You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/01/20 10:25:18 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5e36ae331cab8a310b7f5202fc5830787b5bd6d4)
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 6cee9b7386 deploying docs (apache/tvm@5e36ae331cab8a310b7f5202fc5830787b5bd6d4)
6cee9b7386 is described below
commit 6cee9b73864c143ea8b141d83f76a255da892dda
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jan 20 10:25:10 2023 +0000
deploying docs (apache/tvm@5e36ae331cab8a310b7f5202fc5830787b5bd6d4)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 282079 -> 302170 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22031 -> 22480 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 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 | 4 +-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 459 +++------------------
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 260 +++++++++---
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +--
.../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 | 49 ++-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 10 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 42 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 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 | 4 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 459 +++------------------
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 260 +++++++++---
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../classtvm_1_1tir_1_1ScheduleNode-members.html | 2 +-
.../doxygen/classtvm_1_1tir_1_1ScheduleNode.html | 21 +-
docs/reference/api/doxygen/database_8h_source.html | 2 +-
docs/reference/api/doxygen/functions_c.html | 2 +-
docs/reference/api/doxygen/functions_func_c.html | 2 +-
.../api/doxygen/measure__candidate_8h_source.html | 2 +-
docs/reference/api/doxygen/postproc_8h_source.html | 2 +-
.../api/doxygen/schedule__rule_8h_source.html | 2 +-
docs/reference/api/doxygen/search/all_4.js | 2 +-
docs/reference/api/doxygen/search/functions_3.js | 2 +-
.../doxygen/tir_2schedule_2schedule_8h_source.html | 4 +-
docs/reference/api/doxygen/trace_8h_source.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 10 +-
.../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 | 10 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 271 ++++++------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
142 files changed, 1393 insertions(+), 1744 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index d501408c74..2deab86823 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index 12aef69638..9d8a85810f 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index dbddc1d263..63371a5f0f 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.727 seconds)
+ **Total running time of the script:** ( 1 minutes 14.684 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index bd9874d4d7..1885944802 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 938ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 929ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 16b3bea35b..d14ec0a1e4 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip281edc03-6311-457c-b054-e2f5809f278a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9024e707-0efc-4cb7-aea5-7978f97ab1ee 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 0e48ba6be1..f135f7f7e5 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 51.0MB/s]
33%|###3 | 13.9M/41.5M [00:00<00:00, 65.7MB/s]
49%|####8 | 20.3M/41.5M [00:00<00:00, 51.4MB/s]
62%|######1 | 25.6M/41.5M [00:00<00:00, 50.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 52.8MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 45.2MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 49.6MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 48.0MB/s]
35%|###4 | 14.5M/41.5M [00:00<00:00, 57.1MB/s]
51%|#####1 | 21.4M/41.5M [00:00<00:00, 62.9MB/s]
67%|######6 | 27.6M/41.5M [00:00<00:00, 51.0MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 56.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 59.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index bb6b0ff25e..0a7bb4f36a 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
23%|##2 | 10.1M/44.7M [00:00<00:00, 74.9MB/s]
50%|##### | 22.4M/44.7M [00:00<00:00, 102MB/s]
73%|#######3 | 32.6M/44.7M [00:00<00:00, 87.4MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 98.9MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 72.9MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 63.2MB/s]
54%|#####3 | 24.0M/44.7M [00:00<00:00, 67.0MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 58.2MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 65.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 69.0MB/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 1f6ecbe67a..e85d43b94d 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.160 seconds)
+ **Total running time of the script:** ( 1 minutes 19.050 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 2bcd8f169b..195b94270e 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:07.945** total execution time for **how_to_compile_models** files:
+**06:14.168** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:18.160 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:19.050 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:13.727 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.684 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:50.305 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:51.843 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.853 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.362 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:29.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.853 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.227 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.635 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.431 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.524 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:19.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:19.747 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.617 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index caa6e47528..ca8086602a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,7 +727,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2758.3525 2758.4177 2760.3811 2755.1281 1.6989
+ 2544.5655 2544.3349 2547.9377 2542.5576 1.3979
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 6d921eceb2..3075b7705b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6184 15.5163 16.1542 15.4111 0.2631
+ 16.3751 16.3681 16.4464 16.3137 0.0501
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 29723b06b7..ed0e4ff134 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
6%|5 | 10.1M/170M [00:00<00:01, 86.0MB/s]
12%|#2 | 21.2M/170M [00:00<00:01, 97.2MB/s]
18%|#7 | 30.5M/170M [00:00<00:01, 97.6MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 80.4MB/s]
32%|###1 | 53.9M/170M [00:00<00:01, 101MB/s]
38%|###7 | 64.1M/170M [00:00<00:01, 83.8MB/s]
43%|####2 | 72.8M/170M [00:00<00:01, 81.9MB/s]
48%|####7 | 81.0M/170M [00:01<00:01, 75.3MB/s]
53%|#####3 | 90.6M/170M [00:01<00:01, 81.0MB/s]
59%|#####8 | 99.7M/170M [00:01<00:00, 84.7MB/s]
64%|######3 | 108M/170M [00:01<00:00, 76.1MB/s]
71%|####### | 120M/170M [00:01<00:00, 82.0MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 74.7MB/s]
80%|######## | 136M/170M [00:01<00:00, 67.7MB/s]
86%|########5 | 146M/170M [00:01<00:00, 75.6MB/s]
90%|######### | 153M/170M [00:02<00:00, 64.2MB/s]
95%|#########5| 162M/170M [00:02<00:00, 68.0MB/s]
100%|##########| 170M/170M [00:02<00:00, 78.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 8.02M/170M [00:00<00:02, 84.1MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 77.5MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 74.1MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 70.2MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 72.2MB/s]
30%|##9 | 50.2M/170M [00:00<00:01, 83.0MB/s]
35%|###5 | 59.5M/170M [00:00<00:01, 87.5MB/s]
40%|#### | 68.7M/170M [00:00<00:01, 90.0MB/s]
46%|####5 | 77.3M/170M [00:00<00:01, 87.6MB/s]
51%|##### | 85.8M/170M [00:01<00:01, 82.2MB/s]
55%|#####5 | 93.7M/170M [00:01<00:01, 75.6MB/s]
61%|###### | 103M/170M [00:01<00:00, 82.0MB/s]
65%|######5 | 111M/170M [00:01<00:00, 77.9MB/s]
70%|######9 | 119M/170M [00:01<00:00, 75.3MB/s]
74%|#######4 | 126M/170M [00:01<00:00, 67.7MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 68.7MB/s]
82%|########2 | 140M/170M [00:01<00:00, 67.1MB/s]
86%|########6 | 146M/170M [00:02<00:00, 67.0MB/s]
90%|########9 | 153M/170M [00:02<00:00, 61.1MB/s]
93%|#########3| 158M/170M [00:02<00:00, 50.3MB/s]
96%|#########6| 164M/170M [00:02<00:00, 49.0MB/s]
100%|##########| 170M/170M [00:02<00:00, 70.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 21.632 seconds)
