You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/23 04:41:54 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@3bd168194f25c95904dac8835f8e74abd423a5a3)
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 8329e7b42 deploying docs (apache/tvm@3bd168194f25c95904dac8835f8e74abd423a5a3)
8329e7b42 is described below
commit 8329e7b427b49e67adaefaaafb95b06c75ec9d54
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Aug 23 04:41:49 2022 +0000
deploying docs (apache/tvm@3bd168194f25c95904dac8835f8e74abd423a5a3)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../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 | 11 +-
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 436 +++------------------
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +--
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 24 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 30 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 99 ++++-
docs/how_to/deploy_models/deploy_prequantized.html | 12 +-
.../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 | 39 +-
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 | 8 +-
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 | 7 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 436 +++------------------
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/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 | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++++++------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 41 +-
121 files changed, 1009 insertions(+), 1569 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 99028cd67..71d7adca2 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.056 seconds)
+ **Total running time of the script:** ( 1 minutes 5.183 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 3d8b59edc..bd5dfaee5 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.zip5e93e5f9-0f00-4ee4-bfe8-0ec95c79834b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7ce9fca2-9896-4744-b2c7-01ee7f02a909 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 610207d96..8af8fab42 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 21.6MB/s]
20%|## | 8.40M/41.5M [00:00<00:01, 18.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 30.8MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.0MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 39.7MB/s]
87%|########7 | 36.2M/41.5M [00:01<00:00, 38.1MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 32.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 31.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 44.6MB/s]
26%|##5 | 10.6M/41.5M [00:00<00:00, 33.9MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 33.0MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 37.5MB/s]
63%|######2 | 26.0M/41.5M [00:00<00:00, 34.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.2MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 45.6MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.8MB/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 7c7721d7d..346b53428 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
16%|#6 | 7.20M/44.7M [00:00<00:00, 75.4MB/s]
36%|###6 | 16.2M/44.7M [00:00<00:00, 85.9MB/s]
55%|#####4 | 24.3M/44.7M [00:00<00:00, 53.4MB/s]
85%|########4 | 38.0M/44.7M [00:00<00:00, 79.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 81.1MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
3%|3 | 1.56M/44.7M [00:00<00:02, 16.2MB/s]
10%|# | 4.49M/44.7M [00:00<00:01, 24.4MB/s]
16%|#5 | 6.98M/44.7M [00:00<00:01, 25.0MB/s]
21%|## | 9.37M/44.7M [00:00<00:01, 24.4MB/s]
27%|##7 | 12.2M/44.7M [00:00<00:01, 26.0MB/s]
33%|###2 | 14.7M/44.7M [00:00<00:01, 24.8MB/s]
38%|###8 | 17.0M/44.7M [00:00<00:01, 24.8MB/s]
43%|####3 | 19.4M/44.7M [00:00<00:01, 20.5MB/s]
48%|####8 | 21.5M/44.7M [00:01<00:01, 20.5MB/s]
55%|#####4 | 24.4M/44.7M [00:01<00:00, 22.7MB/s]
61%|######1 | 27.4M/44.7M [00:01<00:00, 24.6MB/s]
68%|######7 | 30.4M/44.7M [00:01<00:00, 26.0MB/s]
74%|#######3 | 32.9M/44.7M [00:01<00:00, 24.7MB/s]
79%|#######9 | 35.3M/44.7M [00:01<00:00, 23.0MB/s]
84%|########4 | 37.5M/44.7M [00:01<00:00, 22.7MB/s]
89%|########9 | 39.8M/44.7M [00:01<00:00, 22.9MB/s]
94%|#########4| 42.0M/44.7M [00
:01<00:00, 21.9MB/s]
99%|#########8| 44.2M/44.7M [00:02<00:00, 22.1MB/s]
100%|##########| 44.7M/44.7M [00:02<00:00, 23.3MB/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 6338160c4..e31c8aeb3 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.214 seconds)
+ **Total running time of the script:** ( 1 minutes 2.906 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 cefadd59d..fa7245648 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
=================
-**05:02.169** total execution time for **how_to_compile_models** files:
+**05:09.016** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.214 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.183 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:04.056 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.906 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:37.889 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.418 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.890 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.289 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.204 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.538 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.942 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.621 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.060 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.463 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.692 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.549 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.380 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.439 | 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 2fbe4be22..cd0832f49 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.4732 15.4615 15.5507 15.4304 0.0408
+ 16.1330 16.1027 16.2472 16.0808 0.0620
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 ac6657812..f048fcd96 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
11%|# | 18.2M/170M [00:00<00:00, 191MB/s]
24%|##4 | 41.6M/170M [00:00<00:00, 223MB/s]
39%|###9 | 66.4M/170M [00:00<00:00, 240MB/s]
53%|#####3 | 90.2M/170M [00:00<00:00, 244MB/s]
67%|######7 | 114M/170M [00:00<00:00, 248MB/s]
82%|########1 | 139M/170M [00:00<00:00, 249MB/s]
96%|#########5| 162M/170M [00:00<00:00, 249MB/s]
100%|##########| 170M/170M [00:00<00:00, 244MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 1.75M/170M [00:00<00:09, 18.3MB/s]
2%|2 | 3.50M/170M [00:00<00:14, 12.3MB/s]
3%|3 | 5.31M/170M [00:00<00:11, 14.7MB/s]
4%|4 | 6.88M/170M [00:00<00:11, 14.9MB/s]
5%|4 | 8.38M/170M [00:00<00:11, 14.6MB/s]
6%|5 | 10.0M/170M [00:00<00:11, 14.3MB/s]
7%|6 | 11.5M/170M [00:00<00:11, 14.6MB/s]
8%|7 | 12.9M/170M [00:00<00:12, 12.8MB/s]
8%|8 | 14.2M/170M [00:01<00:13, 11.8MB/s]
9%|9 | 15.4M/170M [00:01<00:14, 11.3MB/s]
10%|9 | 16.9M/170M [00:01<00:13, 12.3MB/s]
11%|#1 | 18.7M/170M [00:01<00:11, 13.8MB/s]
12%|#2 | 20.4M/170M [00:01<00:10, 14.7MB/s]
13%|#3 | 22.4M/170M [00:01<00:09, 15.9MB/s]
14%|#4 | 23.9M/170M [00:01<00:09, 15.6MB/s]
15%|#4 | 25.4M/170M [00:01<00:09, 15.4MB/s]
16%|#5 | 26.9M/170M [00:02<00:13, 11.1MB/
s]
17%|#6 | 28.1M/170M [00:02<00:14, 10.0MB/s]
17%|#7 | 29.2M/170M [00:02<00:15, 9.82MB/s]
18%|#7 | 30.3M/170M [00:02<00:14, 10.0MB/s]
19%|#8 | 32.0M/170M [00:02<00:12, 11.9MB/s]
20%|#9 | 33.8M/170M [00:02<00:10, 13.4MB/s]
21%|## | 35.6M/170M [00:02<00:09, 14.4MB/s]
22%|##1 | 37.1M/170M [00:02<00:09, 13.9MB/s]
23%|##2 | 39.1M/170M [00:03<00:08, 15.7MB/s]
24%|##4 | 41.1M/170M [00:03<00:07, 17.1MB/s]
25%|##5 | 42.7M/170M [00:03<00:07, 17.1MB/s]
26%|##6 | 44.4M/170M [00:03<00:08, 15.3MB/s]
27%|##7 | 46.0M/170M [00:03<00:08, 15.6MB/s]
28%|##7 | 47.5M/170M [00:03<00:08, 14.8MB/s]
29%|##8 | 49.0M/170M [00:03<00:09, 13.9MB/s]
30%|##9 | 50.4M/170M [00:03<00:09, 13.8MB/s]
31%|### | 52.2M/170M [00:03<00:08, 14.5MB/s]
32%|###1 | 53.6M/170M [00:04<00:08, 14.5MB/s]
32%|###2 | 55.0M/170M [00:04<00:
08, 13.8MB/s]
33%|###3 | 56.3M/170M [00:04<00:10, 11.0MB/s]
34%|###3 | 57.4M/170M [00:04<00:11, 9.93MB/s]
35%|###4 | 59.3M/170M [00:04<00:09, 12.1MB/s]
36%|###5 | 61.0M/170M [00:04<00:09, 12.6MB/s]
37%|###7 | 63.4M/170M [00:04<00:07, 15.5MB/s]
38%|###8 | 65.0M/170M [00:05<00:07, 14.8MB/s]
39%|###9 | 66.4M/170M [00:05<00:07, 14.6MB/s]
40%|#### | 68.1M/170M [00:05<00:07, 15.1MB/s]
41%|#### | 69.5M/170M [00:05<00:07, 13.7MB/s]
42%|####1 | 71.2M/170M [00:05<00:07, 14.5MB/s]
43%|####3 | 73.2M/170M [00:05<00:06, 16.1MB/s]
44%|####4 | 75.4M/170M [00:05<00:05, 18.0MB/s]
46%|####5 | 77.6M/170M [00:05<00:05, 19.2MB/s]
47%|####6 | 79.8M/170M [00:05<00:04, 19.4MB/s]
48%|####8 | 82.1M/170M [00:05<00:04, 20.8MB/s]
50%|####9 | 84.2M/170M [00:06<00:04, 21.3MB/s]
51%|#####1 | 87.2M/170M [00:06<00:03, 24.2MB/s]
53%|#####2 | 89.6M/170M
[00:06<00:03, 24.2MB/s]
54%|#####4 | 91.9M/170M [00:06<00:03, 22.6MB/s]
55%|#####5 | 94.1M/170M [00:06<00:03, 21.5MB/s]
57%|#####6 | 96.2M/170M [00:06<00:03, 21.4MB/s]
58%|#####8 | 98.6M/170M [00:06<00:03, 22.0MB/s]
59%|#####9 | 101M/170M [00:06<00:03, 22.8MB/s]
61%|######1 | 104M/170M [00:06<00:02, 24.7MB/s]
63%|######3 | 108M/170M [00:07<00:02, 23.3MB/s]
65%|######4 | 110M/170M [00:07<00:02, 20.9MB/s]
67%|######6 | 113M/170M [00:07<00:02, 23.8MB/s]
68%|######8 | 116M/170M [00:07<00:03, 18.5MB/s]
69%|######9 | 118M/170M [00:07<00:03, 17.5MB/s]
70%|####### | 119M/170M [00:07<00:02, 17.8MB/s]
72%|#######1 | 122M/170M [00:07<00:02, 19.7MB/s]
74%|#######3 | 125M/170M [00:08<00:02, 22.2MB/s]
75%|#######4 | 127M/170M [00:08<00:02, 15.1MB/s]
76%|#######5 | 129M/170M [00:08<00:03, 13.0MB/s]
77%|#######7 | 131M/170M [00:08<00:02, 14.0MB/s]
78%|#######8 | 132M/170M [
00:08<00:02, 14.0MB/s]
79%|#######8 | 134M/170M [00:08<00:02, 13.9MB/s]
80%|#######9 | 135M/170M [00:09<00:03, 10.8MB/s]
81%|######## | 137M/170M [00:09<00:03, 10.0MB/s]
81%|########1 | 138M/170M [00:09<00:03, 10.7MB/s]
82%|########1 | 139M/170M [00:09<00:03, 10.7MB/s]
83%|########2 | 141M/170M [00:09<00:02, 11.8MB/s]
85%|########5 | 145M/170M [00:09<00:01, 19.7MB/s]
87%|########6 | 147M/170M [00:09<00:01, 21.6MB/s]
89%|########8 | 151M/170M [00:09<00:00, 25.3MB/s]
90%|######### | 153M/170M [00:10<00:00, 23.0MB/s]
92%|#########1| 156M/170M [00:10<00:00, 20.5MB/s]
93%|#########2| 158M/170M [00:10<00:00, 16.7MB/s]
94%|#########4| 160M/170M [00:10<00:00, 18.1MB/s]
96%|#########5| 162M/170M [00:10<00:00, 19.0MB/s]
97%|#########7| 165M/170M [00:10<00:00, 21.5MB/s]
99%|#########8| 167M/170M [00:10<00:00, 20.9MB/s]
100%|#########9| 169M/170M [00:10<00:00, 20.4MB/s]
100%|##########| 170M/170M [00:11<0
0:00, 16.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 48.457 seconds)
+ **Total running time of the script:** ( 3 minutes 11.654 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 bafe55b77..f72400851 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
14%|#4 | 1.94M/13.6M [00:00<00:00, 19.9MB/s]
29%|##8 | 3.88M/13.6M [00:00<00:00, 20.0MB/s]
44%|####3 | 5.94M/13.6M [00:00<00:00, 20.7MB/s]
59%|#####8 | 7.94M/13.6M [00:00<00:00, 20.4MB/s]
73%|#######2 | 9.89M/13.6M [00:00<00:00, 20.0MB/s]
87%|########7 | 11.8M/13.6M [00:00<00:00, 17.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 19.1MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.0580 89.9606 95.2509 89.7288 0.5749
+ 90.4607 90.4614 91.4691 90.1497 0.2161
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.245 seconds)
+ **Total running time of the script:** ( 1 minutes 11.665 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 be4f44766..e00a70b43 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 117.1479 116.9031 122.6961 116.1215 0.9819
+ 120.7069 120.6746 122.2613 119.9769 0.3762
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 50.548 seconds)
+ **Total running time of the script:** ( 1 minutes 52.654 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 710a34889..79db5ea8c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 46.489 seconds)
+ **Total running time of the script:** ( 1 minutes 34.300 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 9370f9795..9792afe3c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4595/132723 [00:00<00:02, 45944.79KB/s]
9%|8 | 11779/132723 [00:00<00:01, 61159.86KB/s]
15%|#5 | 20365/132723 [00:00<00:01, 72433.78KB/s]
22%|##1 | 28817/132723 [00:00<00:01, 77202.30KB/s]
28%|##8 | 37207/132723 [00:00<00:01, 79616.50KB/s]
34%|###4 | 45752/132723 [00:00<00:01, 81596.67KB/s]
41%|#### | 53912/132723 [00:00<00:01, 69598.89KB/s]
47%|####7 | 62405/132723 [00:00<00:00, 73963.36KB/s]
53%|#####3 | 70879/132723 [00:00<00:00, 77079.31KB/s]
60%|#####9 | 79467/132723 [00:01<00:00, 79650.18KB/s]
66%|######5 | 87579/132723 [00:01<00:00, 64943.93KB/s]
72%|#######2 | 96121/132723 [00:01<00:00, 70148.78KB/s]
78%|#######8 | 103600/132723 [00:01<00:00, 51644.42KB/s]
84%|########4 | 112053/132723 [00:01<00:00, 58747.25KB/s]
90%|########9 | 119178/132723 [00:01<00:00, 61693.81KB/s]
96%|########
#6| 127584/132723 [00:01<00:00, 67328.86KB/s]
100%|##########| 132723/132723 [00:01<00:00, 68495.38KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1140/132723 [00:00<00:11, 11244.17KB/s]
3%|2 | 3670/132723 [00:00<00:06, 19463.91KB/s]
7%|6 | 8754/132723 [00:00<00:03, 33682.02KB/s]
12%|#1 | 15570/132723 [00:00<00:02, 47246.20KB/s]
17%|#7 | 23145/132723 [00:00<00:01, 57500.84KB/s]
23%|##3 | 30841/132723 [00:00<00:01, 64104.87KB/s]
29%|##8 | 38451/132723 [00:00<00:01, 68020.56KB/s]
35%|###4 | 45935/132723 [00:00<00:01, 70185.95KB/s]
40%|#### | 53211/132723 [00:00<00:01, 70989.46KB/s]
46%|####5 | 60606/132723 [00:01<00:01, 71900.33KB/s]
51%|#####1 | 68231/132723 [00:01<00:00, 73228.81KB/s]
57%|#####7 | 75883/132723 [00:01<00:00, 74226.98KB/s]
63%|######2 | 83505/132723 [00:01<00:00, 74819.95KB/s]
69%|######8 | 91090/132723 [00:01<00:00, 75128.65KB/s]
74%|#######4 | 98736/132723 [00:01<00:00, 75524.86KB/s]
80%|######## | 1
06411/132723 [00:01<00:00, 75892.01KB/s]
86%|########6 | 114241/132723 [00:01<00:00, 76614.04KB/s]
92%|#########1| 121903/132723 [00:01<00:00, 54333.00KB/s]
98%|#########7| 129512/132723 [00:02<00:00, 59409.21KB/s]
100%|##########| 132723/132723 [00:02<00:00, 63800.38KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 32.114 seconds)
+ **Total running time of the script:** ( 2 minutes 39.966 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 2225f8181..7b0075a26 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:17.038** total execution time for **how_to_deploy_models** files:
+**11:45.727** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:48.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:11.654 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:32.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:39.966 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:50.548 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.654 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:46.489 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.300 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.245 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.665 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.877 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.487 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:21.762 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.733 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.540 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.262 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 13fe337f6..f24ba50e1 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4bb6c9f4-20f2-4207-8f4e-5e1c54f3371c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9c5cf530-9743-4560-be15-86ae3f0b2e2b 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 59d7a520c..23586dbd9 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
=================
-**00:39.579** total execution time for **how_to_extend_tvm** files:
+**00:41.940** 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``) | 00:36.514 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.656 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.148 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.297 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.910 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.979 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 079b87c6d..3da4f122f 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: 7191us [7191us] (47.53%; 47.53%)
- FoldScaleAxis: 7939us [5us] (52.47%; 52.47%)
- FoldConstant: 7934us [1674us] (52.44%; 99.93%)
- InferType: 6260us [6260us] (41.37%; 78.90%)
+ InferType: 7209us [7209us] (45.72%; 45.72%)
+ FoldScaleAxis: 8559us [7us] (54.28%; 54.28%)
+ FoldConstant: 8551us [1741us] (54.23%; 99.91%)
+ InferType: 6810us [6810us] (43.19%; 79.64%)
@@ -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: 6308us [6308us] (44.48%; 44.48%)
- FoldScaleAxis: 7875us [4us] (55.52%; 55.52%)
- FoldConstant: 7870us [1650us] (55.49%; 99.94%)
- InferType: 6220us [6220us] (43.86%; 79.03%)
+ InferType: 7124us [7124us] (46.22%; 46.22%)
+ FoldScaleAxis: 8290us [7us] (53.78%; 53.78%)
+ FoldConstant: 8283us [1727us] (53.74%; 99.92%)
+ InferType: 6556us [6556us] (42.54%; 79.15%)
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 d7d86d45d..37a80378f 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: 54.206375 ms
+ Convolution: 54.190404 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 0b1df02bc..4dc23c6ae 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.715396 ms
+ conv2d with tensor core: 6.917566 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 b571ace0e..ff7d9075a 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: 0.017579
- Baseline: 3.292179
+ Numpy running time: 0.018948
+ Baseline: 3.193578
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.300895
+ Opt1: 0.308097
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335761
+ Opt2: 0.347311
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.112381
+ Opt3: 0.116828
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108402
+ Opt4: 0.109662
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110583
+ Opt5: 0.111108
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.145946
+ Opt6: 0.147767
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 c07dc0424..c7c397ed1 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
=================
-**00:33.825** total execution time for **how_to_optimize_operators** files:
