Progress: (8/20) | 5.58 s
-[Task 17/25] Current/Best: 7.01/ 22.58 GFLOPS | Progress: (12/20) | 7.54 s
-[Task 17/25] Current/Best: 16.49/ 22.58 GFLOPS | Progress: (16/20) | 9.72 s
-[Task 17/25] Current/Best: 15.27/ 22.58 GFLOPS | Progress: (20/20) | 13.45 s Done.
+[Task 17/25] Current/Best: 12.68/ 20.05 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 17/25] Current/Best: 11.62/ 20.05 GFLOPS | Progress: (8/20) | 7.16 s
+[Task 17/25] Current/Best: 6.16/ 22.46 GFLOPS | Progress: (12/20) | 10.55 s
+[Task 17/25] Current/Best: 14.59/ 23.13 GFLOPS | Progress: (16/20) | 12.38 s
+[Task 17/25] Current/Best: 10.42/ 23.13 GFLOPS | Progress: (20/20) | 14.50 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 17.56/ 17.56 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 18/25] Current/Best: 16.98/ 17.56 GFLOPS | Progress: (8/20) | 11.51 s
-[Task 18/25] Current/Best: 14.08/ 17.92 GFLOPS | Progress: (12/20) | 13.23 s
-[Task 18/25] Current/Best: 7.57/ 17.92 GFLOPS | Progress: (16/20) | 17.77 s
-[Task 18/25] Current/Best: 3.09/ 17.92 GFLOPS | Progress: (20/20) | 21.71 s Done.
+[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (4/20) | 3.47 s
+[Task 18/25] Current/Best: 3.11/ 21.21 GFLOPS | Progress: (8/20) | 5.68 s
+[Task 18/25] Current/Best: 14.80/ 21.21 GFLOPS | Progress: (12/20) | 7.84 s
+[Task 18/25] Current/Best: 10.90/ 21.21 GFLOPS | Progress: (16/20) | 11.63 s
+[Task 18/25] Current/Best: 15.51/ 21.21 GFLOPS | Progress: (20/20) | 13.85 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 14.80/ 21.37 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 19/25] Current/Best: 17.00/ 21.37 GFLOPS | Progress: (8/20) | 7.93 s
-[Task 19/25] Current/Best: 10.22/ 21.37 GFLOPS | Progress: (12/20) | 10.17 s
-[Task 19/25] Current/Best: 17.57/ 21.37 GFLOPS | Progress: (16/20) | 12.14 s
-[Task 19/25] Current/Best: 8.84/ 21.37 GFLOPS | Progress: (20/20) | 16.96 s Done.
+[Task 19/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 5.31 s
+[Task 19/25] Current/Best: 10.28/ 21.30 GFLOPS | Progress: (8/20) | 10.31 s
+[Task 19/25] Current/Best: 17.77/ 21.30 GFLOPS | Progress: (12/20) | 13.93 s
+[Task 19/25] Current/Best: 11.87/ 21.30 GFLOPS | Progress: (16/20) | 16.63 s
+[Task 19/25] Current/Best: 10.07/ 21.30 GFLOPS | Progress: (20/20) | 18.59 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.29/ 10.29 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 20/25] Current/Best: 9.58/ 18.51 GFLOPS | Progress: (8/20) | 7.90 s
-[Task 20/25] Current/Best: 10.67/ 19.50 GFLOPS | Progress: (12/20) | 10.60 s
-[Task 20/25] Current/Best: 18.25/ 20.33 GFLOPS | Progress: (16/20) | 13.25 s
-[Task 20/25] Current/Best: 9.64/ 20.33 GFLOPS | Progress: (20/20) | 14.72 s
+[Task 20/25] Current/Best: 13.30/ 16.52 GFLOPS | Progress: (4/20) | 3.39 s
+[Task 20/25] Current/Best: 15.42/ 17.94 GFLOPS | Progress: (8/20) | 5.39 s
+[Task 20/25] Current/Best: 15.57/ 18.82 GFLOPS | Progress: (12/20) | 8.01 s
+[Task 20/25] Current/Best: 16.59/ 18.82 GFLOPS | Progress: (16/20) | 10.84 s
+[Task 20/25] Current/Best: 2.24/ 18.82 GFLOPS | Progress: (20/20) | 13.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (4/20) | 3.90 s
-[Task 21/25] Current/Best: 5.20/ 20.73 GFLOPS | Progress: (8/20) | 6.87 s
-[Task 21/25] Current/Best: 10.59/ 20.73 GFLOPS | Progress: (12/20) | 8.71 s
-[Task 21/25] Current/Best: 15.46/ 20.73 GFLOPS | Progress: (16/20) | 10.89 s
-[Task 21/25] Current/Best: 8.37/ 20.73 GFLOPS | Progress: (20/20) | 15.07 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (4/20) | 3.02 s Done.