+ **Total running time of the script:** ( 3 minutes 26.947 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 8ae9f80c01..1b5e6eaf3b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 76.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 103MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 57.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 64.9MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.1720 90.1005 91.6585 89.8012 0.3037
+ 90.2445 90.1774 91.3289 90.0707 0.2111
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.916 seconds)
+ **Total running time of the script:** ( 1 minutes 13.274 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 02451a16d4..a5ddfda895 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.3536 118.3627 119.9356 117.1745 0.4004
+ 120.1613 120.1603 125.3032 118.4185 0.7664
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 25.221 seconds)
+ **Total running time of the script:** ( 2 minutes 32.873 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 2338c7b8df..b7f83875ab 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.344 seconds)
+ **Total running time of the script:** ( 1 minutes 28.191 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 f9d56cb7a3..84c0a2cbca 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4409/132723 [00:00<00:02, 43293.70KB/s]
8%|8 | 10936/132723 [00:00<00:02, 56120.51KB/s]
14%|#3 | 18550/132723 [00:00<00:01, 65219.72KB/s]
20%|#9 | 26096/132723 [00:00<00:01, 69251.04KB/s]
25%|##5 | 33696/132723 [00:00<00:01, 71679.02KB/s]
31%|###1 | 41335/132723 [00:00<00:01, 73276.82KB/s]
37%|###6 | 48867/132723 [00:00<00:01, 73941.19KB/s]
43%|####2 | 56468/132723 [00:00<00:01, 74596.86KB/s]
48%|####8 | 64162/132723 [00:00<00:00, 75327.52KB/s]
54%|#####4 | 71814/132723 [00:01<00:00, 75692.40KB/s]
60%|#####9 | 79443/132723 [00:01<00:00, 75873.67KB/s]
66%|######5 | 87088/132723 [00:01<00:00, 76047.17KB/s]
71%|#######1 | 94694/132723 [00:01<00:00, 76034.39KB/s]
77%|#######7 | 102397/132723 [00:01<00:00, 76333.30KB/s]
83%|########2 | 110031/132723 [00:01<00:00, 76333.69KB/s]
89%|########8
| 117703/132723 [00:01<00:00, 76447.67KB/s]
94%|#########4| 125369/132723 [00:01<00:00, 76510.11KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73840.87KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7055/132723 [00:00<00:01, 70545.69KB/s]
12%|#1 | 15672/132723 [00:00<00:01, 79733.93KB/s]
18%|#8 | 24274/132723 [00:00<00:01, 82598.57KB/s]
25%|##4 | 32757/132723 [00:00<00:01, 75041.68KB/s]
31%|### | 40975/132723 [00:00<00:01, 77440.29KB/s]
37%|###7 | 49561/132723 [00:00<00:01, 80169.48KB/s]
44%|####3 | 58086/132723 [00:00<00:00, 81776.65KB/s]
50%|##### | 66736/132723 [00:00<00:00, 83245.14KB/s]
57%|#####6 | 75347/132723 [00:00<00:00, 84125.03KB/s]
63%|######3 | 83931/132723 [00:01<00:00, 84639.48KB/s]
70%|######9 | 92493/132723 [00:01<00:00, 84935.51KB/s]
76%|#######6 | 101214/132723 [00:01<00:00, 85622.34KB/s]
83%|########2 | 109868/132723 [00:01<00:00, 85897.02KB/s]
89%|########9 | 118543/132723 [00:01<00:00, 86152.00KB/s]
96%|#########5| 127216/132723 [00:01<00:00, 86323.34KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 83272.90KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 26.377 seconds)
+ **Total running time of the script:** ( 3 minutes 32.040 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 469332e837..de8ba1d09e 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:22.337** total execution time for **how_to_deploy_models** files:
+**14:43.681** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:26.377 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:32.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:21.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:26.947 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:25.221 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.873 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.344 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:28.191 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.916 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.274 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.272 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.396 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:38.670 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:41.364 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.085 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.162 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.814 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.427 | 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 3ead13366d..a49d5c45ac 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip07fb9aa0-cc7e-474e-ab93-9e3af8a9a86f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf0648fd1-8d92-4104-b906-1105398fbcbc 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 a5decbd58b..f1e05b880f 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
=================
-**00:50.546** total execution time for **how_to_extend_tvm** files:
+**00:52.197** 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``) | 00:46.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:48.515 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.544 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.615 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.060 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index edaff2d669..3021f8d12b 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 17614us [17614us] (48.44%; 48.44%)
- FoldScaleAxis: 18746us [6us] (51.56%; 51.56%)
- FoldConstant: 18740us [1648us] (51.54%; 99.97%)
- InferType: 17091us [17091us] (47.00%; 91.20%)
+ InferType: 19102us [19102us] (49.49%; 49.49%)
+ FoldScaleAxis: 19494us [9us] (50.51%; 50.51%)
+ FoldConstant: 19485us [2040us] (50.48%; 99.95%)
+ InferType: 17444us [17444us] (45.20%; 89.53%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 17137us [17137us] (47.94%; 47.94%)
- FoldScaleAxis: 18611us [5us] (52.06%; 52.06%)
- FoldConstant: 18606us [1663us] (52.05%; 99.97%)
- InferType: 16943us [16943us] (47.40%; 91.06%)
+ InferType: 17425us [17425us] (47.84%; 47.84%)
+ FoldScaleAxis: 18998us [6us] (52.16%; 52.16%)
+ FoldConstant: 18992us [1712us] (52.14%; 99.97%)
+ InferType: 17280us [17280us] (47.44%; 90.99%)
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 afada960c6..3dc7a982da 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.217983 ms
+ Convolution: 54.135360 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 e93ff5c59c..15c9ed5deb 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
@@ -602,7 +602,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.685200 ms
+ conv2d with tensor core: 8.441040 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 02f2bbe7f7..f23e96ccb7 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018060
- Baseline: 3.197752
+ Numpy running time: 0.019009
+ Baseline: 3.357877
@@ -224,7 +224,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296106
+ Opt1: 0.318953
@@ -312,7 +312,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333387
+ Opt2: 0.347315
@@ -397,7 +397,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114968
+ Opt3: 0.124776
@@ -511,7 +511,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108361
+ Opt4: 0.109624
@@ -620,7 +620,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111469
+ Opt5: 0.111574
@@ -730,7 +730,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146623
+ Opt6: 0.147443
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 9ea002bb02..d1823e28a7 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
=================
-**00:33.932** total execution time for **how_to_optimize_operators** files:
+**00:35.447** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.743 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.426 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.558 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.025 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.147 | 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 f2f08d6578..0b03df75cb 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
=================
-**09:06.030** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:13.498** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:27.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:30.275 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:36.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:40.071 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.732 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:06.565 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.263 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.565 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.191 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.577 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.132 | 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 c1d24be76f..2e4326337a 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
@@ -765,7 +765,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.355 ms
+ Execution time of this operator: 0.356 ms