+**00:34.161** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.681 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.963 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.182 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.205 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.994 | 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 606200abc..0b147596c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:04.137** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:26.490** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:19.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:36.108 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.433 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.688 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.864 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.997 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:20.774 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.624 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.132 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.478 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.925 | 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 3d87a5cdf..b07ee45bf 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
@@ -206,6 +206,13 @@ file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+
+ .T
+
@@ -771,7 +778,7 @@ 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: 0.376 ms
@@ -1378,7 +1385,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 19.491 seconds)
+ **Total running time of the script:** ( 3 minutes 36.108 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 3a69823d9..079b3a378 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5737 9.5662 9.5977 9.5571 0.0174
+ 10.1971 10.2290 10.2522 10.1100 0.0623
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 6830a500c..a5daea7ef 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 749.6334 748.8467 751.4610 748.5924 1.2965
+ 752.8325 753.0056 753.0691 752.4229 0.2908
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.433 seconds)
+ **Total running time of the script:** ( 1 minutes 23.688 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 0144028ab..af6fdb5de 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,15 +397,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = ((i.outer.inner*256) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -421,387 +420,54 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 13)] = 0f32
compute_5[(cse_var_1 + 14)] = 0f32
compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- compute_5[(cse_var_1 + 128)] = 0f32
- compute_5[(cse_var_1 + 129)] = 0f32
- compute_5[(cse_var_1 + 130)] = 0f32
- compute_5[(cse_var_1 + 131)] = 0f32
- compute_5[(cse_var_1 + 132)] = 0f32
- compute_5[(cse_var_1 + 133)] = 0f32
- compute_5[(cse_var_1 + 134)] = 0f32
- compute_5[(cse_var_1 + 135)] = 0f32
- compute_5[(cse_var_1 + 136)] = 0f32
- compute_5[(cse_var_1 + 137)] = 0f32
- compute_5[(cse_var_1 + 138)] = 0f32
- compute_5[(cse_var_1 + 139)] = 0f32
- compute_5[(cse_var_1 + 140)] = 0f32
- compute_5[(cse_var_1 + 141)] = 0f32
- compute_5[(cse_var_1 + 142)] = 0f32
- compute_5[(cse_var_1 + 143)] = 0f32
- compute_5[(cse_var_1 + 160)] = 0f32
- compute_5[(cse_var_1 + 161)] = 0f32
- compute_5[(cse_var_1 + 162)] = 0f32
- compute_5[(cse_var_1 + 163)] = 0f32
- compute_5[(cse_var_1 + 164)] = 0f32
- compute_5[(cse_var_1 + 165)] = 0f32
- compute_5[(cse_var_1 + 166)] = 0f32
- compute_5[(cse_var_1 + 167)] = 0f32
- compute_5[(cse_var_1 + 168)] = 0f32
- compute_5[(cse_var_1 + 169)] = 0f32
- compute_5[(cse_var_1 + 170)] = 0f32
- compute_5[(cse_var_1 + 171)] = 0f32
- compute_5[(cse_var_1 + 172)] = 0f32
- compute_5[(cse_var_1 + 173)] = 0f32
- compute_5[(cse_var_1 + 174)] = 0f32
- compute_5[(cse_var_1 + 175)] = 0f32
- compute_5[(cse_var_1 + 192)] = 0f32
- compute_5[(cse_var_1 + 193)] = 0f32
- compute_5[(cse_var_1 + 194)] = 0f32
- compute_5[(cse_var_1 + 195)] = 0f32
- compute_5[(cse_var_1 + 196)] = 0f32
- compute_5[(cse_var_1 + 197)] = 0f32
- compute_5[(cse_var_1 + 198)] = 0f32
- compute_5[(cse_var_1 + 199)] = 0f32
- compute_5[(cse_var_1 + 200)] = 0f32
- compute_5[(cse_var_1 + 201)] = 0f32
- compute_5[(cse_var_1 + 202)] = 0f32
- compute_5[(cse_var_1 + 203)] = 0f32
- compute_5[(cse_var_1 + 204)] = 0f32
- compute_5[(cse_var_1 + 205)] = 0f32
- compute_5[(cse_var_1 + 206)] = 0f32
- compute_5[(cse_var_1 + 207)] = 0f32
- compute_5[(cse_var_1 + 224)] = 0f32
- compute_5[(cse_var_1 + 225)] = 0f32
- compute_5[(cse_var_1 + 226)] = 0f32
- compute_5[(cse_var_1 + 227)] = 0f32
- compute_5[(cse_var_1 + 228)] = 0f32
- compute_5[(cse_var_1 + 229)] = 0f32
- compute_5[(cse_var_1 + 230)] = 0f32
- compute_5[(cse_var_1 + 231)] = 0f32
- compute_5[(cse_var_1 + 232)] = 0f32
- compute_5[(cse_var_1 + 233)] = 0f32
- compute_5[(cse_var_1 + 234)] = 0f32
- compute_5[(cse_var_1 + 235)] = 0f32
- compute_5[(cse_var_1 + 236)] = 0f32
- compute_5[(cse_var_1 + 237)] = 0f32
- compute_5[(cse_var_1 + 238)] = 0f32
- compute_5[(cse_var_1 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_131: int32 = (i.outer.inner*2048)
- let cse_var_130: int32 = (elem_idx*16)
- let cse_var_129: int32 = (cse_var_1 + 99)
- let cse_var_128: int32 = (cse_var_1 + 98)
- let cse_var_127: int32 = (cse_var_1 + 97)
- let cse_var_126: int32 = (cse_var_1 + 96)
- let cse_var_125: int32 = (cse_var_1 + 9)
- let cse_var_124: int32 = (cse_var_1 + 8)
- let cse_var_123: int32 = (cse_var_1 + 79)
- let cse_var_122: int32 = (cse_var_1 + 78)
- let cse_var_121: int32 = (cse_var_1 + 77)
- let cse_var_120: int32 = (cse_var_1 + 76)
- let cse_var_119: int32 = (cse_var_1 + 75)
- let cse_var_118: int32 = (cse_var_1 + 74)
- let cse_var_117: int32 = (cse_var_1 + 73)
- let cse_var_116: int32 = (cse_var_1 + 72)
- let cse_var_115: int32 = (cse_var_1 + 71)
- let cse_var_114: int32 = (cse_var_1 + 70)
- let cse_var_113: int32 = (cse_var_1 + 7)
- let cse_var_112: int32 = (cse_var_1 + 69)
- let cse_var_111: int32 = (cse_var_1 + 68)
- let cse_var_110: int32 = (cse_var_1 + 67)
- let cse_var_109: int32 = (cse_var_1 + 66)
- let cse_var_108: int32 = (cse_var_1 + 65)
- let cse_var_107: int32 = (cse_var_1 + 64)
- let cse_var_106: int32 = (cse_var_1 + 6)
- let cse_var_105: int32 = (cse_var_1 + 5)
- let cse_var_104: int32 = (cse_var_1 + 47)
- let cse_var_103: int32 = (cse_var_1 + 46)
- let cse_var_102: int32 = (cse_var_1 + 45)
- let cse_var_101: int32 = (cse_var_1 + 44)
- let cse_var_100: int32 = (cse_var_1 + 43)
- let cse_var_99: int32 = (cse_var_1 + 42)
- let cse_var_98: int32 = (cse_var_1 + 41)
- let cse_var_97: int32 = (cse_var_1 + 40)
- let cse_var_96: int32 = (cse_var_1 + 4)
- let cse_var_95: int32 = (cse_var_1 + 39)
- let cse_var_94: int32 = (cse_var_1 + 38)
- let cse_var_93: int32 = (cse_var_1 + 37)
- let cse_var_92: int32 = (cse_var_1 + 36)
- let cse_var_91: int32 = (cse_var_1 + 35)
- let cse_var_90: int32 = (cse_var_1 + 34)
- let cse_var_89: int32 = (cse_var_1 + 33)
- let cse_var_88: int32 = (cse_var_1 + 32)
- let cse_var_87: int32 = (cse_var_1 + 3)
- let cse_var_86: int32 = (cse_var_1 + 239)
- let cse_var_85: int32 = (cse_var_1 + 238)
- let cse_var_84: int32 = (cse_var_1 + 237)
- let cse_var_83: int32 = (cse_var_1 + 236)
- let cse_var_82: int32 = (cse_var_1 + 235)
- let cse_var_81: int32 = (cse_var_1 + 234)
- let cse_var_80: int32 = (cse_var_1 + 233)
- let cse_var_79: int32 = (cse_var_1 + 232)
- let cse_var_78: int32 = (cse_var_1 + 231)
- let cse_var_77: int32 = (cse_var_1 + 230)
- let cse_var_76: int32 = (cse_var_1 + 229)
- let cse_var_75: int32 = (cse_var_1 + 228)
- let cse_var_74: int32 = (cse_var_1 + 227)
- let cse_var_73: int32 = (cse_var_1 + 226)
- let cse_var_72: int32 = (cse_var_1 + 225)
- let cse_var_71: int32 = (cse_var_1 + 224)
- let cse_var_70: int32 = (cse_var_1 + 207)
- let cse_var_69: int32 = (cse_var_1 + 206)
- let cse_var_68: int32 = (cse_var_1 + 205)
- let cse_var_67: int32 = (cse_var_1 + 204)
- let cse_var_66: int32 = (cse_var_1 + 203)
- let cse_var_65: int32 = (cse_var_1 + 202)
- let cse_var_64: int32 = (cse_var_1 + 201)
- let cse_var_63: int32 = (cse_var_1 + 200)
- let cse_var_62: int32 = (cse_var_1 + 2)
- let cse_var_61: int32 = (cse_var_1 + 199)
- let cse_var_60: int32 = (cse_var_1 + 198)
- let cse_var_59: int32 = (cse_var_1 + 197)
- let cse_var_58: int32 = (cse_var_1 + 196)
- let cse_var_57: int32 = (cse_var_1 + 195)
- let cse_var_56: int32 = (cse_var_1 + 194)
- let cse_var_55: int32 = (cse_var_1 + 193)
- let cse_var_54: int32 = (cse_var_1 + 192)
- let cse_var_53: int32 = (cse_var_1 + 175)
- let cse_var_52: int32 = (cse_var_1 + 174)
- let cse_var_51: int32 = (cse_var_1 + 173)
- let cse_var_50: int32 = (cse_var_1 + 172)
- let cse_var_49: int32 = (cse_var_1 + 171)
- let cse_var_48: int32 = (cse_var_1 + 170)
- let cse_var_47: int32 = (cse_var_1 + 169)
- let cse_var_46: int32 = (cse_var_1 + 168)
- let cse_var_45: int32 = (cse_var_1 + 167)
- let cse_var_44: int32 = (cse_var_1 + 166)
- let cse_var_43: int32 = (cse_var_1 + 165)
- let cse_var_42: int32 = (cse_var_1 + 164)
- let cse_var_41: int32 = (cse_var_1 + 163)
- let cse_var_40: int32 = (cse_var_1 + 162)
- let cse_var_39: int32 = (cse_var_1 + 161)
- let cse_var_38: int32 = (cse_var_1 + 160)
- let cse_var_37: int32 = (cse_var_1 + 15)
- let cse_var_36: int32 = (cse_var_1 + 143)
- let cse_var_35: int32 = (cse_var_1 + 142)
- let cse_var_34: int32 = (cse_var_1 + 141)
- let cse_var_33: int32 = (cse_var_1 + 140)
- let cse_var_32: int32 = (cse_var_1 + 14)
- let cse_var_31: int32 = (cse_var_1 + 139)
- let cse_var_30: int32 = (cse_var_1 + 138)
- let cse_var_29: int32 = (cse_var_1 + 137)
- let cse_var_28: int32 = (cse_var_1 + 136)
- let cse_var_27: int32 = (cse_var_1 + 135)
- let cse_var_26: int32 = (cse_var_1 + 134)
- let cse_var_25: int32 = (cse_var_1 + 133)
- let cse_var_24: int32 = (cse_var_1 + 132)
- let cse_var_23: int32 = (cse_var_1 + 131)
- let cse_var_22: int32 = (cse_var_1 + 130)
- let cse_var_21: int32 = (cse_var_1 + 13)
- let cse_var_20: int32 = (cse_var_1 + 129)
- let cse_var_19: int32 = (cse_var_1 + 128)
- let cse_var_18: int32 = (cse_var_1 + 12)
- let cse_var_17: int32 = (cse_var_1 + 111)
- let cse_var_16: int32 = (cse_var_1 + 110)
- let cse_var_15: int32 = (cse_var_1 + 11)
- let cse_var_14: int32 = (cse_var_1 + 109)
- let cse_var_13: int32 = (cse_var_1 + 108)
- let cse_var_12: int32 = (cse_var_1 + 107)
- let cse_var_11: int32 = (cse_var_1 + 106)
- let cse_var_10: int32 = (cse_var_1 + 105)
- let cse_var_9: int32 = (cse_var_1 + 104)
- let cse_var_8: int32 = (cse_var_1 + 103)
- let cse_var_7: int32 = (cse_var_1 + 102)
- let cse_var_6: int32 = (cse_var_1 + 101)
- let cse_var_5: int32 = (cse_var_1 + 100)
- let cse_var_4: int32 = (cse_var_1 + 10)
- let cse_var_3: int32 = (cse_var_1 + 1)
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- }
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*256) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_132: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_132] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_132]), 0f32)
- }
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -857,7 +523,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.738 ms
+ Execution time of this operator: 3.794 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 de2c7b4d1..86a3cdeec 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:46.184** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.063** 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``) | 00:46.149 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.027 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index ad8bce8e6..d78a9870c 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 218.99/218.99 result: MeasureResult(costs=(0.0010571545379310344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.079108715057373, timestamp=1661217302.0073135) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/218.99 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 190.64/190.64 result: MeasureResult(costs=(0.001214353688888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0405170917510986, timestamp=1661223302.3894737) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/190.64 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 261.25/261.25 result: MeasureResult(costs=(0.0008861356353591159,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5200226306915283, timestamp=1661217302.9286811) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 261.03/261.03 result: MeasureResult(costs=(0.0008868875856353593,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4918577671051025, timestamp=1661223303.3155913) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.26/261.25 result: MeasureResult(costs=(0.0440128,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8412563800811768, timestamp=1661217307.455042) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.35/261.25 result: MeasureResult(costs=(0.06915911549999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.495361804962158, timestamp=1661217308.6873507) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.30/261.03 result: MeasureResult(costs=(0.043679146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8481605052947998, timestamp=1661223307.8777392) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.35/261.03 result: MeasureResult(costs=(0.06918789099999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.568289518356323, timestamp=1661223309.1209316) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.21/261.25 result: MeasureResult(costs=(0.008205208785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2629334926605225, timestamp=1661217319.746553) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.14/261.03 result: MeasureResult(costs=(0.00822618042857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3182265758514404, timestamp=1661223320.137157) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001239
+ Time cost of this operator: 0.001249
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 ea324af87..b25d65bd7 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.745 (1, 2, 10, 10, 3) 2 1 [312.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.015 0.953 (1, 6, 10, 10) 1 1 [3.015]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.301 (1, 1, 10, 10, 3) 1 1 [0.953]
- Total_time - 316.268 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.2 98.74 (1, 2, 10, 10, 3) 2 1 [312.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.954 (1, 6, 10, 10) 1 1 [3.017]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 0.305 (1, 1, 10, 10, 3) 1 1 [0.966]
+ Total_time - 316.183 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.188 96.595 (1, 6, 10, 10, 1) 2 1 [79.188]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.823 2.224 (1, 6, 10, 10) 1 1 [1.823]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 1.181 (1, 1, 10, 10, 3) 1 1 [0.968]
- Total_time - 81.979 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.188 96.302 (1, 6, 10, 10, 1) 2 1 [80.188]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.113 2.538 (1, 6, 10, 10) 1 1 [2.113]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.161 (1, 1, 10, 10, 3) 1 1 [0.967]
+ Total_time - 83.267 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 663576f86..08b4485e8 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/tmp7_d2xnt8/images/random'
+ '/tmp/tmpfzv5euk8/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp7_d2xnt8/images/target contains 8144 images
- /tmp/tmp7_d2xnt8/images/random contains 5000 images
+ /tmp/tmpfzv5euk8/images/target contains 8144 images
+ /tmp/tmpfzv5euk8/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2162 - accuracy: 0.9253 - val_loss: 0.1505 - val_accuracy: 0.9619
+ 328/328 - 56s - loss: 0.2175 - accuracy: 0.9259 - val_loss: 0.1425 - val_accuracy: 0.9539
Epoch 2/3
- 328/328 - 52s - loss: 0.0934 - accuracy: 0.9637 - val_loss: 0.1192 - val_accuracy: 0.9634
+ 328/328 - 53s - loss: 0.0971 - accuracy: 0.9627 - val_loss: 0.1365 - val_accuracy: 0.9603
Epoch 3/3
- 328/328 - 52s - loss: 0.0662 - accuracy: 0.9749 - val_loss: 0.1217 - val_accuracy: 0.9615
+ 328/328 - 52s - loss: 0.0645 - accuracy: 0.9758 - val_loss: 0.1089 - val_accuracy: 0.9630
- <keras.callbacks.History object at 0x7f52764f1650>
+ <keras.callbacks.History object at 0x7efbda0bd710>
@@ -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:** ( 5 minutes 44.227 seconds)
+ **Total running time of the script:** ( 5 minutes 14.122 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 616a67281..7e43669a4 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:36.262** total execution time for **how_to_work_with_microtvm** files:
+**06:08.305** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:44.227 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:14.122 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.173 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.997 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.700 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.824 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.160 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.360 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 323f136c2..2c5554559 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
=================
-**00:42.096** total execution time for **how_to_work_with_relay** files:
+**00:43.005** 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``) | 00:30.680 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.552 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.887 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.957 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.522 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.489 | 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 b22d2e5a5..1f10a4e75 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 0x7f52863d5560>
+ <function my_cuda_math_rule at 0x7efb5147ab00>
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 809a5a9e8..a9d2cbb88 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.047** total execution time for **how_to_work_with_schedules** files:
+**00:04.110** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.860 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.904 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.952 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.961 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.543 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.535 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.508 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.522 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.105 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 2a3bb8d05..4dc092529 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmptu42ibgx/input0.cc'\nsource_filename = \"/tmp/tmptu42ibgx/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/tmpzh40kt43/input0.cc'\nsource_filename = \"/tmp/tmpzh40kt43/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 6435126f3..d4242422b 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:20.768** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.007** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.762 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.000 | 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 d72c53d55..9130fc38b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.10s!