- Done.
+[Task 21/25] Current/Best: 5.22/ 11.16 GFLOPS | Progress: (4/20) | 4.28 s
+[Task 21/25] Current/Best: 8.84/ 14.51 GFLOPS | Progress: (8/20) | 6.79 s
+[Task 21/25] Current/Best: 16.30/ 16.30 GFLOPS | Progress: (12/20) | 9.53 s Done.
-[Task 22/25] Current/Best: 18.29/ 21.35 GFLOPS | Progress: (8/20) | 4.65 s
-[Task 22/25] Current/Best: 18.33/ 21.35 GFLOPS | Progress: (12/20) | 6.08 s
-[Task 22/25] Current/Best: 11.05/ 21.35 GFLOPS | Progress: (16/20) | 8.38 s
-[Task 22/25] Current/Best: 11.10/ 21.35 GFLOPS | Progress: (20/20) | 10.31 s Done.
+[Task 21/25] Current/Best: 11.45/ 20.16 GFLOPS | Progress: (16/20) | 11.91 s
+[Task 21/25] Current/Best: 9.53/ 20.16 GFLOPS | Progress: (20/20) | 14.02 s Done.
+
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25] Current/Best: 9.60/ 11.59 GFLOPS | Progress: (4/20) | 3.54 s
+[Task 22/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.39 s
+[Task 22/25] Current/Best: 4.46/ 17.28 GFLOPS | Progress: (12/20) | 6.87 s
+[Task 22/25] Current/Best: 16.47/ 17.28 GFLOPS | Progress: (16/20) | 8.19 s
+[Task 22/25] Current/Best: 11.96/ 17.28 GFLOPS | Progress: (20/20) | 10.24 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 1.55/ 14.72 GFLOPS | Progress: (4/20) | 5.53 s
-[Task 23/25] Current/Best: 9.48/ 21.76 GFLOPS | Progress: (8/20) | 8.33 s
-[Task 23/25] Current/Best: 3.08/ 21.76 GFLOPS | Progress: (12/20) | 11.54 s
-[Task 23/25] Current/Best: 8.45/ 21.76 GFLOPS | Progress: (16/20) | 14.54 s
-[Task 23/25] Current/Best: 20.25/ 21.76 GFLOPS | Progress: (20/20) | 18.45 s Done.
+[Task 23/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (4/20) | 4.67 s
+[Task 23/25] Current/Best: 13.42/ 16.38 GFLOPS | Progress: (8/20) | 7.15 s
+[Task 23/25] Current/Best: 9.81/ 16.38 GFLOPS | Progress: (12/20) | 10.47 s
+[Task 23/25] Current/Best: 9.80/ 18.98 GFLOPS | Progress: (16/20) | 12.89 s
+[Task 23/25] Current/Best: 8.33/ 18.98 GFLOPS | Progress: (20/20) | 15.21 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 4.55/ 4.55 GFLOPS | Progress: (4/20) | 12.23 s
-[Task 24/25] Current/Best: 4.02/ 5.32 GFLOPS | Progress: (8/20) | 14.92 s
-[Task 24/25] Current/Best: 2.52/ 9.45 GFLOPS | Progress: (12/20) | 25.66 s
-[Task 24/25] Current/Best: 3.00/ 9.45 GFLOPS | Progress: (16/20) | 36.36 s
-[Task 24/25] Current/Best: 6.43/ 9.45 GFLOPS | Progress: (20/20) | 46.84 s
+[Task 24/25] Current/Best: 7.90/ 8.24 GFLOPS | Progress: (4/20) | 12.27 s
+[Task 24/25] Current/Best: 9.93/ 9.93 GFLOPS | Progress: (8/20) | 22.97 s
+[Task 24/25] Current/Best: 3.74/ 9.93 GFLOPS | Progress: (12/20) | 33.71 s
+[Task 24/25] Current/Best: 3.94/ 9.93 GFLOPS | Progress: (16/20) | 44.41 s
+[Task 24/25] Current/Best: 1.71/ 9.93 GFLOPS | Progress: (20/20) | 54.91 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-[Task 25/25] Current/Best: 7.10/ 7.29 GFLOPS | Progress: (4/20) | 8.37 s
-[Task 25/25] Current/Best: 7.89/ 9.57 GFLOPS | Progress: (8/20) | 19.08 s
-[Task 25/25] Current/Best: 5.88/ 9.57 GFLOPS | Progress: (12/20) | 20.84 s
-[Task 25/25] Current/Best: 2.84/ 9.57 GFLOPS | Progress: (16/20) | 31.54 s
-[Task 25/25] Current/Best: 7.41/ 9.57 GFLOPS | Progress: (20/20) | 42.32 s
+[Task 25/25] Current/Best: 3.02/ 3.02 GFLOPS | Progress: (4/20) | 12.98 s
+[Task 25/25] Current/Best: 3.04/ 9.07 GFLOPS | Progress: (8/20) | 18.78 s
+[Task 25/25] Current/Best: 7.75/ 9.07 GFLOPS | Progress: (12/20) | 19.82 s
+[Task 25/25] Current/Best: 1.54/ 9.07 GFLOPS | Progress: (16/20) | 30.55 s
+[Task 25/25] Current/Best: 1.55/ 9.29 GFLOPS | Progress: (20/20) | 35.59 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -946,7 +946,7 @@ model using optimized operators to speed up our computations.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +983,8 @@ 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': 420.22287448999805, 'median': 418.76673499999697, 'std': 3.0618863299389014}
-unoptimized: {'mean': 516.8022287300005, 'median': 516.7068863999987, 'std': 3.7927704287204276}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 416.1014501600016, 'median': 415.50952905000713, 'std': 4.321109686634458}
+unoptimized: {'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
</pre></div>
</div>
</div>