@@ -1372,7 +1372,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 27.031 seconds)
+ **Total running time of the script:** ( 5 minutes 30.275 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index 1bab3f78c4..0abc4f6f1c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8663 7.8661 7.8708 7.8619 0.0036
+ 7.9210 7.9195 7.9253 7.9182 0.0031
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.732 seconds)
+ **Total running time of the script:** ( 1 minutes 6.565 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index fa4ff17b5e..d2060dcd38 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)
- 750.0263 750.0990 750.6909 749.2892 0.5746
+ 757.7189 759.5375 759.7802 753.8389 2.7453
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.571 seconds)
+ **Total running time of the script:** ( 1 minutes 40.071 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 f541801123..d425e976fc 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,407 +386,74 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.buffer_decl((512,), data=compute_1)
- for i_outer_inner, nb_j_inner in T.grid(2, 2):
- cse_var_2: T.int32 = i_outer_inner * 256 + nb_j_inner * 16
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- compute_2[cse_var_2] = T.float32(0)
- compute_2[cse_var_2 + 1] = T.float32(0)
- compute_2[cse_var_2 + 2] = T.float32(0)
- compute_2[cse_var_2 + 3] = T.float32(0)
- compute_2[cse_var_2 + 4] = T.float32(0)
- compute_2[cse_var_2 + 5] = T.float32(0)
- compute_2[cse_var_2 + 6] = T.float32(0)
- compute_2[cse_var_2 + 7] = T.float32(0)
- compute_2[cse_var_2 + 8] = T.float32(0)
- compute_2[cse_var_2 + 9] = T.float32(0)
- compute_2[cse_var_2 + 10] = T.float32(0)
- compute_2[cse_var_2 + 11] = T.float32(0)
- compute_2[cse_var_2 + 12] = T.float32(0)
- compute_2[cse_var_2 + 13] = T.float32(0)
- compute_2[cse_var_2 + 14] = T.float32(0)
- compute_2[cse_var_2 + 15] = T.float32(0)
- compute_2[cse_var_2 + 32] = T.float32(0)
- compute_2[cse_var_2 + 33] = T.float32(0)
- compute_2[cse_var_2 + 34] = T.float32(0)
- compute_2[cse_var_2 + 35] = T.float32(0)
- compute_2[cse_var_2 + 36] = T.float32(0)
- compute_2[cse_var_2 + 37] = T.float32(0)
- compute_2[cse_var_2 + 38] = T.float32(0)
- compute_2[cse_var_2 + 39] = T.float32(0)
- compute_2[cse_var_2 + 40] = T.float32(0)
- compute_2[cse_var_2 + 41] = T.float32(0)
- compute_2[cse_var_2 + 42] = T.float32(0)
- compute_2[cse_var_2 + 43] = T.float32(0)
- compute_2[cse_var_2 + 44] = T.float32(0)
- compute_2[cse_var_2 + 45] = T.float32(0)
- compute_2[cse_var_2 + 46] = T.float32(0)
- compute_2[cse_var_2 + 47] = T.float32(0)
- compute_2[cse_var_2 + 64] = T.float32(0)
- compute_2[cse_var_2 + 65] = T.float32(0)
- compute_2[cse_var_2 + 66] = T.float32(0)
- compute_2[cse_var_2 + 67] = T.float32(0)
- compute_2[cse_var_2 + 68] = T.float32(0)
- compute_2[cse_var_2 + 69] = T.float32(0)
- compute_2[cse_var_2 + 70] = T.float32(0)
- compute_2[cse_var_2 + 71] = T.float32(0)
- compute_2[cse_var_2 + 72] = T.float32(0)
- compute_2[cse_var_2 + 73] = T.float32(0)
- compute_2[cse_var_2 + 74] = T.float32(0)
- compute_2[cse_var_2 + 75] = T.float32(0)
- compute_2[cse_var_2 + 76] = T.float32(0)
- compute_2[cse_var_2 + 77] = T.float32(0)
- compute_2[cse_var_2 + 78] = T.float32(0)
- compute_2[cse_var_2 + 79] = T.float32(0)
- compute_2[cse_var_2 + 96] = T.float32(0)
- compute_2[cse_var_2 + 97] = T.float32(0)
- compute_2[cse_var_2 + 98] = T.float32(0)
- compute_2[cse_var_2 + 99] = T.float32(0)
- compute_2[cse_var_2 + 100] = T.float32(0)
- compute_2[cse_var_2 + 101] = T.float32(0)
- compute_2[cse_var_2 + 102] = T.float32(0)
- compute_2[cse_var_2 + 103] = T.float32(0)
- compute_2[cse_var_2 + 104] = T.float32(0)
- compute_2[cse_var_2 + 105] = T.float32(0)
- compute_2[cse_var_2 + 106] = T.float32(0)
- compute_2[cse_var_2 + 107] = T.float32(0)
- compute_2[cse_var_2 + 108] = T.float32(0)
- compute_2[cse_var_2 + 109] = T.float32(0)
- compute_2[cse_var_2 + 110] = T.float32(0)
- compute_2[cse_var_2 + 111] = T.float32(0)
- compute_2[cse_var_2 + 128] = T.float32(0)
- compute_2[cse_var_2 + 129] = T.float32(0)
- compute_2[cse_var_2 + 130] = T.float32(0)
- compute_2[cse_var_2 + 131] = T.float32(0)
- compute_2[cse_var_2 + 132] = T.float32(0)
- compute_2[cse_var_2 + 133] = T.float32(0)
- compute_2[cse_var_2 + 134] = T.float32(0)
- compute_2[cse_var_2 + 135] = T.float32(0)
- compute_2[cse_var_2 + 136] = T.float32(0)
- compute_2[cse_var_2 + 137] = T.float32(0)
- compute_2[cse_var_2 + 138] = T.float32(0)
- compute_2[cse_var_2 + 139] = T.float32(0)
- compute_2[cse_var_2 + 140] = T.float32(0)
- compute_2[cse_var_2 + 141] = T.float32(0)
- compute_2[cse_var_2 + 142] = T.float32(0)
- compute_2[cse_var_2 + 143] = T.float32(0)
- compute_2[cse_var_2 + 160] = T.float32(0)
- compute_2[cse_var_2 + 161] = T.float32(0)
- compute_2[cse_var_2 + 162] = T.float32(0)
- compute_2[cse_var_2 + 163] = T.float32(0)
- compute_2[cse_var_2 + 164] = T.float32(0)
- compute_2[cse_var_2 + 165] = T.float32(0)
- compute_2[cse_var_2 + 166] = T.float32(0)
- compute_2[cse_var_2 + 167] = T.float32(0)
- compute_2[cse_var_2 + 168] = T.float32(0)
- compute_2[cse_var_2 + 169] = T.float32(0)
- compute_2[cse_var_2 + 170] = T.float32(0)
- compute_2[cse_var_2 + 171] = T.float32(0)
- compute_2[cse_var_2 + 172] = T.float32(0)
- compute_2[cse_var_2 + 173] = T.float32(0)
- compute_2[cse_var_2 + 174] = T.float32(0)
- compute_2[cse_var_2 + 175] = T.float32(0)
- compute_2[cse_var_2 + 192] = T.float32(0)
- compute_2[cse_var_2 + 193] = T.float32(0)
- compute_2[cse_var_2 + 194] = T.float32(0)
- compute_2[cse_var_2 + 195] = T.float32(0)
- compute_2[cse_var_2 + 196] = T.float32(0)
- compute_2[cse_var_2 + 197] = T.float32(0)
- compute_2[cse_var_2 + 198] = T.float32(0)
- compute_2[cse_var_2 + 199] = T.float32(0)
- compute_2[cse_var_2 + 200] = T.float32(0)
- compute_2[cse_var_2 + 201] = T.float32(0)
- compute_2[cse_var_2 + 202] = T.float32(0)
- compute_2[cse_var_2 + 203] = T.float32(0)
- compute_2[cse_var_2 + 204] = T.float32(0)
- compute_2[cse_var_2 + 205] = T.float32(0)
- compute_2[cse_var_2 + 206] = T.float32(0)
- compute_2[cse_var_2 + 207] = T.float32(0)
- compute_2[cse_var_2 + 224] = T.float32(0)
- compute_2[cse_var_2 + 225] = T.float32(0)
- compute_2[cse_var_2 + 226] = T.float32(0)
- compute_2[cse_var_2 + 227] = T.float32(0)
- compute_2[cse_var_2 + 228] = T.float32(0)
- compute_2[cse_var_2 + 229] = T.float32(0)
- compute_2[cse_var_2 + 230] = T.float32(0)
- compute_2[cse_var_2 + 231] = T.float32(0)
- compute_2[cse_var_2 + 232] = T.float32(0)
- compute_2[cse_var_2 + 233] = T.float32(0)
- compute_2[cse_var_2 + 234] = T.float32(0)
- compute_2[cse_var_2 + 235] = T.float32(0)
- compute_2[cse_var_2 + 236] = T.float32(0)
- compute_2[cse_var_2 + 237] = T.float32(0)
- compute_2[cse_var_2 + 238] = T.float32(0)
- compute_2[cse_var_2 + 239] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ for i0_outer_i1_outer_fused in T.parallel(512):
+ compute_1 = T.allocate([128], "float32", "global")
+ compute_2 = T.buffer_decl((128,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init in range(4):
+ cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ compute_2[cse_var_1 + 13] = T.float32(0)
+ compute_2[cse_var_1 + 14] = T.float32(0)
+ compute_2[cse_var_1 + 15] = T.float32(0)
+ for elem_idx, i_inner in T.grid(T.let(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 4):
+ cse_var_2 = T.var("int32")
placeholder_5 = T.buffer_decl((33,), "int32", data=placeholder_3.data)
- cse_var_131: T.int32 = elem_idx * 16
- cse_var_130: T.int32 = cse_var_2 + 99
- cse_var_129: T.int32 = cse_var_2 + 98
- cse_var_128: T.int32 = cse_var_2 + 97
- cse_var_127: T.int32 = cse_var_2 + 96
- cse_var_126: T.int32 = cse_var_2 + 9
- cse_var_125: T.int32 = cse_var_2 + 8
- cse_var_124: T.int32 = cse_var_2 + 79
- cse_var_123: T.int32 = cse_var_2 + 78
- cse_var_122: T.int32 = cse_var_2 + 77
- cse_var_121: T.int32 = cse_var_2 + 76
- cse_var_120: T.int32 = cse_var_2 + 75
- cse_var_119: T.int32 = cse_var_2 + 74
- cse_var_118: T.int32 = cse_var_2 + 73
- cse_var_117: T.int32 = cse_var_2 + 72
- cse_var_116: T.int32 = cse_var_2 + 71
- cse_var_115: T.int32 = cse_var_2 + 70
- cse_var_114: T.int32 = cse_var_2 + 7
- cse_var_113: T.int32 = cse_var_2 + 69
- cse_var_112: T.int32 = cse_var_2 + 68
- cse_var_111: T.int32 = cse_var_2 + 67
- cse_var_110: T.int32 = cse_var_2 + 66
- cse_var_109: T.int32 = cse_var_2 + 65
- cse_var_108: T.int32 = cse_var_2 + 64
- cse_var_107: T.int32 = cse_var_2 + 6
- cse_var_106: T.int32 = cse_var_2 + 5
- cse_var_105: T.int32 = cse_var_2 + 47
- cse_var_104: T.int32 = cse_var_2 + 46
- cse_var_103: T.int32 = cse_var_2 + 45
- cse_var_102: T.int32 = cse_var_2 + 44
- cse_var_101: T.int32 = cse_var_2 + 43
- cse_var_100: T.int32 = cse_var_2 + 42
- cse_var_99: T.int32 = cse_var_2 + 41
- cse_var_98: T.int32 = cse_var_2 + 40
- cse_var_97: T.int32 = cse_var_2 + 4
- cse_var_96: T.int32 = cse_var_2 + 39
- cse_var_95: T.int32 = cse_var_2 + 38
- cse_var_94: T.int32 = cse_var_2 + 37
- cse_var_93: T.int32 = cse_var_2 + 36
- cse_var_92: T.int32 = cse_var_2 + 35