+ resnet18_v1 inference graph built in 24.09s!
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 6b2a18d84..ee9e845df 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.61s!
+ yolov3-tiny inference graph built in 16.67s!
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 cae3dd63d..f55b4523c 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
=================
-**01:30.862** total execution time for **topic_vta_tutorials_frontend** files:
+**01:34.006** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.567 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.779 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.295 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.227 | 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 9403cee0b..764660c02 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
=================
-**00:03.355** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.295** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.964 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.893 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.402 | 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 b4a57a129..8bbdf9518 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
=================
-**00:00.717** total execution time for **topic_vta_tutorials** files:
+**00:00.728** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.384 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.390 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.332 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.337 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 00791a808..e19582a83 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.270 ms
+ Execution time of this operator: 93.418 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 2f8228f4f..291be7422 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 8.68/8.68 result: MeasureResult(costs=(0.030935066599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6275863647460938, timestamp=1661216099.8888297) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.79/8.68 result: MeasureResult(costs=(0.0961245438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.675877332687378, timestamp=1661216101.5898263) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227199812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5541176795959473, timestamp=1661216102.6364021) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.62/11.81 result: MeasureResult(costs=(0.1656084674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.774251937866211, timestamp=1661216105.4520175) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.81 result: MeasureResult(costs=(0.07362594880000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3154656887054443, timestamp=1661216106.8993685) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.78/11.81 result: MeasureResult(costs=(0.1509724626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5314786434173584, timestamp=1661216109.99056) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.81 result: MeasureResult(costs=(0.3077099968,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.043766021728516, timestamp=1661216115.6117537) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.70/11.81 result: MeasureResult(costs=(0.025087378799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5462484359741211, timestamp=1661216116.175242) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.90/11.81 result: MeasureResult(costs=(0.14124858540000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3613462448120117, timestamp=1661216118.6552758) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.80/11.81 result: MeasureResult(costs=(0.0959906124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6528677940368652, timestamp=1661216120.3605332) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.60/10.60 result: MeasureResult(costs=(0.0253293276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5417864322662354, timestamp=1661222060.6588657) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.93/10.60 result: MeasureResult(costs=(0.0916276196,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6544721126556396, timestamp=1661222062.3304863) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022690931,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.555365800857544, timestamp=1661222063.3976574) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.61/11.83 result: MeasureResult(costs=(0.1667162632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7817206382751465, timestamp=1661222066.779948) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.58/11.83 result: MeasureResult(costs=(0.0748927196,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3341362476348877, timestamp=1661222068.2407663) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.74/11.83 result: MeasureResult(costs=(0.15436800479999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.570786952972412, timestamp=1661222070.8539133) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.85/11.83 result: MeasureResult(costs=(0.317051646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.192715883255005, timestamp=1661222076.6295993) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.94/11.83 result: MeasureResult(costs=(0.0270035372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6195971965789795, timestamp=1661222077.26639) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.68/11.83 result: MeasureResult(costs=(0.1599084304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6614413261413574, timestamp=1661222080.0477552) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.46/11.83 result: MeasureResult(costs=(0.1089138932,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.847519874572754, timestamp=1661222081.953327) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 735804623..e1ea7a1ae 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.095531889996, 'median': 496.25740645001315, 'std': 0.9061120950977117}
+ {'mean': 496.46541508000047, 'median': 496.4040101000023, 'std': 0.6307671095444364}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.52/ 17.52 GFLOPS | Progress: (4/20) | 6.41 s
[Task 1/25] Current/Best: 6.14/ 17.52 GFLOPS | Progress: (8/20) | 9.45 s
[Task 1/25] Current/Best: 11.52/ 22.64 GFLOPS | Progress: (12/20) | 11.88 s
[Task 1/25] Current/Best: 16.41/ 22.64 GFLOPS | Progress: (16/20) | 13.59 s
[Task 1/25] Current/Best: 11.22/ 23.67 GFLOPS | Progress: (20/20) | 15.35 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.22/ 12.94 GFLOPS | Progress: (4/20) | 3.69 s
[Task 2/25] Current/Best: 14.18/ 18.65 GFLOPS | Progress: (8/20) | 5.00 s
[Task 2/25] Current/Best: 21.14/ 21.14 GFLOPS | Progress: (12/20) | 6.33 s
[Task 2/25] Current/Best: 12.41/ 21.14 GFLOPS | Progress: (16/20) | 7.58 s
[Task 2/25] Current/Best: 19.87/ 21.14 GFLOPS | Progress: (20/20) | 9.14 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.81 GFLOPS | Progress: (4/20) | 5.90 s
[Task 3/25] Current/Best: 15.31/ 16.77 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.95/ 16.77 GFLOPS | Progress: (12/20) | 9.59 s
[Task 3/25] Current/Best: 7.17/ 23.78 GFLOPS | Progress: (16/20) | 11.50 s
[Task 3/25] Current/Best: 12.61/ 23.78 GFLOPS | Progress: (20/20) | 16.01 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.36/ 18.95 GFLOPS | Progress: (4/20) | 2.43 s
[Task 4/25] Current/Best: 6.83/ 18.95 GFLOPS | Progress: (8/20) | 6.79 s
[Task 4/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (12/20) | 11.36 s
[Task 4/25] Current/Best: 17.12/ 22.19 GFLOPS | Progress: (16/20) | 13.62 s
[Task 4/25] Current/Best: 12.83/ 22.19 GFLOPS | Progress: (20/20) | 15.52 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.52/ 10.10 GFLOPS | Progress: (4/20) | 2.64 s
[Task 5/25] Current/Best: 11.71/ 12.72 GFLOPS | Progress: (8/20) | 4.72 s
[Task 5/25] Current/Best: 11.12/ 18.14 GFLOPS | Progress: (12/20) | 7.70 s
[Task 5/25] Current/Best: 11.64/ 22.67 GFLOPS | Progress: (16/20) | 9.13 s
[Task 5/25] Current/Best: 11.89/ 22.67 GFLOPS | Progress: (20/20) | 11.00 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.19/ 20.74 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 19.01/ 20.74 GFLOPS | Progress: (8/20) | 5.72 s
[Task 6/25] Current/Best: 13.27/ 20.74 GFLOPS | Progress: (12/20) | 7.65 s
[Task 6/25] Current/Best: 20.06/ 20.74 GFLOPS | Progress: (16/20) | 9.89 s
[Task 6/25] Current/Best: 3.74/ 20.74 GFLOPS | Progress: (20/20) | 12.41 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.32/ 12.83 GFLOPS | Progress: (4/20) | 3.51 s
[Task 7/25] Current/Best: 20.51/ 21.37 GFLOPS | Progress: (8/20) | 5.02 s
[Task 7/25] Current/Best: 16.05/ 21.37 GFLOPS | Progress: (12/20) | 6.89 s
[Task 7/25] Current/Best: 12.41/ 21.37 GFLOPS | Progress: (16/20) | 8.89 s
[Task 7/25] Current/Best: 6.33/ 22.04 GFLOPS | Progress: (20/20) | 11.32 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.15/ 14.04 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.57/ 14.04 GFLOPS | Progress: (8/20) | 7.48 s
[Task 8/25] Current/Best: 12.86/ 14.04 GFLOPS | Progress: (12/20) | 13.42 s
[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 15.49 s
[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 21.89 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.52/ 15.93 GFLOPS | Progress: (4/20) | 11.94 s
[Task 9/25] Current/Best: 23.83/ 23.83 GFLOPS | Progress: (8/20) | 13.64 s
[Task 9/25] Current/Best: 8.37/ 23.83 GFLOPS | Progress: (12/20) | 15.97 s
[Task 9/25] Current/Best: 18.21/ 23.83 GFLOPS | Progress: (16/20) | 18.55 s
[Task 9/25] Current/Best: 9.34/ 23.83 GFLOPS | Progress: (20/20) | 25.92 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.52 s
[Task 10/25] Current/Best: 15.61/ 18.34 GFLOPS | Progress: (8/20) | 4.07 s
[Task 10/25] Current/Best: 12.91/ 19.23 GFLOPS | Progress: (12/20) | 5.56 s
[Task 10/25] Current/Best: 19.36/ 20.46 GFLOPS | Progress: (16/20) | 6.65 s
[Task 10/25] Current/Best: 9.02/ 20.46 GFLOPS | Progress: (20/20
) | 8.14 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.35/ 18.46 GFLOPS | Progress: (4/20) | 3.23 s
[Task 11/25] Current/Best: 15.23/ 18.46 GFLOPS | Progress: (8/20) | 5.91 s
[Task 11/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.90 s
[Task 11/25] Current/Best: 13.71/ 21.25 GFLOPS | Progress: (16/20) | 10.55 s
[Task 11/25] Current/Best: 19.74/ 21.81 GFLOPS | Progress: (20/20) | 12.57 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.86/ 18.29 GFLOPS | Progress: (4/20) | 5.19 s
[Task 12/25] Current/Best: 5.19/ 18.29 GFLOPS | Progress: (8/20) | 8.83 s
[Task 12/25] Current/Best: 19.11/ 19.14 GFLOPS | Progress: (12/20) | 10.79 s
[Task 12/25] Current/Best: 15.72/ 19.14 GFLOPS | Progress: (16/20) | 13.54 s
[Task 12/25] Current/Best: 15.41/ 19.14 GFLOPS | Progress: (20/20) | 15.47 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.68/ 17.31 GFLOPS | Progress: (4/20) | 3.60 s
[Task 13/25] Current/Best: 16.14/ 20.89 GFLOPS | Progress: (8/20) | 5.99 s
[Task 13/25] Current/Best: 19.71/ 21.69 GFLOPS | Progress: (12/20) | 8.89 s
[Task 13/25] Current/Best: 12.30/ 21.69 GFLOPS | Progress: (16/20) | 12.25 s
[Task 13/25] Current/Best: 18.70/ 21.69 GFLOPS | Progress: (20/20) | 14.50 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.31 s
[Task 14/25] Current/Best: 6.08/ 13.60 GFLOPS | Progress: (8/20) | 5.47 s
[Task 14/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (12/20) | 8.03 s
[Task 14/25] Current/Best: 16.36/ 20.25 GFLOPS | Progress: (16/20) | 9.68 s Done.
-
[Task 14/25] Current/Best: 17.39/ 20.25 GFLOPS | Progress: (20/20) | 11.39 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.08/ 17.66 GFLOPS | Progress: (4/20) | 2.72 s
[Task 15/25] Current/Best: 14.49/ 18.05 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.50/ 22.56 GFLOPS | Progress: (12/20) | 6.08 s
[Task 15/25] Current/Best: 20.38/ 22.56 GFLOPS | Progress: (16/20) | 9.04 s
[Task 15/25] Current/Best: 9.59/ 22.56 GFLOPS | Progress: (20/20) | 10.00 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 2.93 s
[Task 16/25] Current/Best: 3.04/ 20.58 GFLOPS | Progress: (8/20) | 4.52 s
[Task 16/25] Current/Best: 19.32/ 20.58 GFLOPS | Progress: (12/20) | 5.72 s
[Task 16/25] Current/Best: 17.95/ 20.58 GFLOPS | Progress: (16/20) |
7.05 s
[Task 16/25] Current/Best: 9.92/ 21.97 GFLOPS | Progress: (20/20) | 9.07 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.78/ 18.34 GFLOPS | Progress: (4/20) | 4.71 s
[Task 17/25] Current/Best: 14.28/ 23.39 GFLOPS | Progress: (8/20) | 7.53 s
[Task 17/25] Current/Best: 17.00/ 23.39 GFLOPS | Progress: (12/20) | 9.58 s
[Task 17/25] Current/Best: 16.50/ 23.39 GFLOPS | Progress: (16/20) | 11.69 s
[Task 17/25] Current/Best: 10.07/ 23.39 GFLOPS | Progress: (20/20) | 13.79 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.23/ 17.01 GFLOPS | Progress: (4/20) | 3.68 s
[Task 18/25] Current/Best: 10.59/ 19.64 GFLOPS | Progress: (8/20) | 7.07 s
[Task 18/25] Current/Best: 19.31/ 19.64 GFLOPS | Progress: (12/20) | 8.97 s
[Task 18/25] Current/Best: 10.09/ 19.64 GFLOPS | Progress: (16/20) | 12.44 s
[Task 18/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (20/20) | 13.94 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.30/ 20.29 GFLOPS | Progress: (4/20) | 5.90 s
[Task 19/25] Current/Best: 2.69/ 20.29 GFLOPS | Progress: (8/20) | 9.17 s
[Task 19/25] Current/Best: 20.50/ 21.86 GFLOPS | Progress: (12/20) | 11.94 s
[Task 19/25] Current/Best: 13.61/ 22.41 GFLOPS | Progress: (16/20) | 14.80 s
[Task 19/25] Current/Best: 2.71/ 23.31 GFLOPS | Progress: (20/20) | 17.62 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.09/ 15.21 GFLOPS | Progress: (4/20) | 3.23 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (4/20) | 6.43 s
[Task 1/25] Current/Best: 6.16/ 17.45 GFLOPS | Progress: (8/20) | 9.42 s
[Task 1/25] Current/Best: 11.50/ 22.72 GFLOPS | Progress: (12/20) | 11.87 s
[Task 1/25] Current/Best: 16.38/ 22.74 GFLOPS | Progress: (16/20) | 13.56 s
[Task 1/25] Current/Best: 11.26/ 23.46 GFLOPS | Progress: (20/20) | 15.33 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.18/ 13.24 GFLOPS | Progress: (4/20) | 3.88 s
[Task 2/25] Current/Best: 14.12/ 18.67 GFLOPS | Progress: (8/20) | 5.20 s
[Task 2/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (12/20) | 6.54 s
[Task 2/25] Current/Best: 11.08/ 21.17 GFLOPS | Progress: (16/20) | 7.84 s
[Task 2/25] Current/Best: 20.02/ 21.17 GFLOPS | Progress: (20/20) | 9.45 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.81 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.22/ 16.71 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 14.97/ 16.71 GFLOPS | Progress: (12/20) | 9.58 s
[Task 3/25] Current/Best: 7.16/ 23.68 GFLOPS | Progress: (16/20) | 11.51 s
[Task 3/25] Current/Best: 12.61/ 23.68 GFLOPS | Progress: (20/20) | 16.05 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 18.53 GFLOPS | Progress: (4/20) | 2.44 s
[Task 4/25] Current/Best: 6.87/ 18.53 GFLOPS | Progress: (8/20) | 6.78 s
[Task 4/25] Current/Best: 21.71/ 21.71 GFLOPS | Progress: (12/20) | 11.31 s
[Task 4/25] Current/Best: 16.73/ 21.71 GFLOPS | Progress: (16/20) | 13.53 s
[Task 4/25] Current/Best: 13.42/ 21.71 GFLOPS | Progress: (20/20) | 15.57 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.79/ 10.34 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.95/ 12.97 GFLOPS | Progress: (8/20) | 4.69 s
[Task 5/25] Current/Best: 10.76/ 18.01 GFLOPS | Progress: (12/20) | 7.82 s
[Task 5/25] Current/Best: 11.85/ 22.60 GFLOPS | Progress: (16/20) | 9.26 s
[Task 5/25] Current/Best: 11.68/ 22.60 GFLOPS | Progress: (20/20) | 11.14 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.26/ 20.62 GFLOPS | Progress: (4/20) | 4.05 s
[Task 6/25] Current/Best: 18.95/ 20.62 GFLOPS | Progress: (8/20) | 5.81 s
[Task 6/25] Current/Best: 13.23/ 20.62 GFLOPS | Progress: (12/20) | 7.72 s
[Task 6/25] Current/Best: 19.92/ 20.62 GFLOPS | Progress: (16/20) | 9.96 s
[Task 6/25] Current/Best: 3.78/ 20.62 GFLOPS | Progress: (20/20) | 12.48 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.85 GFLOPS | Progress: (4/20) | 3.68 s
[Task 7/25] Current/Best: 20.16/ 21.11 GFLOPS | Progress: (8/20) | 5.20 s
[Task 7/25] Current/Best: 15.77/ 21.11 GFLOPS | Progress: (12/20) | 7.15 s
[Task 7/25] Current/Best: 12.23/ 21.11 GFLOPS | Progress: (16/20) | 9.18 s
[Task 7/25] Current/Best: 6.49/ 21.59 GFLOPS | Progress: (20/20) | 11.64 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.53/ 14.65 GFLOPS | Progress: (4/20) | 2.94 s
[Task 8/25] Current/Best: 10.15/ 14.65 GFLOPS | Progress: (8/20) | 7.68 s
[Task 8/25] Current/Best: 13.17/ 14.65 GFLOPS | Progress: (12/20) | 13.87 s
[Task 8/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (16/20) | 15.95 s
[Task 8/25] Current/Best: 19.76/ 19.76 GFLOPS | Progress: (20/20) | 22.42 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.08/ 15.72 GFLOPS | Progress: (4/20) | 12.00 s
[Task 9/25] Current/Best: 22.93/ 22.93 GFLOPS | Progress: (8/20) | 13.84 s
[Task 9/25] Current/Best: 8.26/ 22.93 GFLOPS | Progress: (12/20) | 16.23 s
[Task 9/25] Current/Best: 17.84/ 22.93 GFLOPS | Progress: (16/20) | 18.88 s
[Task 9/25] Current/Best: 9.08/ 22.93 GFLOPS | Progress: (20/20) | 26.59 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.58/ 18.20 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 13.08/ 19.08 GFLOPS | Progress: (12/20) | 5.70 s
[Task 10/25] Current/Best: 19.00/ 20.42 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.84/ 20.42 GFLOPS | Progress: (20/20
) | 8.37 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.32/ 18.20 GFLOPS | Progress: (4/20) | 3.38 s
[Task 11/25] Current/Best: 16.85/ 18.20 GFLOPS | Progress: (8/20) | 6.12 s
[Task 11/25] Current/Best: 18.05/ 18.20 GFLOPS | Progress: (12/20) | 8.16 s
[Task 11/25] Current/Best: 12.28/ 20.92 GFLOPS | Progress: (16/20) | 10.96 s
[Task 11/25] Current/Best: 19.43/ 21.28 GFLOPS | Progress: (20/20) | 13.03 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.03 GFLOPS | Progress: (4/20) | 5.45 s
[Task 12/25] Current/Best: 5.34/ 18.03 GFLOPS | Progress: (8/20) | 9.12 s
[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.09 s
[Task 12/25] Current/Best: 15.19/ 18.91 GFLOPS | Progress: (16/20) | 13.87 s
[Task 12/25] Current/Best: 15.19/ 19.07 GFLOPS | Progress: (20/20) | 15.80 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.75/ 17.29 GFLOPS | Progress: (4/20) | 3.70 s
[Task 13/25] Current/Best: 15.97/ 20.91 GFLOPS | Progress: (8/20) | 6.16 s
[Task 13/25] Current/Best: 19.41/ 21.31 GFLOPS | Progress: (12/20) | 9.09 s
[Task 13/25] Current/Best: 12.23/ 21.31 GFLOPS | Progress: (16/20) | 12.49 s
[Task 13/25] Current/Best: 18.73/ 21.31 GFLOPS | Progress: (20/20) | 14.77 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.53/ 13.53 GFLOPS | Progress: (4/20) | 3.37 s
[Task 14/25] Current/Best: 6.07/ 13.53 GFLOPS | Progress: (8/20) | 5.57 s
[Task 14/25] Current/Best: 20.11/ 20.11 GFLOPS | Progress: (12/20) | 8.12 s
[Task 14/25] Current/Best: 17.23/ 20.11 GFLOPS | Progress: (16/20) | 9.78 s Done.