@@ -998,7 +998,7 @@ 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> ( 11 minutes 10.288 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 28.828 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 ee6ce02600..d0d6f19df0 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ 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>1.257e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.25e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index ea7ff737ec..86d9a96cf4 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x12be1250)), stage(b, placeholder(b, 0x70eb700)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x8a10b00)), stage(b, placeholder(b, 0x2399d1b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 0bd83c41b4..1164acd295 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<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>14:39.951</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:11.609</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</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>11:10.288</p></td>
+<td><p>11:28.828</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>01:20.022</p></td>
+<td><p>01:33.730</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.982</p></td>
+<td><p>00:59.170</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>00:33.596</p></td>
+<tr class="row-even"><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>00:33.794</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>00:32.521</p></td>
+<tr class="row-odd"><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>00:33.784</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>00:01.591</p></td>
+<td><p>00:01.355</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>00:00.760</p></td>
+<td><p>00:00.761</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>00:00.183</p></td>
+<td><p>00:00.176</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
@@ -388,15 +388,15 @@
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 6332c76a32..b15de9a5ce 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -552,7 +552,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000008
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -639,7 +639,7 @@ 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: 0.000024
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000046
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [n: int32], [stride: int32], type="auto"),
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.635360000222135e-06 1.0
- naive 7.793600000000001e-06 1.0207246285405354
-parallel 7.0009e-06 0.9169050313012516
- vector 2.4484700000000003e-05 3.2067512205433237
+ numpy 7.813590000296245e-06 1.0
+ naive 6.7472e-06 0.8635211215003842
+parallel 6.9564e-06 0.8902949860097925
+ vector 4.60098e-05 5.888432845626093
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ 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: 0.020652
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018505
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ 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: 3.321090
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.251925
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ 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: 0.310711
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.306264
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ 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: 0.334473
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.341208
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ 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: 0.140346
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119167
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ 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: 0.127151
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110721
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ 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: 0.118909
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111180
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ 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: 0.150095
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146938
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ 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 3.3210900419 1.0
- blocking 0.31071136 0.0935570418386614
- vectorization 0.33447345679999996 0.10071195076922614
-loop permutation 0.14034593560000003 0.04225899744642513
- array packing 0.1271508498 0.0382858784904419
- block caching 0.1189094664 0.03580434884324056
- parallelization 0.1500954634 0.04519463835859451
+ none 3.2519253935 1.0
+ blocking 0.30626426110000005 0.09417936269760858
+ vectorization 0.3412077699 0.10492484562592103
+loop permutation 0.1191673078 0.036645154294804395
+ array packing 0.1107214522 0.034047968142600006
+ block caching 0.11117954749999999 0.03418883708778419
+ parallelization 0.1469377231 0.04518483830954469
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,7 +1520,6 @@ 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 0.982 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>