- cse_var_91: T.int32 = cse_var_2 + 34
- cse_var_90: T.int32 = cse_var_2 + 33
- cse_var_89: T.int32 = cse_var_2 + 32
- cse_var_88: T.int32 = cse_var_2 + 3
- cse_var_87: T.int32 = cse_var_2 + 239
- cse_var_86: T.int32 = cse_var_2 + 238
- cse_var_85: T.int32 = cse_var_2 + 237
- cse_var_84: T.int32 = cse_var_2 + 236
- cse_var_83: T.int32 = cse_var_2 + 235
- cse_var_82: T.int32 = cse_var_2 + 234
- cse_var_81: T.int32 = cse_var_2 + 233
- cse_var_80: T.int32 = cse_var_2 + 232
- cse_var_79: T.int32 = cse_var_2 + 231
- cse_var_78: T.int32 = cse_var_2 + 230
- cse_var_77: T.int32 = cse_var_2 + 229
- cse_var_76: T.int32 = cse_var_2 + 228
- cse_var_75: T.int32 = cse_var_2 + 227
- cse_var_74: T.int32 = cse_var_2 + 226
- cse_var_73: T.int32 = cse_var_2 + 225
- cse_var_72: T.int32 = cse_var_2 + 224
- cse_var_71: T.int32 = cse_var_2 + 207
- cse_var_70: T.int32 = cse_var_2 + 206
- cse_var_69: T.int32 = cse_var_2 + 205
- cse_var_68: T.int32 = cse_var_2 + 204
- cse_var_67: T.int32 = cse_var_2 + 203
- cse_var_66: T.int32 = cse_var_2 + 202
- cse_var_65: T.int32 = cse_var_2 + 201
- cse_var_64: T.int32 = cse_var_2 + 200
- cse_var_63: T.int32 = cse_var_2 + 2
- cse_var_62: T.int32 = cse_var_2 + 199
- cse_var_61: T.int32 = cse_var_2 + 198
- cse_var_60: T.int32 = cse_var_2 + 197
- cse_var_59: T.int32 = cse_var_2 + 196
- cse_var_58: T.int32 = cse_var_2 + 195
- cse_var_57: T.int32 = cse_var_2 + 194
- cse_var_56: T.int32 = cse_var_2 + 193
- cse_var_55: T.int32 = cse_var_2 + 192
- cse_var_54: T.int32 = cse_var_2 + 175
- cse_var_53: T.int32 = cse_var_2 + 174
- cse_var_52: T.int32 = cse_var_2 + 173
- cse_var_51: T.int32 = cse_var_2 + 172
- cse_var_50: T.int32 = cse_var_2 + 171
- cse_var_49: T.int32 = cse_var_2 + 170
- cse_var_48: T.int32 = cse_var_2 + 169
- cse_var_47: T.int32 = cse_var_2 + 168
- cse_var_46: T.int32 = cse_var_2 + 167
- cse_var_45: T.int32 = cse_var_2 + 166
- cse_var_44: T.int32 = cse_var_2 + 165
- cse_var_43: T.int32 = cse_var_2 + 164
- cse_var_42: T.int32 = cse_var_2 + 163
- cse_var_41: T.int32 = cse_var_2 + 162
- cse_var_40: T.int32 = cse_var_2 + 161
- cse_var_39: T.int32 = cse_var_2 + 160
- cse_var_38: T.int32 = cse_var_2 + 15
- cse_var_37: T.int32 = cse_var_2 + 143
- cse_var_36: T.int32 = cse_var_2 + 142
- cse_var_35: T.int32 = cse_var_2 + 141
- cse_var_34: T.int32 = cse_var_2 + 140
- cse_var_33: T.int32 = cse_var_2 + 14
- cse_var_32: T.int32 = cse_var_2 + 139
- cse_var_31: T.int32 = cse_var_2 + 138
- cse_var_30: T.int32 = cse_var_2 + 137
- cse_var_29: T.int32 = cse_var_2 + 136
- cse_var_28: T.int32 = cse_var_2 + 135
- cse_var_27: T.int32 = cse_var_2 + 134
- cse_var_26: T.int32 = cse_var_2 + 133
- cse_var_25: T.int32 = cse_var_2 + 132
- cse_var_24: T.int32 = cse_var_2 + 131
- cse_var_23: T.int32 = cse_var_2 + 130
- cse_var_22: T.int32 = cse_var_2 + 13
- cse_var_21: T.int32 = cse_var_2 + 129
- cse_var_20: T.int32 = cse_var_2 + 128
- cse_var_19: T.int32 = cse_var_2 + 12
- cse_var_18: T.int32 = cse_var_2 + 111
- cse_var_17: T.int32 = cse_var_2 + 110
- cse_var_16: T.int32 = cse_var_2 + 11
- cse_var_15: T.int32 = cse_var_2 + 109
- cse_var_14: T.int32 = cse_var_2 + 108
- cse_var_13: T.int32 = cse_var_2 + 107
- cse_var_12: T.int32 = cse_var_2 + 106
- cse_var_11: T.int32 = cse_var_2 + 105
- cse_var_10: T.int32 = cse_var_2 + 104
- cse_var_9: T.int32 = cse_var_2 + 103
- cse_var_8: T.int32 = cse_var_2 + 102
- cse_var_7: T.int32 = cse_var_2 + 101
- cse_var_6: T.int32 = cse_var_2 + 100
- cse_var_5: T.int32 = cse_var_2 + 10
- cse_var_4: T.int32 = cse_var_2 + 1
- cse_var_3: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i_outer_inner * 2048
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 1024 + i_inner * 256
+ cse_var_17: T.int32 = cse_var_20 + 9
+ cse_var_16: T.int32 = cse_var_20 + 8
+ cse_var_15: T.int32 = cse_var_20 + 7
+ cse_var_14: T.int32 = cse_var_20 + 6
+ cse_var_13: T.int32 = cse_var_20 + 5
+ cse_var_12: T.int32 = cse_var_20 + 4
+ cse_var_11: T.int32 = cse_var_20 + 3
+ cse_var_10: T.int32 = cse_var_20 + 2
+ cse_var_9: T.int32 = cse_var_20 + 15
+ cse_var_8: T.int32 = cse_var_20 + 14
+ cse_var_7: T.int32 = cse_var_20 + 13
+ cse_var_6: T.int32 = cse_var_20 + 12
+ cse_var_5: T.int32 = cse_var_20 + 11
+ cse_var_4: T.int32 = cse_var_20 + 10
+ cse_var_3: T.int32 = cse_var_20 + 1
placeholder_6 = T.buffer_decl((78656,), data=placeholder_1.data)
placeholder_7 = T.buffer_decl((32768,), data=placeholder.data)
placeholder_8 = T.buffer_decl((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_63] = compute_2[cse_var_63] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_88] = compute_2[cse_var_88] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_97] = compute_2[cse_var_97] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_106] = compute_2[cse_var_106] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_107] = compute_2[cse_var_107] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_114] = compute_2[cse_var_114] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_125] = compute_2[cse_var_125] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_126] = compute_2[cse_var_126] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_22] = compute_2[cse_var_22] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_33] = compute_2[cse_var_33] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_38] = compute_2[cse_var_38] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_89] = compute_2[cse_var_89] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_90] = compute_2[cse_var_90] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_91] = compute_2[cse_var_91] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_92] = compute_2[cse_var_92] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_93] = compute_2[cse_var_93] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_94] = compute_2[cse_var_94] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_95] = compute_2[cse_var_95] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_96] = compute_2[cse_var_96] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_98] = compute_2[cse_var_98] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_99] = compute_2[cse_var_99] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_100] = compute_2[cse_var_100] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_101] = compute_2[cse_var_101] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_102] = compute_2[cse_var_102] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_103] = compute_2[cse_var_103] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_104] = compute_2[cse_var_104] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_105] = compute_2[cse_var_105] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_108] = compute_2[cse_var_108] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_109] = compute_2[cse_var_109] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_110] = compute_2[cse_var_110] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_111] = compute_2[cse_var_111] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_112] = compute_2[cse_var_112] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_113] = compute_2[cse_var_113] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_115] = compute_2[cse_var_115] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_116] = compute_2[cse_var_116] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_117] = compute_2[cse_var_117] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_118] = compute_2[cse_var_118] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_119] = compute_2[cse_var_119] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_120] = compute_2[cse_var_120] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_121] = compute_2[cse_var_121] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_122] = compute_2[cse_var_122] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_123] = compute_2[cse_var_123] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_124] = compute_2[cse_var_124] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_127] = compute_2[cse_var_127] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_128] = compute_2[cse_var_128] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_129] = compute_2[cse_var_129] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_130] = compute_2[cse_var_130] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_21] = compute_2[cse_var_21] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_23] = compute_2[cse_var_23] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_24] = compute_2[cse_var_24] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_25] = compute_2[cse_var_25] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_26] = compute_2[cse_var_26] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_27] = compute_2[cse_var_27] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_28] = compute_2[cse_var_28] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_29] = compute_2[cse_var_29] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