+
[Task 14/25] Current/Best: 17.12/ 20.11 GFLOPS | Progress: (20/20) | 11.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.17/ 17.57 GFLOPS | Progress: (4/20) | 2.77 s
[Task 15/25] Current/Best: 14.47/ 18.02 GFLOPS | Progress: (8/20) | 4.13 s
[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.20 s
[Task 15/25] Current/Best: 20.43/ 22.28 GFLOPS | Progress: (16/20) | 9.08 s
[Task 15/25] Current/Best: 9.66/ 22.28 GFLOPS | Progress: (20/20) | 10.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.21/ 20.21 GFLOPS | Progress: (4/20) | 3.04 s
[Task 16/25] Current/Best: 3.01/ 20.21 GFLOPS | Progress: (8/20) | 4.66 s
[Task 16/25] Current/Best: 18.91/ 20.21 GFLOPS | Progress: (12/20) | 5.88 s
[Task 16/25] Current/Best: 17.51/ 20.21 GFLOPS | Progress: (16/20) |
7.22 s
[Task 16/25] Current/Best: 9.98/ 21.90 GFLOPS | Progress: (20/20) | 9.27 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.81/ 18.33 GFLOPS | Progress: (4/20) | 4.78 s
[Task 17/25] Current/Best: 12.78/ 22.97 GFLOPS | Progress: (8/20) | 7.67 s
[Task 17/25] Current/Best: 17.22/ 22.97 GFLOPS | Progress: (12/20) | 9.74 s
[Task 17/25] Current/Best: 16.36/ 22.97 GFLOPS | Progress: (16/20) | 11.87 s
[Task 17/25] Current/Best: 10.03/ 22.97 GFLOPS | Progress: (20/20) | 14.00 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.23/ 18.20 GFLOPS | Progress: (4/20) | 3.74 s
[Task 18/25] Current/Best: 10.60/ 18.20 GFLOPS | Progress: (8/20) | 7.18 s
[Task 18/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (12/20) | 9.14 s
[Task 18/25] Current/Best: 9.97/ 19.41 GFLOPS | Progress: (16/20) | 12.70 s
[Task 18/25] Current/Best: 20.71/ 20.71 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.40/ 20.10 GFLOPS | Progress: (4/20) | 6.23 s
[Task 19/25] Current/Best: 2.69/ 20.10 GFLOPS | Progress: (8/20) | 9.44 s
[Task 19/25] Current/Best: 19.46/ 20.70 GFLOPS | Progress: (12/20) | 12.22 s
[Task 19/25] Current/Best: 13.62/ 21.17 GFLOPS | Progress: (16/20) | 15.10 s
[Task 19/25] Current/Best: 2.70/ 22.58 GFLOPS | Progress: (20/20) | 17.87 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.40/ 15.15 GFLOPS | Progress: (4/20) | 3.40 s Done.
Done.
-
[Task 20/25] Current/Best: 9.69/ 15.21 GFLOPS | Progress: (8/20) | 6.49 s
[Task 20/25] Current/Best: 2.33/ 16.42 GFLOPS | Progress: (12/20) | 10.36 s
[Task 20/25] Current/Best: 12.38/ 16.42 GFLOPS | Progress: (16/20) | 13.96 s
[Task 20/25] Current/Best: 12.20/ 22.28 GFLOPS | Progress: (20/20) | 16.03 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.69 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.51/ 17.69 GFLOPS | Progress: (8/20) | 4.72 s
[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 6.84 s
[Task 21/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (16/20) | 10.23 s
[Task 21/25] Current/Best: 4.45/ 17.78 GFLOPS | Progress: (20/20) | 17.14 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.71/ 17.02 GFLOPS | Progress: (4/20
) | 2.66 s
[Task 22/25] Current/Best: 8.61/ 22.02 GFLOPS | Progress: (8/20) | 4.56 s
[Task 22/25] Current/Best: 19.75/ 22.02 GFLOPS | Progress: (12/20) | 6.86 s
[Task 22/25] Current/Best: 15.36/ 22.02 GFLOPS | Progress: (16/20) | 8.89 s
[Task 22/25] Current/Best: 14.24/ 22.02 GFLOPS | Progress: (20/20) | 10.60 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.75/ 20.99 GFLOPS | Progress: (4/20) | 3.23 s
[Task 23/25] Current/Best: 14.75/ 20.99 GFLOPS | Progress: (8/20) | 6.57 s
[Task 23/25] Current/Best: 21.01/ 21.88 GFLOPS | Progress: (12/20) | 8.34 s
[Task 23/25] Current/Best: 6.53/ 21.88 GFLOPS | Progress: (16/20) | 15.24 s
[Task 23/25] Current/Best: 7.96/ 21.88 GFLOPS | Progress: (20/20) | 19.39 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.34/ 8.34 GFLOPS | Progress: (4/20) | 11.77 s
[Task 24/25] Current/Best: 2.02/ 8.34 GFLOPS | Progress: (8/20) | 22.83 s
[Task 24/25] Current/Best: 4.45/ 8.34 GFLOPS | Progress: (12/20) | 34.39 s Done.
-
[Task 24/25] Current/Best: 6.26/ 9.05 GFLOPS | Progress: (16/20) | 39.92 s
[Task 24/25] Current/Best: 3.39/ 9.06 GFLOPS | Progress: (20/20) | 45.66 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.60 s
[Task 25/25] Current/Best: 6.18/ 8.54 GFLOPS | Progress: (8/20) | 23.04 s
[Task 25/25] Current/Best: 6.09/ 8.54 GFLOPS | Progress: (12/20) | 34.52 s
[Task 25/25] Current/Best: 5.97/ 8.93 GFLOPS | Progress: (16/20) | 36.24 s
[Task 25/25] Current/Best: 2.88/ 9.55 GFLOPS | Progress: (20/20) | 46.93 s
+
[Task 20/25] Current/Best: 10.41/ 15.15 GFLOPS | Progress: (8/20) | 6.70 s
[Task 20/25] Current/Best: 2.32/ 15.15 GFLOPS | Progress: (12/20) | 10.65 s
[Task 20/25] Current/Best: 12.56/ 15.15 GFLOPS | Progress: (16/20) | 14.44 s
[Task 20/25] Current/Best: 13.36/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.37/ 17.70 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.57/ 17.70 GFLOPS | Progress: (8/20) | 4.88 s
[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.04 s
[Task 21/25] Current/Best: 17.83/ 17.83 GFLOPS | Progress: (16/20) | 10.51 s
[Task 21/25] Current/Best: 4.46/ 17.83 GFLOPS | Progress: (20/20) | 17.62 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20
) | 2.74 s
[Task 22/25] Current/Best: 9.17/ 21.61 GFLOPS | Progress: (8/20) | 4.64 s
[Task 22/25] Current/Best: 19.92/ 21.61 GFLOPS | Progress: (12/20) | 6.94 s
[Task 22/25] Current/Best: 15.15/ 21.61 GFLOPS | Progress: (16/20) | 9.03 s
[Task 22/25] Current/Best: 14.87/ 21.61 GFLOPS | Progress: (20/20) | 10.74 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.35/ 20.29 GFLOPS | Progress: (4/20) | 3.32 s
[Task 23/25] Current/Best: 15.94/ 20.29 GFLOPS | Progress: (8/20) | 6.68 s
[Task 23/25] Current/Best: 20.72/ 21.30 GFLOPS | Progress: (12/20) | 8.53 s
[Task 23/25] Current/Best: 6.24/ 21.30 GFLOPS | Progress: (16/20) | 15.54 s
[Task 23/25] Current/Best: 7.56/ 21.30 GFLOPS | Progress: (20/20) | 19.80 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (4/20) | 11.85 s
[Task 24/25] Current/Best: 1.96/ 8.48 GFLOPS | Progress: (8/20) | 22.90 s
[Task 24/25] Current/Best: 4.34/ 8.48 GFLOPS | Progress: (12/20) | 34.46 s Done.
+
[Task 24/25] Current/Best: 7.25/ 8.72 GFLOPS | Progress: (16/20) | 39.89 s
[Task 24/25] Current/Best: 3.31/ 8.93 GFLOPS | Progress: (20/20) | 45.78 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.94 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.65/ 7.42 GFLOPS | Progress: (8/20) | 22.95 s
[Task 25/25] Current/Best: 5.82/ 7.42 GFLOPS | Progress: (12/20) | 34.39 s
[Task 25/25] Current/Best: 5.72/ 9.06 GFLOPS | Progress: (16/20) | 36.28 s
[Task 25/25] Current/Best: 2.93/ 9.06 GFLOPS | Progress: (20/20) | 47.00 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 405.6997717099921, 'median': 405.49599050000324, 'std': 0.5053295578524342}
- unoptimized: {'mean': 496.095531889996, 'median': 496.25740645001315, 'std': 0.9061120950977117}
+ optimized: {'mean': 412.6048881799966, 'median': 412.17131859999654, 'std': 1.3900040551179313}
+ unoptimized: {'mean': 496.46541508000047, 'median': 496.4040101000023, 'std': 0.6307671095444364}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 11.947 seconds)
+ **Total running time of the script:** ( 10 minutes 22.685 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 f413e2f8a..d959499c2 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.285e-07 secs/op
+ 1.237e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 6bd38f442..baacef829 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x23784e40)), stage(b, placeholder(b, 0x213e1080)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x21e52920)), stage(b, placeholder(b, 0xf46d3b0)), 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 9360616ea..4c9c927ab 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
=================
-**13:03.983** total execution time for **tutorial** files:
+**13:13.486** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:11.947 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:22.685 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.458 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.827 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:56.024 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:53.834 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.237 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.294 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.969 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.816 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.696 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.153 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.506 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.711 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.136 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 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``) | 00:00.002 | 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_tvmc_python.py` (``tvmc_python.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_command_line_driver.py` (``tvmc_command_line_driver.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 f4b9ff0bb..acd7619de 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000006
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.277610002347501e-06 1.0
- naive 5.9196e-06 0.8133989040482446
- parallel 6.1369000000000005e-06 0.8432576076514752
- vector 2.4546299999999996e-05 3.3728518005337222
+ numpy 7.890279998719052e-06 1.0
+ naive 5.791799999999999e-06 0.734042391517192
+ parallel 6.047e-06 0.7663859838917884
+ vector 2.46919e-05 3.1294073219212253
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017490
+ Numpy running time: 0.018969
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.407462
+ none: 3.218482
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.293541
+ blocking: 0.316966
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.331567
+ vectorization: 0.347821
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.111469
+ loop permutation: 0.123013
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.107273
+ array packing: 0.110326
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.110060
+ block caching: 0.111111
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.145915
+ parallelization: 0.147077
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4074616575 1.0
- blocking 0.2935412285 0.08614659767451836
- vectorization 0.3315665954 0.09730603854931272
- loop permutation 0.11146864009999999 0.0327131018054603
- array packing 0.10727264489999999 0.031481688037160255
- block caching 0.1100600754 0.032299725268442
- parallelization 0.1459146999 0.04282211058159207
+ none 3.2184822234999997 1.0
+ blocking 0.316966411 0.0984831945584925
+ vectorization 0.34782091039999996 0.10806985598999379
+ loop permutation 0.12301334099999998 0.03822091671092929
+ array packing 0.110326467 0.034279035687829085
+ block caching 0.11111058089999999 0.034522664157880814
+ parallelization 0.1470772099 0.045697692168719856
@@ -1686,11 +1686,6 @@ 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 0.458 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index bd9419482..46e94d0cd 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-8e95bba69787bfc34ad63f60565f8f064b51cb88
+3bd168194f25c95904dac8835f8e74abd423a5a3
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 2b0cafa92..5455a20da 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.056 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.183 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 0cedc326f..230466c3e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip5e93e5f9-0f00-4ee4-bfe8-0ec95c79834b 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.zip7ce9fca2-9896-4744-b2c7-01ee7f02a909 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 2ac3b4942..c8a84de41 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,14 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:01, 21.6MB/s]
- 20%|## | 8.40M/41.5M [00:00<00:01, 18.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 30.8MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.0MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 39.7MB/s]
- 87%|########7 | 36.2M/41.5M [00:01<00:00, 38.1MB/s]
- 96%|#########6| 40.0M/41.5M [00:01<00:00, 32.4MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 31.3MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 44.6MB/s]
+ 26%|##5 | 10.6M/41.5M [00:00<00:00, 33.9MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 33.0MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 37.5MB/s]
+ 63%|######2 | 26.0M/41.5M [00:00<00:00, 34.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.2MB/s]
+ 96%|#########6| 40.0M/41.5M [00:01<00:00, 45.6MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 40.8MB/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 376075ea2..e225a9f3f 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,11 +414,25 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 16%|#6 | 7.20M/44.7M [00:00<00:00, 75.4MB/s]
- 36%|###6 | 16.2M/44.7M [00:00<00:00, 85.9MB/s]
- 55%|#####4 | 24.3M/44.7M [00:00<00:00, 53.4MB/s]
- 85%|########4 | 38.0M/44.7M [00:00<00:00, 79.1MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 81.1MB/s]
+ 3%|3 | 1.56M/44.7M [00:00<00:02, 16.2MB/s]
+ 10%|# | 4.49M/44.7M [00:00<00:01, 24.4MB/s]
+ 16%|#5 | 6.98M/44.7M [00:00<00:01, 25.0MB/s]
+ 21%|## | 9.37M/44.7M [00:00<00:01, 24.4MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:01, 26.0MB/s]
+ 33%|###2 | 14.7M/44.7M [00:00<00:01, 24.8MB/s]
+ 38%|###8 | 17.0M/44.7M [00:00<00:01, 24.8MB/s]
+ 43%|####3 | 19.4M/44.7M [00:00<00:01, 20.5MB/s]
+ 48%|####8 | 21.5M/44.7M [00:01<00:01, 20.5MB/s]
+ 55%|#####4 | 24.4M/44.7M [00:01<00:00, 22.7MB/s]
+ 61%|######1 | 27.4M/44.7M [00:01<00:00, 24.6MB/s]
+ 68%|######7 | 30.4M/44.7M [00:01<00:00, 26.0MB/s]
+ 74%|#######3 | 32.9M/44.7M [00:01<00:00, 24.7MB/s]
+ 79%|#######9 | 35.3M/44.7M [00:01<00:00, 23.0MB/s]
+ 84%|########4 | 37.5M/44.7M [00:01<00:00, 22.7MB/s]
+ 89%|########9 | 39.8M/44.7M [00:01<00:00, 22.9MB/s]
+ 94%|#########4| 42.0M/44.7M [00:01<00:00, 21.9MB/s]
+ 99%|#########8| 44.2M/44.7M [00:02<00:00, 22.1MB/s]
+100%|##########| 44.7M/44.7M [00:02<00:00, 23.3MB/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 1ac6eab92..6ee5f7ee4 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.214 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.906 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 82a674c34..d3d69aa04 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.169</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:09.016</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:04.214</p></td>
+<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>01:05.183</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:04.056</p></td>
+<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>01:02.906</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>00:37.889</p></td>
+<td><p>00:39.418</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:27.890</p></td>
+<td><p>00:28.289</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>00:25.204</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:25.538</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:24.818</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:24.942</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:21.621</p></td>
+<td><p>00:23.060</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.463</p></td>
+<td><p>00:21.692</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:14.635</p></td>
+<td><p>00:15.549</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>00:02.380</p></td>
+<td><p>00:02.439</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 b3ba505c8..55343eeac 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.4732 15.4615 15.5507 15.4304 0.0408
+ 16.1330 16.1027 16.2472 16.0808 0.0620
</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 6ef6602af..e83182dbc 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,95 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 11%|# | 18.2M/170M [00:00<00:00, 191MB/s]
- 24%|##4 | 41.6M/170M [00:00<00:00, 223MB/s]
- 39%|###9 | 66.4M/170M [00:00<00:00, 240MB/s]
- 53%|#####3 | 90.2M/170M [00:00<00:00, 244MB/s]
- 67%|######7 | 114M/170M [00:00<00:00, 248MB/s]
- 82%|########1 | 139M/170M [00:00<00:00, 249MB/s]
- 96%|#########5| 162M/170M [00:00<00:00, 249MB/s]
-100%|##########| 170M/170M [00:00<00:00, 244MB/s]
+ 1%|1 | 1.75M/170M [00:00<00:09, 18.3MB/s]
+ 2%|2 | 3.50M/170M [00:00<00:14, 12.3MB/s]
+ 3%|3 | 5.31M/170M [00:00<00:11, 14.7MB/s]
+ 4%|4 | 6.88M/170M [00:00<00:11, 14.9MB/s]
+ 5%|4 | 8.38M/170M [00:00<00:11, 14.6MB/s]
+ 6%|5 | 10.0M/170M [00:00<00:11, 14.3MB/s]
+ 7%|6 | 11.5M/170M [00:00<00:11, 14.6MB/s]
+ 8%|7 | 12.9M/170M [00:00<00:12, 12.8MB/s]
+ 8%|8 | 14.2M/170M [00:01<00:13, 11.8MB/s]
+ 9%|9 | 15.4M/170M [00:01<00:14, 11.3MB/s]
+ 10%|9 | 16.9M/170M [00:01<00:13, 12.3MB/s]
+ 11%|#1 | 18.7M/170M [00:01<00:11, 13.8MB/s]
+ 12%|#2 | 20.4M/170M [00:01<00:10, 14.7MB/s]
+ 13%|#3 | 22.4M/170M [00:01<00:09, 15.9MB/s]
+ 14%|#4 | 23.9M/170M [00:01<00:09, 15.6MB/s]
+ 15%|#4 | 25.4M/170M [00:01<00:09, 15.4MB/s]
+ 16%|#5 | 26.9M/170M [00:02<00:13, 11.1MB/s]
+ 17%|#6 | 28.1M/170M [00:02<00:14, 10.0MB/s]
+ 17%|#7 | 29.2M/170M [00:02<00:15, 9.82MB/s]
+ 18%|#7 | 30.3M/170M [00:02<00:14, 10.0MB/s]
+ 19%|#8 | 32.0M/170M [00:02<00:12, 11.9MB/s]
+ 20%|#9 | 33.8M/170M [00:02<00:10, 13.4MB/s]
+ 21%|## | 35.6M/170M [00:02<00:09, 14.4MB/s]
+ 22%|##1 | 37.1M/170M [00:02<00:09, 13.9MB/s]
+ 23%|##2 | 39.1M/170M [00:03<00:08, 15.7MB/s]
+ 24%|##4 | 41.1M/170M [00:03<00:07, 17.1MB/s]
+ 25%|##5 | 42.7M/170M [00:03<00:07, 17.1MB/s]
+ 26%|##6 | 44.4M/170M [00:03<00:08, 15.3MB/s]
+ 27%|##7 | 46.0M/170M [00:03<00:08, 15.6MB/s]
+ 28%|##7 | 47.5M/170M [00:03<00:08, 14.8MB/s]