_30] = compute_2[cse_var_30] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_31] = compute_2[cse_var_31] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_32] = compute_2[cse_var_32] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_34] = compute_2[cse_var_34] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_35] = compute_2[cse_var_35] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_36] = compute_2[cse_var_36] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_37] = compute_2[cse_var_37] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_39] = compute_2[cse_var_39] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_40] = compute_2[cse_var_40] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_41] = compute_2[cse_var_41] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_42] = compute_2[cse_var_42] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_43] = compute_2[cse_var_43] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_44] = compute_2[cse_var_44] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_45] = compute_2[cse_var_45] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_46] = compute_2[cse_var_46] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_47] = compute_2[cse_var_47] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_48] = compute_2[cse_var_48] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_49] = compute_2[cse_var_49] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_50] = compute_2[cse_var_50] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_51] = compute_2[cse_var_51] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_52] = compute_2[cse_var_52] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_53] = compute_2[cse_var_53] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_54] = compute_2[cse_var_54] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_55] = compute_2[cse_var_55] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_56] = compute_2[cse_var_56] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_57] = compute_2[cse_var_57] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_58] = compute_2[cse_var_58] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_59] = compute_2[cse_var_59] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_60] = compute_2[cse_var_60] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_61] = compute_2[cse_var_61] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_62] = compute_2[cse_var_62] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_64] = compute_2[cse_var_64] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_65] = compute_2[cse_var_65] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_66] = compute_2[cse_var_66] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_67] = compute_2[cse_var_67] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_68] = compute_2[cse_var_68] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_69] = compute_2[cse_var_69] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_70] = compute_2[cse_var_70] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_71] = compute_2[cse_var_71] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_72] = compute_2[cse_var_72] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_73] = compute_2[cse_var_73] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_74] = compute_2[cse_var_74] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_75] = compute_2[cse_var_75] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_76] = compute_2[cse_var_76] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_77] = compute_2[cse_var_77] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_78] = compute_2[cse_var_78] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_79] = compute_2[cse_var_79] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_80] = compute_2[cse_var_80] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_81] = compute_2[cse_var_81] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_82] = compute_2[cse_var_82] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_83] = compute_2[cse_var_83] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_84] = compute_2[cse_var_84] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_85] = compute_2[cse_var_85] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_86] = compute_2[cse_var_86] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_87] = compute_2[cse_var_87] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- for i0_inner in range(16):
- cse_var_132: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ for i0_inner in range(4):
+ cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 2048 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.buffer_decl((65536,), data=compute.data)
placeholder_5 = T.buffer_decl((65536,), data=placeholder_4.data)
- compute_3[cse_var_132:cse_var_132 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_132:cse_var_132 + 32], T.Broadcast(T.float32(0), 32))
+ compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
@@ -836,7 +503,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.768 ms
+ Execution time of this operator: 1.848 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 9137835e06..513c1885a3 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:41.552** total execution time for **how_to_tune_with_autotvm** files:
+**00:42.629** 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``) | 00:41.519 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:42.596 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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 194b082ce6..92b564f1a6 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
@@ -268,8 +268,9 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 7.75/7.75 result: MeasureResult(costs=(0.0298710955,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.783884048461914, timestamp=1674185426.5654202) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,41550
- No: 2 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 224.33/224.33 result: MeasureResult(costs=(0.0010319512178217822,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0957257747650146, timestamp=1674208851.3760052) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2521220
+ No: 2 GFLOPS: 5.65/224.33 result: MeasureResult(costs=(0.0409666975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.2628161907196045, timestamp=1674208852.342046) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7945067
+ No: 3 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -391,8 +392,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1224397
- No: 3 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3153438
+ No: 4 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -514,8 +515,161 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10372241
- No: 4 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9153133
+ No: 5 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 4: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+ During handling of the above exception, another exception occurred:
+
+ Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f95217c5fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+ Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5489408
+ No: 6 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -637,8 +791,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10342327
- No: 5 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10277052
+ No: 7 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,9 +914,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4392618
- No: 6 GFLOPS: 127.76/127.76 result: MeasureResult(costs=(0.0018119425555555557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.839144229888916, timestamp=1674185434.4324708) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9502410
- No: 7 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1459555
+ No: 8 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -884,8 +1037,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6022183
- No: 8 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10210078
+ No: 9 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1007,8 +1160,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2289829
- No: 9 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2937055
+ No: 10 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1130,26 +1283,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7162656
- No: 10 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9195726
- No: 11 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8708587
+ No: 11 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1271,8 +1406,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5058574
- No: 12 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7064602
+ No: 12 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9952904
+ No: 13 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1394,10 +1547,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2190495