+ 29%|##8 | 49.0M/170M [00:03<00:09, 13.9MB/s]
+ 30%|##9 | 50.4M/170M [00:03<00:09, 13.8MB/s]
+ 31%|### | 52.2M/170M [00:03<00:08, 14.5MB/s]
+ 32%|###1 | 53.6M/170M [00:04<00:08, 14.5MB/s]
+ 32%|###2 | 55.0M/170M [00:04<00:08, 13.8MB/s]
+ 33%|###3 | 56.3M/170M [00:04<00:10, 11.0MB/s]
+ 34%|###3 | 57.4M/170M [00:04<00:11, 9.93MB/s]
+ 35%|###4 | 59.3M/170M [00:04<00:09, 12.1MB/s]
+ 36%|###5 | 61.0M/170M [00:04<00:09, 12.6MB/s]
+ 37%|###7 | 63.4M/170M [00:04<00:07, 15.5MB/s]
+ 38%|###8 | 65.0M/170M [00:05<00:07, 14.8MB/s]
+ 39%|###9 | 66.4M/170M [00:05<00:07, 14.6MB/s]
+ 40%|#### | 68.1M/170M [00:05<00:07, 15.1MB/s]
+ 41%|#### | 69.5M/170M [00:05<00:07, 13.7MB/s]
+ 42%|####1 | 71.2M/170M [00:05<00:07, 14.5MB/s]
+ 43%|####3 | 73.2M/170M [00:05<00:06, 16.1MB/s]
+ 44%|####4 | 75.4M/170M [00:05<00:05, 18.0MB/s]
+ 46%|####5 | 77.6M/170M [00:05<00:05, 19.2MB/s]
+ 47%|####6 | 79.8M/170M [00:05<00:04, 19.4MB/s]
+ 48%|####8 | 82.1M/170M [00:05<00:04, 20.8MB/s]
+ 50%|####9 | 84.2M/170M [00:06<00:04, 21.3MB/s]
+ 51%|#####1 | 87.2M/170M [00:06<00:03, 24.2MB/s]
+ 53%|#####2 | 89.6M/170M [00:06<00:03, 24.2MB/s]
+ 54%|#####4 | 91.9M/170M [00:06<00:03, 22.6MB/s]
+ 55%|#####5 | 94.1M/170M [00:06<00:03, 21.5MB/s]
+ 57%|#####6 | 96.2M/170M [00:06<00:03, 21.4MB/s]
+ 58%|#####8 | 98.6M/170M [00:06<00:03, 22.0MB/s]
+ 59%|#####9 | 101M/170M [00:06<00:03, 22.8MB/s]
+ 61%|######1 | 104M/170M [00:06<00:02, 24.7MB/s]
+ 63%|######3 | 108M/170M [00:07<00:02, 23.3MB/s]
+ 65%|######4 | 110M/170M [00:07<00:02, 20.9MB/s]
+ 67%|######6 | 113M/170M [00:07<00:02, 23.8MB/s]
+ 68%|######8 | 116M/170M [00:07<00:03, 18.5MB/s]
+ 69%|######9 | 118M/170M [00:07<00:03, 17.5MB/s]
+ 70%|####### | 119M/170M [00:07<00:02, 17.8MB/s]
+ 72%|#######1 | 122M/170M [00:07<00:02, 19.7MB/s]
+ 74%|#######3 | 125M/170M [00:08<00:02, 22.2MB/s]
+ 75%|#######4 | 127M/170M [00:08<00:02, 15.1MB/s]
+ 76%|#######5 | 129M/170M [00:08<00:03, 13.0MB/s]
+ 77%|#######7 | 131M/170M [00:08<00:02, 14.0MB/s]
+ 78%|#######8 | 132M/170M [00:08<00:02, 14.0MB/s]
+ 79%|#######8 | 134M/170M [00:08<00:02, 13.9MB/s]
+ 80%|#######9 | 135M/170M [00:09<00:03, 10.8MB/s]
+ 81%|######## | 137M/170M [00:09<00:03, 10.0MB/s]
+ 81%|########1 | 138M/170M [00:09<00:03, 10.7MB/s]
+ 82%|########1 | 139M/170M [00:09<00:03, 10.7MB/s]
+ 83%|########2 | 141M/170M [00:09<00:02, 11.8MB/s]
+ 85%|########5 | 145M/170M [00:09<00:01, 19.7MB/s]
+ 87%|########6 | 147M/170M [00:09<00:01, 21.6MB/s]
+ 89%|########8 | 151M/170M [00:09<00:00, 25.3MB/s]
+ 90%|######### | 153M/170M [00:10<00:00, 23.0MB/s]
+ 92%|#########1| 156M/170M [00:10<00:00, 20.5MB/s]
+ 93%|#########2| 158M/170M [00:10<00:00, 16.7MB/s]
+ 94%|#########4| 160M/170M [00:10<00:00, 18.1MB/s]
+ 96%|#########5| 162M/170M [00:10<00:00, 19.0MB/s]
+ 97%|#########7| 165M/170M [00:10<00:00, 21.5MB/s]
+ 99%|#########8| 167M/170M [00:10<00:00, 20.9MB/s]
+100%|#########9| 169M/170M [00:10<00:00, 20.4MB/s]
+100%|##########| 170M/170M [00:11<00:00, 16.1MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -538,7 +619,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 48.457 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.654 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 ed0b31231..36f6e27b7 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,13 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 180MB/s]
+ 14%|#4 | 1.94M/13.6M [00:00<00:00, 19.9MB/s]
+ 29%|##8 | 3.88M/13.6M [00:00<00:00, 20.0MB/s]
+ 44%|####3 | 5.94M/13.6M [00:00<00:00, 20.7MB/s]
+ 59%|#####8 | 7.94M/13.6M [00:00<00:00, 20.4MB/s]
+ 73%|#######2 | 9.89M/13.6M [00:00<00:00, 20.0MB/s]
+ 87%|########7 | 11.8M/13.6M [00:00<00:00, 17.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 19.1MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +575,7 @@ 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)
- 90.0580 89.9606 95.2509 89.7288 0.5749
+ 90.4607 90.4614 91.4691 90.1497 0.2161
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +614,7 @@ 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 7.245 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.665 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 7031d028d..b8bc34ab4 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 117.1479 116.9031 122.6961 116.1215 0.9819
+ 120.7069 120.6746 122.2613 119.9769 0.3762
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 50.548 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.654 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 3d2562782..7c1084a4a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 46.489 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.300 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 9a165a476..c18a30b5c 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,26 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|3 | 4595/132723 [00:00<00:02, 45944.79KB/s]
- 9%|8 | 11779/132723 [00:00<00:01, 61159.86KB/s]
- 15%|#5 | 20365/132723 [00:00<00:01, 72433.78KB/s]
- 22%|##1 | 28817/132723 [00:00<00:01, 77202.30KB/s]
- 28%|##8 | 37207/132723 [00:00<00:01, 79616.50KB/s]
- 34%|###4 | 45752/132723 [00:00<00:01, 81596.67KB/s]
- 41%|#### | 53912/132723 [00:00<00:01, 69598.89KB/s]
- 47%|####7 | 62405/132723 [00:00<00:00, 73963.36KB/s]
- 53%|#####3 | 70879/132723 [00:00<00:00, 77079.31KB/s]
- 60%|#####9 | 79467/132723 [00:01<00:00, 79650.18KB/s]
- 66%|######5 | 87579/132723 [00:01<00:00, 64943.93KB/s]
- 72%|#######2 | 96121/132723 [00:01<00:00, 70148.78KB/s]
- 78%|#######8 | 103600/132723 [00:01<00:00, 51644.42KB/s]
- 84%|########4 | 112053/132723 [00:01<00:00, 58747.25KB/s]
- 90%|########9 | 119178/132723 [00:01<00:00, 61693.81KB/s]
- 96%|#########6| 127584/132723 [00:01<00:00, 67328.86KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 68495.38KB/s]
+ 1%| | 1140/132723 [00:00<00:11, 11244.17KB/s]
+ 3%|2 | 3670/132723 [00:00<00:06, 19463.91KB/s]
+ 7%|6 | 8754/132723 [00:00<00:03, 33682.02KB/s]
+ 12%|#1 | 15570/132723 [00:00<00:02, 47246.20KB/s]
+ 17%|#7 | 23145/132723 [00:00<00:01, 57500.84KB/s]
+ 23%|##3 | 30841/132723 [00:00<00:01, 64104.87KB/s]
+ 29%|##8 | 38451/132723 [00:00<00:01, 68020.56KB/s]
+ 35%|###4 | 45935/132723 [00:00<00:01, 70185.95KB/s]
+ 40%|#### | 53211/132723 [00:00<00:01, 70989.46KB/s]
+ 46%|####5 | 60606/132723 [00:01<00:01, 71900.33KB/s]
+ 51%|#####1 | 68231/132723 [00:01<00:00, 73228.81KB/s]
+ 57%|#####7 | 75883/132723 [00:01<00:00, 74226.98KB/s]
+ 63%|######2 | 83505/132723 [00:01<00:00, 74819.95KB/s]
+ 69%|######8 | 91090/132723 [00:01<00:00, 75128.65KB/s]
+ 74%|#######4 | 98736/132723 [00:01<00:00, 75524.86KB/s]
+ 80%|######## | 106411/132723 [00:01<00:00, 75892.01KB/s]
+ 86%|########6 | 114241/132723 [00:01<00:00, 76614.04KB/s]
+ 92%|#########1| 121903/132723 [00:01<00:00, 54333.00KB/s]
+ 98%|#########7| 129512/132723 [00:02<00:00, 59409.21KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 63800.38KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +503,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.114 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 39.966 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 dd25c9ec0..cfd857a69 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:17.038</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:45.727</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:48.457</p></td>
+<td><p>03:11.654</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:32.114</p></td>
+<td><p>02:39.966</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:50.548</p></td>
+<td><p>01:52.654</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>01:46.489</p></td>
+<td><p>01:34.300</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>01:07.245</p></td>
+<td><p>01:11.665</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:28.877</p></td>
+<td><p>00:30.487</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:21.762</p></td>
+<td><p>00:22.733</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.540</p></td>
+<td><p>00:22.262</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 4b1b5de13..16c06f53d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4bb6c9f4-20f2-4207-8f4e-5e1c54f3371c 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.zip9c5cf530-9743-4560-be15-86ae3f0b2e2b 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 f011ee1da..233bffaa2 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.579</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.940</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:36.514</p></td>
+<td><p>00:38.656</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>00:02.148</p></td>
+<td><p>00:02.297</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.910</p></td>
+<td><p>00:00.979</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>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 3612d4a5f..59d0fc991 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7191us [7191us] (47.53%; 47.53%)
-FoldScaleAxis: 7939us [5us] (52.47%; 52.47%)
- FoldConstant: 7934us [1674us] (52.44%; 99.93%)
- InferType: 6260us [6260us] (41.37%; 78.90%)
+InferType: 7209us [7209us] (45.72%; 45.72%)
+FoldScaleAxis: 8559us [7us] (54.28%; 54.28%)
+ FoldConstant: 8551us [1741us] (54.23%; 99.91%)
+ InferType: 6810us [6810us] (43.19%; 79.64%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6308us [6308us] (44.48%; 44.48%)
-FoldScaleAxis: 7875us [4us] (55.52%; 55.52%)
- FoldConstant: 7870us [1650us] (55.49%; 99.94%)
- InferType: 6220us [6220us] (43.86%; 79.03%)
+InferType: 7124us [7124us] (46.22%; 46.22%)
+FoldScaleAxis: 8290us [7us] (53.78%; 53.78%)
+ FoldConstant: 8283us [1727us] (53.74%; 99.92%)
+ InferType: 6556us [6556us] (42.54%; 79.15%)
</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 96c54211a..5fc94a0e1 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.206375 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.190404 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 799a95786..80a529d1a 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.715396 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.917566 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 4fc3c845f..22e69a773 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017579
-Baseline: 3.292179
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018948
+Baseline: 3.193578
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300895
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308097
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335761
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347311
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.112381
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116828
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108402
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109662
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110583
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111108
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145946
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147767
</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 16c17fae0..11e922c03 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:33.825</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.161</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.681</p></td>
+<td><p>00:31.963</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>00:01.182</p></td>
+<td><p>00:01.205</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>00:00.962</p></td>
+<td><p>00:00.994</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 256785cc8..29fa1b6dd 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:04.137</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:26.490</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:19.491</p></td>
+<td><p>03:36.108</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.433</p></td>
+<td><p>01:23.688</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.113</p></td>
+<td><p>00:47.864</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>00:19.997</p></td>
+<td><p>00:20.774</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.624</p></td>
+<td><p>00:09.132</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.478</p></td>
+<td><p>00:08.925</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 1e315986e..7dc9e37fa 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
@@ -475,6 +475,9 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</pre></div>
+</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -1004,7 +1007,7 @@ 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: 0.376 ms
</pre></div>
</div>
</div>
@@ -1567,7 +1570,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 19.491 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 36.108 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 2f7375a4a..a96e8e24f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5737 9.5662 9.5977 9.5571 0.0174
+ 10.1971 10.2290 10.2522 10.1100 0.0623
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 36098def5..39476ba58 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 749.6334 748.8467 751.4610 748.5924 1.2965
+ 752.8325 753.0056 753.0691 752.4229 0.2908
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.433 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.688 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 8d129eb42..94a6e1e88 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,15 +625,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 16) {
+ let cse_var_1: int32 = ((i.outer.inner*256) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -649,387 +648,54 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 13)] = 0f32
compute_5[(cse_var_1 + 14)] = 0f32
compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- compute_5[(cse_var_1 + 128)] = 0f32
- compute_5[(cse_var_1 + 129)] = 0f32
- compute_5[(cse_var_1 + 130)] = 0f32
- compute_5[(cse_var_1 + 131)] = 0f32
- compute_5[(cse_var_1 + 132)] = 0f32
- compute_5[(cse_var_1 + 133)] = 0f32
- compute_5[(cse_var_1 + 134)] = 0f32
- compute_5[(cse_var_1 + 135)] = 0f32
- compute_5[(cse_var_1 + 136)] = 0f32
- compute_5[(cse_var_1 + 137)] = 0f32
- compute_5[(cse_var_1 + 138)] = 0f32
- compute_5[(cse_var_1 + 139)] = 0f32
- compute_5[(cse_var_1 + 140)] = 0f32
- compute_5[(cse_var_1 + 141)] = 0f32
- compute_5[(cse_var_1 + 142)] = 0f32
- compute_5[(cse_var_1 + 143)] = 0f32
- compute_5[(cse_var_1 + 160)] = 0f32
- compute_5[(cse_var_1 + 161)] = 0f32
- compute_5[(cse_var_1 + 162)] = 0f32
- compute_5[(cse_var_1 + 163)] = 0f32
- compute_5[(cse_var_1 + 164)] = 0f32
- compute_5[(cse_var_1 + 165)] = 0f32
- compute_5[(cse_var_1 + 166)] = 0f32
- compute_5[(cse_var_1 + 167)] = 0f32
- compute_5[(cse_var_1 + 168)] = 0f32
- compute_5[(cse_var_1 + 169)] = 0f32
- compute_5[(cse_var_1 + 170)] = 0f32
- compute_5[(cse_var_1 + 171)] = 0f32
- compute_5[(cse_var_1 + 172)] = 0f32
- compute_5[(cse_var_1 + 173)] = 0f32
- compute_5[(cse_var_1 + 174)] = 0f32
- compute_5[(cse_var_1 + 175)] = 0f32
- compute_5[(cse_var_1 + 192)] = 0f32
- compute_5[(cse_var_1 + 193)] = 0f32
- compute_5[(cse_var_1 + 194)] = 0f32
- compute_5[(cse_var_1 + 195)] = 0f32
- compute_5[(cse_var_1 + 196)] = 0f32
- compute_5[(cse_var_1 + 197)] = 0f32
- compute_5[(cse_var_1 + 198)] = 0f32
- compute_5[(cse_var_1 + 199)] = 0f32
- compute_5[(cse_var_1 + 200)] = 0f32
- compute_5[(cse_var_1 + 201)] = 0f32
- compute_5[(cse_var_1 + 202)] = 0f32
- compute_5[(cse_var_1 + 203)] = 0f32
- compute_5[(cse_var_1 + 204)] = 0f32
- compute_5[(cse_var_1 + 205)] = 0f32
- compute_5[(cse_var_1 + 206)] = 0f32
- compute_5[(cse_var_1 + 207)] = 0f32
- compute_5[(cse_var_1 + 224)] = 0f32
- compute_5[(cse_var_1 + 225)] = 0f32
- compute_5[(cse_var_1 + 226)] = 0f32
- compute_5[(cse_var_1 + 227)] = 0f32
- compute_5[(cse_var_1 + 228)] = 0f32
- compute_5[(cse_var_1 + 229)] = 0f32
- compute_5[(cse_var_1 + 230)] = 0f32
- compute_5[(cse_var_1 + 231)] = 0f32
- compute_5[(cse_var_1 + 232)] = 0f32
- compute_5[(cse_var_1 + 233)] = 0f32
- compute_5[(cse_var_1 + 234)] = 0f32
- compute_5[(cse_var_1 + 235)] = 0f32
- compute_5[(cse_var_1 + 236)] = 0f32
- compute_5[(cse_var_1 + 237)] = 0f32
- compute_5[(cse_var_1 + 238)] = 0f32
- compute_5[(cse_var_1 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_131: int32 = (i.outer.inner*2048)
- let cse_var_130: int32 = (elem_idx*16)
- let cse_var_129: int32 = (cse_var_1 + 99)
- let cse_var_128: int32 = (cse_var_1 + 98)
- let cse_var_127: int32 = (cse_var_1 + 97)
- let cse_var_126: int32 = (cse_var_1 + 96)
- let cse_var_125: int32 = (cse_var_1 + 9)
- let cse_var_124: int32 = (cse_var_1 + 8)
- let cse_var_123: int32 = (cse_var_1 + 79)
- let cse_var_122: int32 = (cse_var_1 + 78)
- let cse_var_121: int32 = (cse_var_1 + 77)
- let cse_var_120: int32 = (cse_var_1 + 76)
- let cse_var_119: int32 = (cse_var_1 + 75)
- let cse_var_118: int32 = (cse_var_1 + 74)
- let cse_var_117: int32 = (cse_var_1 + 73)
- let cse_var_116: int32 = (cse_var_1 + 72)
- let cse_var_115: int32 = (cse_var_1 + 71)
- let cse_var_114: int32 = (cse_var_1 + 70)
- let cse_var_113: int32 = (cse_var_1 + 7)
- let cse_var_112: int32 = (cse_var_1 + 69)
- let cse_var_111: int32 = (cse_var_1 + 68)
- let cse_var_110: int32 = (cse_var_1 + 67)
- let cse_var_109: int32 = (cse_var_1 + 66)
- let cse_var_108: int32 = (cse_var_1 + 65)
- let cse_var_107: int32 = (cse_var_1 + 64)
- let cse_var_106: int32 = (cse_var_1 + 6)
- let cse_var_105: int32 = (cse_var_1 + 5)
- let cse_var_104: int32 = (cse_var_1 + 47)
- let cse_var_103: int32 = (cse_var_1 + 46)
- let cse_var_102: int32 = (cse_var_1 + 45)
- let cse_var_101: int32 = (cse_var_1 + 44)
- let cse_var_100: int32 = (cse_var_1 + 43)
- let cse_var_99: int32 = (cse_var_1 + 42)
- let cse_var_98: int32 = (cse_var_1 + 41)
- let cse_var_97: int32 = (cse_var_1 + 40)
- let cse_var_96: int32 = (cse_var_1 + 4)
- let cse_var_95: int32 = (cse_var_1 + 39)
- let cse_var_94: int32 = (cse_var_1 + 38)
- let cse_var_93: int32 = (cse_var_1 + 37)
- let cse_var_92: int32 = (cse_var_1 + 36)
- let cse_var_91: int32 = (cse_var_1 + 35)
- let cse_var_90: int32 = (cse_var_1 + 34)
- let cse_var_89: int32 = (cse_var_1 + 33)
- let cse_var_88: int32 = (cse_var_1 + 32)
- let cse_var_87: int32 = (cse_var_1 + 3)
- let cse_var_86: int32 = (cse_var_1 + 239)
- let cse_var_85: int32 = (cse_var_1 + 238)
- let cse_var_84: int32 = (cse_var_1 + 237)
- let cse_var_83: int32 = (cse_var_1 + 236)
- let cse_var_82: int32 = (cse_var_1 + 235)
- let cse_var_81: int32 = (cse_var_1 + 234)
- let cse_var_80: int32 = (cse_var_1 + 233)
- let cse_var_79: int32 = (cse_var_1 + 232)
- let cse_var_78: int32 = (cse_var_1 + 231)
- let cse_var_77: int32 = (cse_var_1 + 230)
- let cse_var_76: int32 = (cse_var_1 + 229)
- let cse_var_75: int32 = (cse_var_1 + 228)
- let cse_var_74: int32 = (cse_var_1 + 227)
- let cse_var_73: int32 = (cse_var_1 + 226)
- let cse_var_72: int32 = (cse_var_1 + 225)
- let cse_var_71: int32 = (cse_var_1 + 224)
- let cse_var_70: int32 = (cse_var_1 + 207)
- let cse_var_69: int32 = (cse_var_1 + 206)
- let cse_var_68: int32 = (cse_var_1 + 205)
- let cse_var_67: int32 = (cse_var_1 + 204)
- let cse_var_66: int32 = (cse_var_1 + 203)
- let cse_var_65: int32 = (cse_var_1 + 202)
- let cse_var_64: int32 = (cse_var_1 + 201)
- let cse_var_63: int32 = (cse_var_1 + 200)
- let cse_var_62: int32 = (cse_var_1 + 2)
- let cse_var_61: int32 = (cse_var_1 + 199)
- let cse_var_60: int32 = (cse_var_1 + 198)
- let cse_var_59: int32 = (cse_var_1 + 197)
- let cse_var_58: int32 = (cse_var_1 + 196)
- let cse_var_57: int32 = (cse_var_1 + 195)
- let cse_var_56: int32 = (cse_var_1 + 194)
- let cse_var_55: int32 = (cse_var_1 + 193)
- let cse_var_54: int32 = (cse_var_1 + 192)
- let cse_var_53: int32 = (cse_var_1 + 175)
- let cse_var_52: int32 = (cse_var_1 + 174)
- let cse_var_51: int32 = (cse_var_1 + 173)
- let cse_var_50: int32 = (cse_var_1 + 172)
- let cse_var_49: int32 = (cse_var_1 + 171)
- let cse_var_48: int32 = (cse_var_1 + 170)
- let cse_var_47: int32 = (cse_var_1 + 169)
- let cse_var_46: int32 = (cse_var_1 + 168)
- let cse_var_45: int32 = (cse_var_1 + 167)
- let cse_var_44: int32 = (cse_var_1 + 166)
- let cse_var_43: int32 = (cse_var_1 + 165)
- let cse_var_42: int32 = (cse_var_1 + 164)
- let cse_var_41: int32 = (cse_var_1 + 163)
- let cse_var_40: int32 = (cse_var_1 + 162)
- let cse_var_39: int32 = (cse_var_1 + 161)
- let cse_var_38: int32 = (cse_var_1 + 160)
- let cse_var_37: int32 = (cse_var_1 + 15)
- let cse_var_36: int32 = (cse_var_1 + 143)
- let cse_var_35: int32 = (cse_var_1 + 142)
- let cse_var_34: int32 = (cse_var_1 + 141)
- let cse_var_33: int32 = (cse_var_1 + 140)
- let cse_var_32: int32 = (cse_var_1 + 14)
- let cse_var_31: int32 = (cse_var_1 + 139)
- let cse_var_30: int32 = (cse_var_1 + 138)
- let cse_var_29: int32 = (cse_var_1 + 137)
- let cse_var_28: int32 = (cse_var_1 + 136)
- let cse_var_27: int32 = (cse_var_1 + 135)
- let cse_var_26: int32 = (cse_var_1 + 134)
- let cse_var_25: int32 = (cse_var_1 + 133)
- let cse_var_24: int32 = (cse_var_1 + 132)
- let cse_var_23: int32 = (cse_var_1 + 131)
- let cse_var_22: int32 = (cse_var_1 + 130)
- let cse_var_21: int32 = (cse_var_1 + 13)
- let cse_var_20: int32 = (cse_var_1 + 129)
- let cse_var_19: int32 = (cse_var_1 + 128)
- let cse_var_18: int32 = (cse_var_1 + 12)
- let cse_var_17: int32 = (cse_var_1 + 111)
- let cse_var_16: int32 = (cse_var_1 + 110)
- let cse_var_15: int32 = (cse_var_1 + 11)
- let cse_var_14: int32 = (cse_var_1 + 109)
- let cse_var_13: int32 = (cse_var_1 + 108)
- let cse_var_12: int32 = (cse_var_1 + 107)
- let cse_var_11: int32 = (cse_var_1 + 106)
- let cse_var_10: int32 = (cse_var_1 + 105)
- let cse_var_9: int32 = (cse_var_1 + 104)
- let cse_var_8: int32 = (cse_var_1 + 103)
- let cse_var_7: int32 = (cse_var_1 + 102)
- let cse_var_6: int32 = (cse_var_1 + 101)
- let cse_var_5: int32 = (cse_var_1 + 100)
- let cse_var_4: int32 = (cse_var_1 + 10)
- let cse_var_3: int32 = (cse_var_1 + 1)
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[(cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_130)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 1)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 2)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 3)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 4)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 5)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 6)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 7)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 8)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 9)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 10)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 11)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 12)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 13)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 14)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_130) + 15)]*max(placeholder[((cse_var_131 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- }
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(i0.outer.i1.outer.fused, 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 16) {
+ let cse_var_21: int32 = floordiv(i0.outer.i1.outer.fused, 2)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*4096) + (i.inner*256))
+ let cse_var_18: int32 = ((i.outer.inner*256) + (i.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_132: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_132] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_132]), 0f32)
- }
+ let cse_var_23: int32 = (i0.outer.i1.outer.fused*8)
+ let cse_var_22: int32 = ((i0.inner*512) + cse_var_23)
+ compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_23) - (floordiv(i0.outer.i1.outer.fused, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
}
}
}
@@ -1067,7 +733,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.738 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.794 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 edd7bd200..b7e193410 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.184</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.063</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.149</p></td>
+<td><p>00:46.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 0aadb26c7..37557413b 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 218.99/218.99 result: MeasureResult(costs=(0.0010571545379310344,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.079108715057373, timestamp=1661217302.0073135) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/218.99 result: Traceback (most recent call last):
+No: 9 GFLOPS: 190.64/190.64 result: MeasureResult(costs=(0.001214353688888889,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0405170917510986, timestamp=1661223302.3894737) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/190.64 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 261.25/261.25 result: MeasureResult(costs=(0.0008861356353591159,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5200226306915283, timestamp=1661217302.9286811) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 11 GFLOPS: 261.03/261.03 result: MeasureResult(costs=(0.0008868875856353593,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4918577671051025, timestamp=1661223303.3155913) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.26/261.25 result: MeasureResult(costs=(0.0440128,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8412563800811768, timestamp=1661217307.455042) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.35/261.25 result: MeasureResult(costs=(0.06915911549999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.495361804962158, timestamp=1661217308.6873507) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.30/261.03 result: MeasureResult(costs=(0.043679146,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8481605052947998, timestamp=1661223307.8777392) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.35/261.03 result: MeasureResult(costs=(0.06918789099999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.568289518356323, timestamp=1661223309.1209316) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.21/261.25 result: MeasureResult(costs=(0.008205208785714286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2629334926605225, timestamp=1661217319.746553) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.14/261.03 result: MeasureResult(costs=(0.00822618042857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3182265758514404, timestamp=1661223320.137157) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/261.25 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/261.03 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001239
+Time cost of this operator: 0.001249
</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 4725edd18..650062127 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.3 98.745 (1, 2, 10, 10, 3) 2 1 [312.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.015 0.953 (1, 6, 10, 10) 1 1 [3.015]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.301 (1, 1, 10, 10, 3) 1 1 [0.953]
-Total_time - 316.268 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.2 98.74 (1, 2, 10, 10, 3) 2 1 [312.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.954 (1, 6, 10, 10) 1 1 [3.017]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.966 0.305 (1, 1, 10, 10, 3) 1 1 [0.966]
+Total_time - 316.183 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.188 96.595 (1, 6, 10, 10, 1) 2 1 [79.188]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.823 2.224 (1, 6, 10, 10) 1 1 [1.823]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 1.181 (1, 1, 10, 10, 3) 1 1 [0.968]
-Total_time - 81.979 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.188 96.302 (1, 6, 10, 10, 1) 2 1 [80.188]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.113 2.538 (1, 6, 10, 10) 1 1 [2.113]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.161 (1, 1, 10, 10, 3) 1 1 [0.967]
+Total_time - 83.267 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 66a4d90f1..72461f040 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp7_d2xnt8/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpfzv5euk8/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp7_d2xnt8/images/target contains 8144 images
-/tmp/tmp7_d2xnt8/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpfzv5euk8/images/target contains 8144 images
+/tmp/tmpfzv5euk8/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2162 - accuracy: 0.9253 - val_loss: 0.1505 - val_accuracy: 0.9619
+328/328 - 56s - loss: 0.2175 - accuracy: 0.9259 - val_loss: 0.1425 - val_accuracy: 0.9539
Epoch 2/3
-328/328 - 52s - loss: 0.0934 - accuracy: 0.9637 - val_loss: 0.1192 - val_accuracy: 0.9634
+328/328 - 53s - loss: 0.0971 - accuracy: 0.9627 - val_loss: 0.1365 - val_accuracy: 0.9603
Epoch 3/3
-328/328 - 52s - loss: 0.0662 - accuracy: 0.9749 - val_loss: 0.1217 - val_accuracy: 0.9615
+328/328 - 52s - loss: 0.0645 - accuracy: 0.9758 - val_loss: 0.1089 - val_accuracy: 0.9630
-<keras.callbacks.History object at 0x7f52764f1650>
+<keras.callbacks.History object at 0x7efbda0bd710>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 44.227 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 14.122 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 cba23dd93..a1eac98e3 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:36.262</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:08.305</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:44.227</p></td>
+<td><p>05:14.122</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:41.173</p></td>
+<td><p>00:42.997</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.700</p></td>
+<td><p>00:07.824</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.160</p></td>
+<td><p>00:03.360</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 9e78226bd..d43b16263 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.096</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.005</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.680</p></td>
+<td><p>00:31.552</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>00:09.887</p></td>
+<td><p>00:09.957</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>00:01.522</p></td>
+<td><p>00:01.489</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 9ae2ac4f5..b6c9aa082 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f52863d5560>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7efb5147ab00>
</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 4f870c608..8b407f773 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.047</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.110</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.860</p></td>
+<td><p>00:01.904</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>00:00.952</p></td>
+<td><p>00:00.961</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>00:00.543</p></td>
+<td><p>00:00.535</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>00:00.508</p></td>
+<td><p>00:00.522</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>00:00.101</p></td>
+<td><p>00:00.105</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.042</p></td>
+<td><p>00:00.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 2af17d4e3..f3badd45c 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmptu42ibgx/input0.cc'\nsource_filename = \"/tmp/tmptu42ibgx/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/tmpzh40kt43/input0.cc'\nsource_filename = \"/tmp/tmpzh40kt43/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 402aede72..ee171190c 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 66ff3ff29..a9d2817fa 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/8e95bba69/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 584dcf900..41336a4b1 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/8e95bba69/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 118c39c25..f8dea2b49 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/8e95bba69/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 f9af5a3c2..1ffe9b078 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/8e95bba69/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 5a8e77719..c5c8e4867 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/8e95bba69/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 5a0c78bee..4a20494ae 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/8e95bba69/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 aa3983531..db1dc5d75 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/8e95bba69/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 774fd6852..549f7efd8 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/8e95bba69/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 95eb2713d..a3f1699b3 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/8e95bba69/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 6a279caac..989e78438 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/8e95bba69/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 a03f6978c..14bc5a1bf 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/8e95bba69/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 1c3eb59b1..15d16710e 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/8e95bba69/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 ccc70872c..21d9784d8 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/8e95bba69/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 076c7c27a..ec2e32228 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/8e95bba69/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 9836d15e3..02a603266 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/8e95bba69/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 4bfb27ade..e65f60ee0 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/8e95bba69/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 a80401064..6dba98501 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/8e95bba69/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 f296c3e0f..56d4c1398 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/8e95bba69/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 5b9db4f58..758530dd8 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/8e95bba69/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 5331d7b04..dbecac2f4 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/8e95bba69/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 e689f451c..a53be235c 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/8e95bba69/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 5fdb223fd..84a7f6423 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/8e95bba69/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 f83fbad49..f6db190d2 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/8e95bba69/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 3fa52ca59..0fcb9ab45 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/8e95bba69/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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/8e95bba69/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/3bd168194/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 d74a3e74c..6bfa0dd4c 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 d754ae6e5..959d0c8c0 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.768</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:22.007</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.762</p></td>
+<td><p>00:22.000</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 842a585c4..cec8c82dd 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.10s!