- No: 13 GFLOPS: 2.71/127.76 result: MeasureResult(costs=(0.08529100775000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.805093050003052, timestamp=1674185450.5576441) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7325263
- No: 14 GFLOPS: 299.03/299.03 result: MeasureResult(costs=(0.000774184811594203,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5905015468597412, timestamp=1674185451.5622723) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,436081
- No: 15 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2108670
+ No: 14 GFLOPS: 31.44/224.33 result: MeasureResult(costs=(0.007363165714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9638252258300781, timestamp=1674208874.2653227) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6995175
+ No: 15 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1519,8 +1671,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2864031
- No: 16 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8128400
+ No: 16 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1642,8 +1794,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5632838
- No: 17 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7031901
+ No: 17 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1765,8 +1917,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2313260
- No: 18 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,477880
+ No: 18 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1888,8 +2040,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9836868
- No: 19 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,116947
+ No: 19 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2011,8 +2163,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7970924
- No: 20 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6647737
+ No: 20 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2134,7 +2286,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3935986
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7368198
@@ -2189,9 +2341,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,436081
+ [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2521220
Finish loading 20 records
- Time cost of this operator: 0.001133
+ Time cost of this operator: 0.001407
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 b6057f0766..631347b999 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
@@ -363,10 +363,10 @@ 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 307.8 98.719 (1, 2, 10, 10, 3) 2 1 [307.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.969 (1, 6, 10, 10) 1 1 [3.021]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.312 (1, 1, 10, 10, 3) 1 1 [0.972]
- Total_time - 311.793 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.729 (1, 2, 10, 10, 3) 2 1 [310.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.966 (1, 6, 10, 10) 1 1 [3.042]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.305 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 314.902 - - - - -
@@ -431,10 +431,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.8 97.555 (1, 6, 10, 10, 1) 2 1 [104.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.776 1.653 (1, 6, 10, 10) 1 1 [1.776]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.851 0.792 (1, 3, 10, 10, 1) 1 1 [0.851]
- Total_time - 107.426 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.7 97.488 (1, 6, 10, 10, 1) 2 1 [103.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.817 1.708 (1, 6, 10, 10) 1 1 [1.817]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.855 0.804 (1, 3, 10, 10, 1) 1 1 [0.855]
+ Total_time - 106.372 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 2cd0784826..650c017925 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -117,7 +117,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 137MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
88%|########8 | 3.02M/3.42M [00:00<00:00, 31.7MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 35.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.086 seconds)
+ **Total running time of the script:** ( 1 minutes 9.733 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 12be13df9d..d30d7385dd 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpiql0qhf6/images/random'
+ '/tmp/tmppak212zv/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpiql0qhf6/images/target contains 8144 images
- /tmp/tmpiql0qhf6/images/random contains 5000 images
+ /tmp/tmppak212zv/images/target contains 8144 images
+ /tmp/tmppak212zv/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2138 - accuracy: 0.9251 - val_loss: 0.1147 - val_accuracy: 0.9562 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2188 - accuracy: 0.9257 - val_loss: 0.1318 - val_accuracy: 0.9585 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0960 - accuracy: 0.9631 - val_loss: 0.0898 - val_accuracy: 0.9671 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0977 - accuracy: 0.9653 - val_loss: 0.1354 - val_accuracy: 0.9569 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0588 - accuracy: 0.9798 - val_loss: 0.1360 - val_accuracy: 0.9528 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0697 - accuracy: 0.9748 - val_loss: 0.1547 - val_accuracy: 0.9543 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f6b69639fd0>
+ <keras.callbacks.History object at 0x7f1da663ca10>
@@ -857,7 +857,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 19.926 seconds)
+ **Total running time of the script:** ( 4 minutes 23.628 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 be1453c589..1f5748d416 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:30.155** total execution time for **how_to_work_with_microtvm** files:
+**06:39.732** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:19.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:23.628 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:07.086 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:09.733 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.864 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.336 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.512 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.093 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.768 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.942 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 1660fe8fc2..174588ca29 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.680** total execution time for **how_to_work_with_relay** files:
+**00:45.586** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.387 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.161 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.602 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.541 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.591 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index c192de79a8..d4e25e8d29 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f6bc0351440>
+ <function my_cuda_math_rule at 0x7f1da6dbe8c0>
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 44e3b6bd55..20580fcb2b 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.523** total execution time for **how_to_work_with_schedules** files:
+**00:07.376** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.064 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.689 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.247 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.570 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.614 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.597 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.121 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.025 | 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 3b448c4bb0..459a99a061 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -328,7 +328,7 @@ The importing needs to happen before the tensorized GEMV being executed.
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpqmz888xx/input0.cc'\nsource_filename = \"/tmp/tmpqmz888xx/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 float*, [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpo8jl13gc/input0.cc'\nsource_filename = \"/tmp/tmpo8jl13gc/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 float*, [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
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 25d16a489b..321e65ce67 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
=================
-**00:29.175** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:30.597** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.169 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.590 | 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 2756a84548..a8ad699d6a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 30.69s!
+ resnet18_v1 inference graph built in 31.73s!
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 c21f909da6..b3b3b82181 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 21.09s!
+ yolov3-tiny inference graph built in 21.78s!