+resnet18_v1 inference graph built in 24.09s!
</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 c05386394..bb7c88407 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.61s!
+yolov3-tiny inference graph built in 16.67s!
</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 cb6688d91..bc661d0e3 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:30.862</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:34.006</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.567</p></td>
+<td><p>00:49.779</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>00:42.295</p></td>
+<td><p>00:44.227</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 837003db0..67e588642 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.355</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.295</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.964</p></td>
+<td><p>00:02.893</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.391</p></td>
+<td><p>00:00.402</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 62fdc0464..e2e9c238f 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.717</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.728</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.384</p></td>
+<td><p>00:00.390</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>00:00.332</p></td>
+<td><p>00:00.337</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 025a854b3..b4f8caa51 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -567,7 +567,7 @@ 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: 93.270 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.418 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 057de0950..d32fe4222 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -669,16 +669,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 8.68/8.68 result: MeasureResult(costs=(0.030935066599999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6275863647460938, timestamp=1661216099.8888297) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.79/8.68 result: MeasureResult(costs=(0.0961245438,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.675877332687378, timestamp=1661216101.5898263) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.81/11.81 result: MeasureResult(costs=(0.0227199812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5541176795959473, timestamp=1661216102.6364021) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.62/11.81 result: MeasureResult(costs=(0.1656084674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.774251937866211, timestamp=1661216105.4520175) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.65/11.81 result: MeasureResult(costs=(0.07362594880000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3154656887054443, timestamp=1661216106.8993685) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.78/11.81 result: MeasureResult(costs=(0.1509724626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5314786434173584, timestamp=1661216109.99056) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.81 result: MeasureResult(costs=(0.3077099968,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.043766021728516, timestamp=1661216115.6117537) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.70/11.81 result: MeasureResult(costs=(0.025087378799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5462484359741211, timestamp=1661216116.175242) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.90/11.81 result: MeasureResult(costs=(0.14124858540000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3613462448120117, timestamp=1661216118.6552758) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.80/11.81 result: MeasureResult(costs=(0.0959906124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6528677940368652, timestamp=1661216120.3605332) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.60/10.60 result: MeasureResult(costs=(0.0253293276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5417864322662354, timestamp=1661222060.6588657) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.93/10.60 result: MeasureResult(costs=(0.0916276196,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6544721126556396, timestamp=1661222062.3304863) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022690931,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.555365800857544, timestamp=1661222063.3976574) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.61/11.83 result: MeasureResult(costs=(0.1667162632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7817206382751465, timestamp=1661222066.779948) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.58/11.83 result: MeasureResult(costs=(0.0748927196,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3341362476348877, timestamp=1661222068.2407663) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.74/11.83 result: MeasureResult(costs=(0.15436800479999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.570786952972412, timestamp=1661222070.8539133) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.85/11.83 result: MeasureResult(costs=(0.317051646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.192715883255005, timestamp=1661222076.6295993) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 9.94/11.83 result: MeasureResult(costs=(0.0270035372,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6195971965789795, timestamp=1661222077.26639) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.68/11.83 result: MeasureResult(costs=(0.1599084304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6614413261413574, timestamp=1661222080.0477552) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.46/11.83 result: MeasureResult(costs=(0.1089138932,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.847519874572754, timestamp=1661222081.953327) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 5400acb68..2cf16c0a8 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -551,7 +551,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.095531889996, 'median': 496.25740645001315, 'std': 0.9061120950977117}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.46541508000047, 'median': 496.4040101000023, 'std': 0.6307671095444364}
</pre></div>
</div>
</div>
@@ -706,178 +706,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.52/ 17.52 GFLOPS | Progress: (4/20) | 6.41 s
-[Task 1/25] Current/Best: 6.14/ 17.52 GFLOPS | Progress: (8/20) | 9.45 s
-[Task 1/25] Current/Best: 11.52/ 22.64 GFLOPS | Progress: (12/20) | 11.88 s
-[Task 1/25] Current/Best: 16.41/ 22.64 GFLOPS | Progress: (16/20) | 13.59 s
-[Task 1/25] Current/Best: 11.22/ 23.67 GFLOPS | Progress: (20/20) | 15.35 s Done.
+[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (4/20) | 6.43 s
+[Task 1/25] Current/Best: 6.16/ 17.45 GFLOPS | Progress: (8/20) | 9.42 s
+[Task 1/25] Current/Best: 11.50/ 22.72 GFLOPS | Progress: (12/20) | 11.87 s
+[Task 1/25] Current/Best: 16.38/ 22.74 GFLOPS | Progress: (16/20) | 13.56 s
+[Task 1/25] Current/Best: 11.26/ 23.46 GFLOPS | Progress: (20/20) | 15.33 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.22/ 12.94 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 2/25] Current/Best: 14.18/ 18.65 GFLOPS | Progress: (8/20) | 5.00 s
-[Task 2/25] Current/Best: 21.14/ 21.14 GFLOPS | Progress: (12/20) | 6.33 s
-[Task 2/25] Current/Best: 12.41/ 21.14 GFLOPS | Progress: (16/20) | 7.58 s
-[Task 2/25] Current/Best: 19.87/ 21.14 GFLOPS | Progress: (20/20) | 9.14 s Done.
+[Task 2/25] Current/Best: 12.18/ 13.24 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 2/25] Current/Best: 14.12/ 18.67 GFLOPS | Progress: (8/20) | 5.20 s
+[Task 2/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (12/20) | 6.54 s
+[Task 2/25] Current/Best: 11.08/ 21.17 GFLOPS | Progress: (16/20) | 7.84 s
+[Task 2/25] Current/Best: 20.02/ 21.17 GFLOPS | Progress: (20/20) | 9.45 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.81 GFLOPS | Progress: (4/20) | 5.90 s
-[Task 3/25] Current/Best: 15.31/ 16.77 GFLOPS | Progress: (8/20) | 7.84 s
-[Task 3/25] Current/Best: 14.95/ 16.77 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 3/25] Current/Best: 7.17/ 23.78 GFLOPS | Progress: (16/20) | 11.50 s
-[Task 3/25] Current/Best: 12.61/ 23.78 GFLOPS | Progress: (20/20) | 16.01 s Done.
+[Task 3/25] Current/Best: 1.62/ 10.81 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 3/25] Current/Best: 15.22/ 16.71 GFLOPS | Progress: (8/20) | 7.85 s
+[Task 3/25] Current/Best: 14.97/ 16.71 GFLOPS | Progress: (12/20) | 9.58 s
+[Task 3/25] Current/Best: 7.16/ 23.68 GFLOPS | Progress: (16/20) | 11.51 s
+[Task 3/25] Current/Best: 12.61/ 23.68 GFLOPS | Progress: (20/20) | 16.05 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.36/ 18.95 GFLOPS | Progress: (4/20) | 2.43 s
-[Task 4/25] Current/Best: 6.83/ 18.95 GFLOPS | Progress: (8/20) | 6.79 s
-[Task 4/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (12/20) | 11.36 s
-[Task 4/25] Current/Best: 17.12/ 22.19 GFLOPS | Progress: (16/20) | 13.62 s
-[Task 4/25] Current/Best: 12.83/ 22.19 GFLOPS | Progress: (20/20) | 15.52 s Done.
+[Task 4/25] Current/Best: 9.55/ 18.53 GFLOPS | Progress: (4/20) | 2.44 s
+[Task 4/25] Current/Best: 6.87/ 18.53 GFLOPS | Progress: (8/20) | 6.78 s
+[Task 4/25] Current/Best: 21.71/ 21.71 GFLOPS | Progress: (12/20) | 11.31 s
+[Task 4/25] Current/Best: 16.73/ 21.71 GFLOPS | Progress: (16/20) | 13.53 s
+[Task 4/25] Current/Best: 13.42/ 21.71 GFLOPS | Progress: (20/20) | 15.57 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.52/ 10.10 GFLOPS | Progress: (4/20) | 2.64 s
-[Task 5/25] Current/Best: 11.71/ 12.72 GFLOPS | Progress: (8/20) | 4.72 s
-[Task 5/25] Current/Best: 11.12/ 18.14 GFLOPS | Progress: (12/20) | 7.70 s
-[Task 5/25] Current/Best: 11.64/ 22.67 GFLOPS | Progress: (16/20) | 9.13 s
-[Task 5/25] Current/Best: 11.89/ 22.67 GFLOPS | Progress: (20/20) | 11.00 s Done.
+[Task 5/25] Current/Best: 9.79/ 10.34 GFLOPS | Progress: (4/20) | 2.62 s
+[Task 5/25] Current/Best: 11.95/ 12.97 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 5/25] Current/Best: 10.76/ 18.01 GFLOPS | Progress: (12/20) | 7.82 s
+[Task 5/25] Current/Best: 11.85/ 22.60 GFLOPS | Progress: (16/20) | 9.26 s
+[Task 5/25] Current/Best: 11.68/ 22.60 GFLOPS | Progress: (20/20) | 11.14 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.19/ 20.74 GFLOPS | Progress: (4/20) | 3.98 s
-[Task 6/25] Current/Best: 19.01/ 20.74 GFLOPS | Progress: (8/20) | 5.72 s
-[Task 6/25] Current/Best: 13.27/ 20.74 GFLOPS | Progress: (12/20) | 7.65 s
-[Task 6/25] Current/Best: 20.06/ 20.74 GFLOPS | Progress: (16/20) | 9.89 s
-[Task 6/25] Current/Best: 3.74/ 20.74 GFLOPS | Progress: (20/20) | 12.41 s Done.
+[Task 6/25] Current/Best: 12.26/ 20.62 GFLOPS | Progress: (4/20) | 4.05 s
+[Task 6/25] Current/Best: 18.95/ 20.62 GFLOPS | Progress: (8/20) | 5.81 s
+[Task 6/25] Current/Best: 13.23/ 20.62 GFLOPS | Progress: (12/20) | 7.72 s
+[Task 6/25] Current/Best: 19.92/ 20.62 GFLOPS | Progress: (16/20) | 9.96 s
+[Task 6/25] Current/Best: 3.78/ 20.62 GFLOPS | Progress: (20/20) | 12.48 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.32/ 12.83 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 7/25] Current/Best: 20.51/ 21.37 GFLOPS | Progress: (8/20) | 5.02 s
-[Task 7/25] Current/Best: 16.05/ 21.37 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 7/25] Current/Best: 12.41/ 21.37 GFLOPS | Progress: (16/20) | 8.89 s
-[Task 7/25] Current/Best: 6.33/ 22.04 GFLOPS | Progress: (20/20) | 11.32 s Done.
+[Task 7/25] Current/Best: 11.17/ 12.85 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 7/25] Current/Best: 20.16/ 21.11 GFLOPS | Progress: (8/20) | 5.20 s
+[Task 7/25] Current/Best: 15.77/ 21.11 GFLOPS | Progress: (12/20) | 7.15 s
+[Task 7/25] Current/Best: 12.23/ 21.11 GFLOPS | Progress: (16/20) | 9.18 s
+[Task 7/25] Current/Best: 6.49/ 21.59 GFLOPS | Progress: (20/20) | 11.64 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.15/ 14.04 GFLOPS | Progress: (4/20) | 2.90 s
-[Task 8/25] Current/Best: 9.57/ 14.04 GFLOPS | Progress: (8/20) | 7.48 s
-[Task 8/25] Current/Best: 12.86/ 14.04 GFLOPS | Progress: (12/20) | 13.42 s
-[Task 8/25] Current/Best: 19.12/ 19.12 GFLOPS | Progress: (16/20) | 15.49 s
-[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 21.89 s Done.
+[Task 8/25] Current/Best: 10.53/ 14.65 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 8/25] Current/Best: 10.15/ 14.65 GFLOPS | Progress: (8/20) | 7.68 s
+[Task 8/25] Current/Best: 13.17/ 14.65 GFLOPS | Progress: (12/20) | 13.87 s
+[Task 8/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (16/20) | 15.95 s
+[Task 8/25] Current/Best: 19.76/ 19.76 GFLOPS | Progress: (20/20) | 22.42 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.52/ 15.93 GFLOPS | Progress: (4/20) | 11.94 s
-[Task 9/25] Current/Best: 23.83/ 23.83 GFLOPS | Progress: (8/20) | 13.64 s
-[Task 9/25] Current/Best: 8.37/ 23.83 GFLOPS | Progress: (12/20) | 15.97 s
-[Task 9/25] Current/Best: 18.21/ 23.83 GFLOPS | Progress: (16/20) | 18.55 s
-[Task 9/25] Current/Best: 9.34/ 23.83 GFLOPS | Progress: (20/20) | 25.92 s
+[Task 9/25] Current/Best: 14.08/ 15.72 GFLOPS | Progress: (4/20) | 12.00 s
+[Task 9/25] Current/Best: 22.93/ 22.93 GFLOPS | Progress: (8/20) | 13.84 s
+[Task 9/25] Current/Best: 8.26/ 22.93 GFLOPS | Progress: (12/20) | 16.23 s
+[Task 9/25] Current/Best: 17.84/ 22.93 GFLOPS | Progress: (16/20) | 18.88 s
+[Task 9/25] Current/Best: 9.08/ 22.93 GFLOPS | Progress: (20/20) | 26.59 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/20) | 2.52 s
-[Task 10/25] Current/Best: 15.61/ 18.34 GFLOPS | Progress: (8/20) | 4.07 s
-[Task 10/25] Current/Best: 12.91/ 19.23 GFLOPS | Progress: (12/20) | 5.56 s
-[Task 10/25] Current/Best: 19.36/ 20.46 GFLOPS | Progress: (16/20) | 6.65 s
-[Task 10/25] Current/Best: 9.02/ 20.46 GFLOPS | Progress: (20/20) | 8.14 s Done.
+[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.59 s
+[Task 10/25] Current/Best: 15.58/ 18.20 GFLOPS | Progress: (8/20) | 4.18 s
+[Task 10/25] Current/Best: 13.08/ 19.08 GFLOPS | Progress: (12/20) | 5.70 s
+[Task 10/25] Current/Best: 19.00/ 20.42 GFLOPS | Progress: (16/20) | 6.82 s
+[Task 10/25] Current/Best: 8.84/ 20.42 GFLOPS | Progress: (20/20) | 8.37 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.35/ 18.46 GFLOPS | Progress: (4/20) | 3.23 s
-[Task 11/25] Current/Best: 15.23/ 18.46 GFLOPS | Progress: (8/20) | 5.91 s
-[Task 11/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.90 s
-[Task 11/25] Current/Best: 13.71/ 21.25 GFLOPS | Progress: (16/20) | 10.55 s
-[Task 11/25] Current/Best: 19.74/ 21.81 GFLOPS | Progress: (20/20) | 12.57 s Done.
+[Task 11/25] Current/Best: 12.32/ 18.20 GFLOPS | Progress: (4/20) | 3.38 s
+[Task 11/25] Current/Best: 16.85/ 18.20 GFLOPS | Progress: (8/20) | 6.12 s
+[Task 11/25] Current/Best: 18.05/ 18.20 GFLOPS | Progress: (12/20) | 8.16 s
+[Task 11/25] Current/Best: 12.28/ 20.92 GFLOPS | Progress: (16/20) | 10.96 s
+[Task 11/25] Current/Best: 19.43/ 21.28 GFLOPS | Progress: (20/20) | 13.03 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.86/ 18.29 GFLOPS | Progress: (4/20) | 5.19 s
-[Task 12/25] Current/Best: 5.19/ 18.29 GFLOPS | Progress: (8/20) | 8.83 s
-[Task 12/25] Current/Best: 19.11/ 19.14 GFLOPS | Progress: (12/20) | 10.79 s
-[Task 12/25] Current/Best: 15.72/ 19.14 GFLOPS | Progress: (16/20) | 13.54 s
-[Task 12/25] Current/Best: 15.41/ 19.14 GFLOPS | Progress: (20/20) | 15.47 s Done.