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 d9669d45eb..49788a56b7 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
=================
-**01:35.112** total execution time for **topic_vta_tutorials_frontend** files:
+**01:37.233** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.673 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.654 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.439 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.579 | 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 b53df5cf7c..d1fbc66734 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
=================
-**00:03.115** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.332** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.666 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.829 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.448 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.503 | 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 fdcd43cb0d..d2952ed6d9 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
=================
-**00:00.786** total execution time for **topic_vta_tutorials** files:
+**00:00.872** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.457 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.373 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.415 | 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 cd82899457..008256f07e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,13 +207,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -322,7 +315,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 96.538 ms
+ Execution time of this operator: 94.021 ms
@@ -440,7 +433,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.420 seconds)
+ **Total running time of the script:** ( 1 minutes 30.223 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 3a04adbaf0..8fd0c9c632 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 4.18/4.18 result: MeasureResult(costs=(0.06415541500000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.287381649017334, timestamp=1674183947.8544009) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
- No: 2 GFLOPS: 2.70/4.18 result: MeasureResult(costs=(0.099422066,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8374905586242676, timestamp=1674183949.698981) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 3 GFLOPS: 8.37/8.37 result: MeasureResult(costs=(0.032066305,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7405209541320801, timestamp=1674183951.2165217) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
- No: 4 GFLOPS: 3.71/8.37 result: MeasureResult(costs=(0.07238791139999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3979723453521729, timestamp=1674183953.3796506) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
- No: 5 GFLOPS: 10.89/10.89 result: MeasureResult(costs=(0.0246521962,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6746640205383301, timestamp=1674183954.9166691) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 6 GFLOPS: 1.77/10.89 result: MeasureResult(costs=(0.1514064862,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.660912036895752, timestamp=1674183957.5901525) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
- No: 7 GFLOPS: 1.33/10.89 result: MeasureResult(costs=(0.20251314800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4556992053985596, timestamp=1674183961.0785851) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
- No: 8 GFLOPS: 9.18/10.89 result: MeasureResult(costs=(0.029232778999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6821742057800293, timestamp=1674183961.7943165) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
- No: 9 GFLOPS: 13.50/13.50 result: MeasureResult(costs=(0.019883790800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5237207412719727, timestamp=1674183962.4325068) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
- No: 10 GFLOPS: 1.78/13.50 result: MeasureResult(costs=(0.1507603704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.611154317855835, timestamp=1674183965.0960453) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 1 GFLOPS: 12.49/12.49 result: MeasureResult(costs=(0.0214892088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5937304496765137, timestamp=1674207344.7230031) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+ No: 2 GFLOPS: 12.93/12.93 result: MeasureResult(costs=(0.0207669992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5739247798919678, timestamp=1674207346.1109023) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 3 GFLOPS: 11.78/12.93 result: MeasureResult(costs=(0.022784174799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6616606712341309, timestamp=1674207347.535165) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+ No: 4 GFLOPS: 12.61/12.93 result: MeasureResult(costs=(0.0212889474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6334853172302246, timestamp=1674207348.135068) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+ No: 5 GFLOPS: 4.14/12.93 result: MeasureResult(costs=(0.0648186526,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2923367023468018, timestamp=1674207349.6181529) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
+ No: 6 GFLOPS: 2.24/12.93 result: MeasureResult(costs=(0.1199507176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1554558277130127, timestamp=1674207351.7927608) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+ No: 7 GFLOPS: 12.46/12.93 result: MeasureResult(costs=(0.0215484072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5837976932525635, timestamp=1674207353.1999807) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 8 GFLOPS: 12.09/12.93 result: MeasureResult(costs=(0.0221962052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6870126724243164, timestamp=1674207353.8154304) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
+ No: 9 GFLOPS: 3.85/12.93 result: MeasureResult(costs=(0.06976133640000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3460557460784912, timestamp=1674207355.2814348) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 10 GFLOPS: 12.78/12.93 result: MeasureResult(costs=(0.021006779,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5583662986755371, timestamp=1674207355.8758848) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 3d52bf14a5..004fb7360d 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 477.48544495999687, 'median': 477.1313110499932, 'std': 1.163654270518335}
+ {'mean': 514.3162037599905, 'median': 514.0795248999893, 'std': 2.380002958562946}
@@ -545,29 +545,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 15.30/ 18.71 GFLOPS | Progress: (4/20) | 7.85 s
[Task 1/25] Current/Best: 12.14/ 18.71 GFLOPS | Progress: (8/20) | 11.20 s
[Task 1/25] Current/Best: 6.83/ 23.82 GFLOPS | Progress: (12/20) | 14.40 s
[Task 1/25] Current/Best: 16.58/ 23.82 GFLOPS | Progress: (16/20) | 17.92 s
[Task 1/25] Current/Best: 9.74/ 23.82 GFLOPS | Progress: (20/20) | 20.11 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.60/ 14.27 GFLOPS | Progress: (4/20) | 3.90 s
[Task 2/25] Current/Best: 6.61/ 19.78 GFLOPS | Progress: (8/20) | 5.90 s
[Task 2/25] Current/Best: 11.01/ 19.78 GFLOPS | Progress: (12/20) | 7.84 s
[Task 2/25] Current/Best: 6.19/ 19.78 GFLOPS | Progress: (16/20) | 10.69 s
[Task 2/25] Current/Best: 14.99/ 19.92 GFLOPS | Progress: (20/20) | 11.99 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.85/ 18.87 GFLOPS | Progress: (4/20) | 4.02 s
[Task 3/25] Current/Best: 18.06/ 18.87 GFLOPS | Progress: (8/20) | 6.62 s
[Task 3/25] Current/Best: 11.32/ 18.87 GFLOPS | Progress: (12/20) | 8.83 s
[Task 3/25] Current/Best: 7.72/ 21.24 GFLOPS | Progress: (16/20) | 11.17 s
[Task 3/25] Current/Best: 9.67/ 21.24 GFLOPS | Progress: (20/20) | 14.17 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.41/ 16.65 GFLOPS | Progress: (4/20) | 6.52 s
[Task 4/25] Current/Best: 14.24/ 16.65 GFLOPS | Progress: (8/20) | 8.66 s
[Task 4/25] Current/Best: 18.32/ 18.32 GFLOPS | Progress: (12/20) | 10.77 s
[Task 4/25] Current/Best: 11.23/ 18.32 GFLOPS | Progress: (16/20) | 13.68 s
[Task 4/25] Current/Best: 14.60/ 18.47 GFLOPS | Progress: (20/20) | 15.37 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 6.07/ 16.00 GFLOPS | Progress: (4/20) | 3.69 s
[Task 5/25] Current/Best: 16.29/ 23.13 GFLOPS | Progress: (8/20) | 5.62 s
[Task 5/25] Current/Best: 14.06/ 23.13 GFLOPS | Progress: (12/20) | 7.58 s
[Task 5/25] Current/Best: 12.15/ 23.13 GFLOPS | Progress: (16/20) | 9.75 s
[Task 5/25] Current/Best: 5.66/ 23.13 GFLOPS | Progress: (20/20) | 11.70 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.17/ 23.11 GFLOPS | Progress: (4/20) | 4.11 s
[Task 6/25] Current/Best: 13.31/ 23.11 GFLOPS | Progress: (8/20) | 6.51 s
[Task 6/25] Current/Best: 15.13/ 23.11 GFLOPS | Progress: (12/20) | 9.36 s
[Task 6/25] Current/Best: 4.13/ 23.11 GFLOPS | Progress: (16/20) | 13.20 s
[Task 6/25] Current/Best: 2.81/ 23.11 GFLOPS | Progress: (20/20) | 17.23 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.43/ 18.22 GFLOPS | Progress: (4/20) | 4.48 s
[Task 7/25] Current/Best: 13.84/ 18.22 GFLOPS | Progress: (8/20) | 6.79 s
[Task 7/25] Current/Best: 12.23/ 20.78 GFLOPS | Progress: (12/20) | 8.84 s
[Task 7/25] Current/Best: 23.29/ 23.29 GFLOPS | Progress: (16/20) | 10.72 s
[Task 7/25] Current/Best: 9.72/ 23.29 GFLOPS | Progress: (20/20) | 12.77 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 3.62/ 11.80 GFLOPS | Progress: (4/20) | 11.38 s
[Task 8/25] Current/Best: 7.33/ 12.44 GFLOPS | Progress: (8/20) | 16.47 s
[Task 8/25] Current/Best: 5.14/ 13.67 GFLOPS | Progress: (12/20) | 21.18 s
[Task 8/25] Current/Best: 10.57/ 13.67 GFLOPS | Progress: (16/20) | 26.95 s
[Task 8/25] Current/Best: 2.81/ 18.58 GFLOPS | Progress: (20/20) | 34.54 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.01/ 13.89 GFLOPS | Progress: (4/20) | 5.91 s
[Task 9/25] Current/Best: 12.57/ 22.75 GFLOPS | Progress: (8/20) | 16.29 s
[Task 9/25] Current/Best: 16.27/ 22.75 GFLOPS | Progress: (12/20) | 27.37 s
[Task 9/25] Current/Best: 16.64/ 22.75 GFLOPS | Progress: (16/20) | 30.03 s
[Task 9/25] Current/Best: 13.22/ 22.75 GFLOPS | Progress: (20/20) | 32.51 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 7.16/ 12.91 GFLOPS | Progress: (4/20) | 3.86 s
[Task 10/25] Current/Best: 9.49/ 13.08 GFLOPS | Progress: (8/20) | 6.51 s
[Task 10/25] Current/Best: 9.40/ 22.06 GFLOPS | Progress: (12/20) | 8.95 s
[Task 10/25] Current/Best: 14.26/ 22.06 GFLOPS | Progress: (16/20) | 11.30 s
[Task 10/25] Current/Best: 11.07/ 22.57 GFLOPS | Progress: (20/20
) | 13.49 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 17.02/ 17.02 GFLOPS | Progress: (4/20) | 4.13 s
[Task 11/25] Current/Best: 10.07/ 22.61 GFLOPS | Progress: (8/20) | 6.58 s
[Task 11/25] Current/Best: 16.71/ 22.61 GFLOPS | Progress: (12/20) | 10.58 s
[Task 11/25] Current/Best: 19.73/ 22.61 GFLOPS | Progress: (16/20) | 12.70 s
[Task 11/25] Current/Best: 19.42/ 22.61 GFLOPS | Progress: (20/20) | 15.44 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 16.42/ 17.67 GFLOPS | Progress: (4/20) | 3.98 s
[Task 12/25] Current/Best: 13.24/ 18.53 GFLOPS | Progress: (8/20) | 7.47 s
[Task 12/25] Current/Best: 11.77/ 18.53 GFLOPS | Progress: (12/20) | 10.42 s
[Task 12/25] Current/Best: 4.57/ 18.53 GFLOPS | Progress: (16/20) | 12.81 s
[Task 12/25] Current/Best: 5.08/ 20.63 GFLOPS | Progress: (20/20) | 15.29 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.86/ 20.33 GFLOPS | Progress: (4/20) | 4.75 s
[Task 13/25] Current/Best: 21.82/ 21.82 GFLOPS | Progress: (8/20) | 7.72 s
[Task 13/25] Current/Best: 16.97/ 21.82 GFLOPS | Progress: (12/20) | 11.23 s
[Task 13/25] Current/Best: 12.25/ 23.21 GFLOPS | Progress: (16/20) | 13.92 s
[Task 13/25] Current/Best: 12.19/ 23.21 GFLOPS | Progress: (20/20) | 16.11 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.29/ 17.68 GFLOPS | Progress: (4/20) | 3.95 s
[Task 14/25] Current/Best: 8.59/ 17.68 GFLOPS | Progress: (8/20) | 6.34 s
[Task 14/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (12/20) | 9.78 s Done.