+[Task 12/25] Current/Best: 7.77/ 18.03 GFLOPS | Progress: (4/20) | 5.45 s
+[Task 12/25] Current/Best: 5.34/ 18.03 GFLOPS | Progress: (8/20) | 9.12 s
+[Task 12/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (12/20) | 11.09 s
+[Task 12/25] Current/Best: 15.19/ 18.91 GFLOPS | Progress: (16/20) | 13.87 s
+[Task 12/25] Current/Best: 15.19/ 19.07 GFLOPS | Progress: (20/20) | 15.80 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.68/ 17.31 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 13/25] Current/Best: 16.14/ 20.89 GFLOPS | Progress: (8/20) | 5.99 s
-[Task 13/25] Current/Best: 19.71/ 21.69 GFLOPS | Progress: (12/20) | 8.89 s
-[Task 13/25] Current/Best: 12.30/ 21.69 GFLOPS | Progress: (16/20) | 12.25 s
-[Task 13/25] Current/Best: 18.70/ 21.69 GFLOPS | Progress: (20/20) | 14.50 s Done.
+[Task 13/25] Current/Best: 8.75/ 17.29 GFLOPS | Progress: (4/20) | 3.70 s
+[Task 13/25] Current/Best: 15.97/ 20.91 GFLOPS | Progress: (8/20) | 6.16 s
+[Task 13/25] Current/Best: 19.41/ 21.31 GFLOPS | Progress: (12/20) | 9.09 s
+[Task 13/25] Current/Best: 12.23/ 21.31 GFLOPS | Progress: (16/20) | 12.49 s
+[Task 13/25] Current/Best: 18.73/ 21.31 GFLOPS | Progress: (20/20) | 14.77 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.31 s
-[Task 14/25] Current/Best: 6.08/ 13.60 GFLOPS | Progress: (8/20) | 5.47 s
-[Task 14/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (12/20) | 8.03 s
-[Task 14/25] Current/Best: 16.36/ 20.25 GFLOPS | Progress: (16/20) | 9.68 s Done.
+[Task 14/25] Current/Best: 13.53/ 13.53 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 14/25] Current/Best: 6.07/ 13.53 GFLOPS | Progress: (8/20) | 5.57 s
+[Task 14/25] Current/Best: 20.11/ 20.11 GFLOPS | Progress: (12/20) | 8.12 s
+[Task 14/25] Current/Best: 17.23/ 20.11 GFLOPS | Progress: (16/20) | 9.78 s Done.
-[Task 14/25] Current/Best: 17.39/ 20.25 GFLOPS | Progress: (20/20) | 11.39 s
+[Task 14/25] Current/Best: 17.12/ 20.11 GFLOPS | Progress: (20/20) | 11.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.08/ 17.66 GFLOPS | Progress: (4/20) | 2.72 s
-[Task 15/25] Current/Best: 14.49/ 18.05 GFLOPS | Progress: (8/20) | 4.06 s
-[Task 15/25] Current/Best: 10.50/ 22.56 GFLOPS | Progress: (12/20) | 6.08 s
-[Task 15/25] Current/Best: 20.38/ 22.56 GFLOPS | Progress: (16/20) | 9.04 s
-[Task 15/25] Current/Best: 9.59/ 22.56 GFLOPS | Progress: (20/20) | 10.00 s
+[Task 15/25] Current/Best: 16.17/ 17.57 GFLOPS | Progress: (4/20) | 2.77 s
+[Task 15/25] Current/Best: 14.47/ 18.02 GFLOPS | Progress: (8/20) | 4.13 s
+[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.20 s
+[Task 15/25] Current/Best: 20.43/ 22.28 GFLOPS | Progress: (16/20) | 9.08 s
+[Task 15/25] Current/Best: 9.66/ 22.28 GFLOPS | Progress: (20/20) | 10.06 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.58/ 20.58 GFLOPS | Progress: (4/20) | 2.93 s
-[Task 16/25] Current/Best: 3.04/ 20.58 GFLOPS | Progress: (8/20) | 4.52 s
-[Task 16/25] Current/Best: 19.32/ 20.58 GFLOPS | Progress: (12/20) | 5.72 s
-[Task 16/25] Current/Best: 17.95/ 20.58 GFLOPS | Progress: (16/20) | 7.05 s
-[Task 16/25] Current/Best: 9.92/ 21.97 GFLOPS | Progress: (20/20) | 9.07 s Done.
+[Task 16/25] Current/Best: 20.21/ 20.21 GFLOPS | Progress: (4/20) | 3.04 s
+[Task 16/25] Current/Best: 3.01/ 20.21 GFLOPS | Progress: (8/20) | 4.66 s
+[Task 16/25] Current/Best: 18.91/ 20.21 GFLOPS | Progress: (12/20) | 5.88 s
+[Task 16/25] Current/Best: 17.51/ 20.21 GFLOPS | Progress: (16/20) | 7.22 s
+[Task 16/25] Current/Best: 9.98/ 21.90 GFLOPS | Progress: (20/20) | 9.27 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 11.78/ 18.34 GFLOPS | Progress: (4/20) | 4.71 s
-[Task 17/25] Current/Best: 14.28/ 23.39 GFLOPS | Progress: (8/20) | 7.53 s
-[Task 17/25] Current/Best: 17.00/ 23.39 GFLOPS | Progress: (12/20) | 9.58 s
-[Task 17/25] Current/Best: 16.50/ 23.39 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 17/25] Current/Best: 10.07/ 23.39 GFLOPS | Progress: (20/20) | 13.79 s Done.
+[Task 17/25] Current/Best: 13.81/ 18.33 GFLOPS | Progress: (4/20) | 4.78 s
+[Task 17/25] Current/Best: 12.78/ 22.97 GFLOPS | Progress: (8/20) | 7.67 s
+[Task 17/25] Current/Best: 17.22/ 22.97 GFLOPS | Progress: (12/20) | 9.74 s
+[Task 17/25] Current/Best: 16.36/ 22.97 GFLOPS | Progress: (16/20) | 11.87 s
+[Task 17/25] Current/Best: 10.03/ 22.97 GFLOPS | Progress: (20/20) | 14.00 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.23/ 17.01 GFLOPS | Progress: (4/20) | 3.68 s
-[Task 18/25] Current/Best: 10.59/ 19.64 GFLOPS | Progress: (8/20) | 7.07 s
-[Task 18/25] Current/Best: 19.31/ 19.64 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 18/25] Current/Best: 10.09/ 19.64 GFLOPS | Progress: (16/20) | 12.44 s
-[Task 18/25] Current/Best: 20.88/ 20.88 GFLOPS | Progress: (20/20) | 13.94 s Done.
+[Task 18/25] Current/Best: 11.23/ 18.20 GFLOPS | Progress: (4/20) | 3.74 s
+[Task 18/25] Current/Best: 10.60/ 18.20 GFLOPS | Progress: (8/20) | 7.18 s
+[Task 18/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (12/20) | 9.14 s
+[Task 18/25] Current/Best: 9.97/ 19.41 GFLOPS | Progress: (16/20) | 12.70 s
+[Task 18/25] Current/Best: 20.71/ 20.71 GFLOPS | Progress: (20/20) | 14.21 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.30/ 20.29 GFLOPS | Progress: (4/20) | 5.90 s
-[Task 19/25] Current/Best: 2.69/ 20.29 GFLOPS | Progress: (8/20) | 9.17 s
-[Task 19/25] Current/Best: 20.50/ 21.86 GFLOPS | Progress: (12/20) | 11.94 s
-[Task 19/25] Current/Best: 13.61/ 22.41 GFLOPS | Progress: (16/20) | 14.80 s
-[Task 19/25] Current/Best: 2.71/ 23.31 GFLOPS | Progress: (20/20) | 17.62 s Done.
+[Task 19/25] Current/Best: 6.40/ 20.10 GFLOPS | Progress: (4/20) | 6.23 s
+[Task 19/25] Current/Best: 2.69/ 20.10 GFLOPS | Progress: (8/20) | 9.44 s
+[Task 19/25] Current/Best: 19.46/ 20.70 GFLOPS | Progress: (12/20) | 12.22 s
+[Task 19/25] Current/Best: 13.62/ 21.17 GFLOPS | Progress: (16/20) | 15.10 s
+[Task 19/25] Current/Best: 2.70/ 22.58 GFLOPS | Progress: (20/20) | 17.87 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.09/ 15.21 GFLOPS | Progress: (4/20) | 3.23 s Done.
+[Task 20/25] Current/Best: 8.40/ 15.15 GFLOPS | Progress: (4/20) | 3.40 s Done.
Done.
-[Task 20/25] Current/Best: 9.69/ 15.21 GFLOPS | Progress: (8/20) | 6.49 s
-[Task 20/25] Current/Best: 2.33/ 16.42 GFLOPS | Progress: (12/20) | 10.36 s
-[Task 20/25] Current/Best: 12.38/ 16.42 GFLOPS | Progress: (16/20) | 13.96 s
-[Task 20/25] Current/Best: 12.20/ 22.28 GFLOPS | Progress: (20/20) | 16.03 s
+[Task 20/25] Current/Best: 10.41/ 15.15 GFLOPS | Progress: (8/20) | 6.70 s
+[Task 20/25] Current/Best: 2.32/ 15.15 GFLOPS | Progress: (12/20) | 10.65 s
+[Task 20/25] Current/Best: 12.56/ 15.15 GFLOPS | Progress: (16/20) | 14.44 s
+[Task 20/25] Current/Best: 13.36/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.38/ 17.69 GFLOPS | Progress: (4/20) | 3.19 s
-[Task 21/25] Current/Best: 14.51/ 17.69 GFLOPS | Progress: (8/20) | 4.72 s
-[Task 21/25] Current/Best: 1.61/ 17.69 GFLOPS | Progress: (12/20) | 6.84 s
-[Task 21/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (16/20) | 10.23 s
-[Task 21/25] Current/Best: 4.45/ 17.78 GFLOPS | Progress: (20/20) | 17.14 s
+[Task 21/25] Current/Best: 6.37/ 17.70 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 21/25] Current/Best: 14.57/ 17.70 GFLOPS | Progress: (8/20) | 4.88 s
+[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.04 s
+[Task 21/25] Current/Best: 17.83/ 17.83 GFLOPS | Progress: (16/20) | 10.51 s
+[Task 21/25] Current/Best: 4.46/ 17.83 GFLOPS | Progress: (20/20) | 17.62 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.71/ 17.02 GFLOPS | Progress: (4/20) | 2.66 s
-[Task 22/25] Current/Best: 8.61/ 22.02 GFLOPS | Progress: (8/20) | 4.56 s
-[Task 22/25] Current/Best: 19.75/ 22.02 GFLOPS | Progress: (12/20) | 6.86 s
-[Task 22/25] Current/Best: 15.36/ 22.02 GFLOPS | Progress: (16/20) | 8.89 s
-[Task 22/25] Current/Best: 14.24/ 22.02 GFLOPS | Progress: (20/20) | 10.60 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20) | 2.74 s
+[Task 22/25] Current/Best: 9.17/ 21.61 GFLOPS | Progress: (8/20) | 4.64 s
+[Task 22/25] Current/Best: 19.92/ 21.61 GFLOPS | Progress: (12/20) | 6.94 s
+[Task 22/25] Current/Best: 15.15/ 21.61 GFLOPS | Progress: (16/20) | 9.03 s
+[Task 22/25] Current/Best: 14.87/ 21.61 GFLOPS | Progress: (20/20) | 10.74 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.75/ 20.99 GFLOPS | Progress: (4/20) | 3.23 s
-[Task 23/25] Current/Best: 14.75/ 20.99 GFLOPS | Progress: (8/20) | 6.57 s
-[Task 23/25] Current/Best: 21.01/ 21.88 GFLOPS | Progress: (12/20) | 8.34 s
-[Task 23/25] Current/Best: 6.53/ 21.88 GFLOPS | Progress: (16/20) | 15.24 s
-[Task 23/25] Current/Best: 7.96/ 21.88 GFLOPS | Progress: (20/20) | 19.39 s Done.
+[Task 23/25] Current/Best: 17.35/ 20.29 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 23/25] Current/Best: 15.94/ 20.29 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 23/25] Current/Best: 20.72/ 21.30 GFLOPS | Progress: (12/20) | 8.53 s
+[Task 23/25] Current/Best: 6.24/ 21.30 GFLOPS | Progress: (16/20) | 15.54 s
+[Task 23/25] Current/Best: 7.56/ 21.30 GFLOPS | Progress: (20/20) | 19.80 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.34/ 8.34 GFLOPS | Progress: (4/20) | 11.77 s
-[Task 24/25] Current/Best: 2.02/ 8.34 GFLOPS | Progress: (8/20) | 22.83 s
-[Task 24/25] Current/Best: 4.45/ 8.34 GFLOPS | Progress: (12/20) | 34.39 s Done.
+[Task 24/25] Current/Best: 8.48/ 8.48 GFLOPS | Progress: (4/20) | 11.85 s
+[Task 24/25] Current/Best: 1.96/ 8.48 GFLOPS | Progress: (8/20) | 22.90 s
+[Task 24/25] Current/Best: 4.34/ 8.48 GFLOPS | Progress: (12/20) | 34.46 s Done.
-[Task 24/25] Current/Best: 6.26/ 9.05 GFLOPS | Progress: (16/20) | 39.92 s
-[Task 24/25] Current/Best: 3.39/ 9.06 GFLOPS | Progress: (20/20) | 45.66 s Done.
+[Task 24/25] Current/Best: 7.25/ 8.72 GFLOPS | Progress: (16/20) | 39.89 s
+[Task 24/25] Current/Best: 3.31/ 8.93 GFLOPS | Progress: (20/20) | 45.78 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.75 GFLOPS | Progress: (4/20) | 11.60 s
-[Task 25/25] Current/Best: 6.18/ 8.54 GFLOPS | Progress: (8/20) | 23.04 s
-[Task 25/25] Current/Best: 6.09/ 8.54 GFLOPS | Progress: (12/20) | 34.52 s
-[Task 25/25] Current/Best: 5.97/ 8.93 GFLOPS | Progress: (16/20) | 36.24 s
-[Task 25/25] Current/Best: 2.88/ 9.55 GFLOPS | Progress: (20/20) | 46.93 s
+[Task 25/25] Current/Best: 1.55/ 2.94 GFLOPS | Progress: (4/20) | 11.65 s
+[Task 25/25] Current/Best: 5.65/ 7.42 GFLOPS | Progress: (8/20) | 22.95 s
+[Task 25/25] Current/Best: 5.82/ 7.42 GFLOPS | Progress: (12/20) | 34.39 s
+[Task 25/25] Current/Best: 5.72/ 9.06 GFLOPS | Progress: (16/20) | 36.28 s
+[Task 25/25] Current/Best: 2.93/ 9.06 GFLOPS | Progress: (20/20) | 47.00 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -981,8 +981,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 405.6997717099921, 'median': 405.49599050000324, 'std': 0.5053295578524342}
-unoptimized: {'mean': 496.095531889996, 'median': 496.25740645001315, 'std': 0.9061120950977117}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 412.6048881799966, 'median': 412.17131859999654, 'std': 1.3900040551179313}
+unoptimized: {'mean': 496.46541508000047, 'median': 496.4040101000023, 'std': 0.6307671095444364}
</pre></div>
</div>
</div>
@@ -996,7 +996,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 11.947 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 22.685 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 fa06eb8e5..c8f7ab14c 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -527,7 +527,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.285e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.237e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index fc5dd92cf..b5864abb8 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -484,7 +484,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x23784e40)), stage(b, placeholder(b, 0x213e1080)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x21e52920)), stage(b, placeholder(b, 0xf46d3b0)), 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 de8479342..3d1475c43 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:03.983</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:13.486</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</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>10:11.947</p></td>
+<td><p>10:22.685</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.458</p></td>
+<td><p>00:58.827</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:56.024</p></td>
+<td><p>00:53.834</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>00:30.237</p></td>
+<td><p>00:31.294</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:23.969</p></td>
+<td><p>00:24.816</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.696</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:01.153</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.506</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.711</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>00:00.136</p></td>
+<td><p>00:00.156</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>
@@ -375,15 +375,15 @@
<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<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="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>
+<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>
<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 b221e420c..f7fd5ac58 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -542,7 +542,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
naive: 0.000006
</pre></div>
</div>
@@ -668,10 +668,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.277610002347501e-06 1.0
- naive 5.9196e-06 0.8133989040482446
-parallel 6.1369000000000005e-06 0.8432576076514752
- vector 2.4546299999999996e-05 3.3728518005337222
+ numpy 7.890279998719052e-06 1.0
+ naive 5.791799999999999e-06 0.734042391517192
+parallel 6.047e-06 0.7663859838917884
+ vector 2.46919e-05 3.1294073219212253
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -987,7 +987,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017490
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018969
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1030,7 +1030,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.407462
+none: 3.218482
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1097,7 +1097,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.293541
+blocking: 0.316966
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.331567
+vectorization: 0.347821
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1215,7 +1215,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.111469
+loop permutation: 0.123013
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1293,7 +1293,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.107273
+array packing: 0.110326
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1369,7 +1369,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.110060
+block caching: 0.111111
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1438,7 +1438,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.145915
+parallelization: 0.147077
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4074616575 1.0
- blocking 0.2935412285 0.08614659767451836
- vectorization 0.3315665954 0.09730603854931272
-loop permutation 0.11146864009999999 0.0327131018054603
- array packing 0.10727264489999999 0.031481688037160255
- block caching 0.1100600754 0.032299725268442
- parallelization 0.1459146999 0.04282211058159207
+ none 3.2184822234999997 1.0
+ blocking 0.316966411 0.0984831945584925
+ vectorization 0.34782091039999996 0.10806985598999379
+loop permutation 0.12301334099999998 0.03822091671092929
+ array packing 0.110326467 0.034279035687829085
+ block caching 0.11111058089999999 0.034522664157880814
+ parallelization 0.1470772099 0.045697692168719856
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1538,7 +1538,6 @@ 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 0.458 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>