-
[Task 14/25] Current/Best: 10.30/ 22.75 GFLOPS | Progress: (16/20) | 12.37 s
[Task 14/25] Current/Best: 4.55/ 22.75 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 8.87/ 12.81 GFLOPS | Progress: (4/20) | 4.85 s
[Task 15/25] Current/Best: 15.48/ 18.88 GFLOPS | Progress: (8/20) | 6.43 s
[Task 15/25] Current/Best: 13.28/ 18.88 GFLOPS | Progress: (12/20) | 9.06 s
[Task 15/25] Current/Best: 15.18/ 20.23 GFLOPS | Progress: (16/20) | 10.78 s
[Task 15/25] Current/Best: 10.95/ 20.23 GFLOPS | Progress: (20/20) | 13.09 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 7.67/ 19.12 GFLOPS | Progress: (4/20) | 4.20 s
[Task 16/25] Current/Best: 17.02/ 19.12 GFLOPS | Progress: (8/20) | 6.60 s
[Task 16/25] Current/Best: 14.04/ 19.12 GFLOPS | Progress: (12/20) | 10.29 s
[Task 16/25] Current/Best: 18.09/ 19.12 GFLOPS | Progress: (16/20) | 11.79 s
[Task 16/25] Current/Best: 16.36/ 19.12 GFLOPS | Progress: (20/20)
| 15.41 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 6.22/ 20.51 GFLOPS | Progress: (4/20) | 4.28 s
[Task 17/25] Current/Best: 12.27/ 20.51 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 15.02/ 20.51 GFLOPS | Progress: (12/20) | 9.84 s
[Task 17/25] Current/Best: 16.16/ 20.51 GFLOPS | Progress: (16/20) | 12.51 s
[Task 17/25] Current/Best: 16.17/ 20.51 GFLOPS | Progress: (20/20) | 15.24 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.44/ 17.44 GFLOPS | Progress: (4/20) | 6.42 s
[Task 18/25] Current/Best: 12.29/ 19.96 GFLOPS | Progress: (8/20) | 9.49 s
[Task 18/25] Current/Best: 20.27/ 20.27 GFLOPS | Progress: (12/20) | 11.30 s
[Task 18/25] Current/Best: 11.19/ 21.02 GFLOPS | Progress: (16/20) | 17.84 s
[Task 18/25] Current/Best: 7.88/ 21.02 GFLOPS | Progress: (20/20) | 21.90 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (4/20) | 5.47 s
[Task 19/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (8/20) | 9.26 s
[Task 19/25] Current/Best: 18.07/ 21.10 GFLOPS | Progress: (12/20) | 12.50 s
[Task 19/25] Current/Best: 6.11/ 21.10 GFLOPS | Progress: (16/20) | 16.33 s
[Task 19/25] Current/Best: 20.04/ 21.10 GFLOPS | Progress: (20/20) | 19.24 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 18.49/ 20.04 GFLOPS | Progress: (4/20) | 4.58 s
[Task 20/25] Current/Best: 16.62/ 20.04 GFLOPS | Progress: (8/20) | 7.52 s
[Task 20/25] Current/Best: 6.20/ 20.04 GFLOPS | Progress: (12/20) | 9.30 s
[Task 20/25] Current/Best: 8.57/ 20.04 GFLOPS | Progress: (16/20) | 11.33 s Done.
-
[Task 20/25] Current/Best: 11.29/ 20.06 GFLOPS | Progress: (20/20) | 14.35 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 9.45/ 18.85 GFLOPS | Progress: (4/20) | 3.79 s
[Task 21/25] Current/Best: 22.47/ 22.47 GFLOPS | Progress: (8/20) | 5.72 s
[Task 21/25] Current/Best: 10.95/ 22.47 GFLOPS | Progress: (12/20) | 8.91 s
[Task 21/25] Current/Best: 6.93/ 22.47 GFLOPS | Progress: (16/20) | 11.23 s
[Task 21/25] Current/Best: 17.10/ 22.47 GFLOPS | Progress: (20/20) | 12.82 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 15.99 GFLOPS | Progress: (4/20) | 5.03 s
[Task 22/25] Current/Best: 12.40/ 15.99 GFLOPS | Progress: (8/20) | 7.28 s
[Task 22/25] Current/Best: 16.05/ 16.05 GFLOPS | Progress: (12/20) | 9.60 s
[Task 22/25] Current/Best: 16.57/ 18.99 GFLOPS | Progress: (16/20)
| 11.17 s
[Task 22/25] Current/Best: 11.23/ 18.99 GFLOPS | Progress: (20/20) | 13.02 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 8.38/ 18.13 GFLOPS | Progress: (4/20) | 5.09 s
[Task 23/25] Current/Best: 12.32/ 18.98 GFLOPS | Progress: (8/20) | 8.03 s
[Task 23/25] Current/Best: 11.99/ 18.98 GFLOPS | Progress: (12/20) | 10.97 s
[Task 23/25] Current/Best: 22.52/ 22.52 GFLOPS | Progress: (16/20) | 13.97 s
[Task 23/25] Current/Best: 14.05/ 22.52 GFLOPS | Progress: (20/20) | 16.69 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.61/ 9.73 GFLOPS | Progress: (4/20) | 12.76 s
[Task 24/25] Current/Best: 0.54/ 9.73 GFLOPS | Progress: (8/20) | 20.64 s
[Task 24/25] Current/Best: 3.01/ 10.69 GFLOPS | Progress: (12/20) | 22.00 s
[Task 24/25] Current/Best: 6.27/ 10.69 GFLOPS | Progress: (16/20) | 32.92 s Done.
-
[Task 24/25] Current/Best: 3.29/ 10.69 GFLOPS | Progress: (20/20) | 44.62 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.42/ 6.08 GFLOPS | Progress: (4/20) | 13.52 s
[Task 25/25] Current/Best: 6.15/ 9.80 GFLOPS | Progress: (8/20) | 24.48 s
[Task 25/25] Current/Best: 7.84/ 9.80 GFLOPS | Progress: (12/20) | 26.91 s
[Task 25/25] Current/Best: 9.10/ 9.80 GFLOPS | Progress: (16/20) | 37.87 s
[Task 25/25] Current/Best: 7.96/ 9.80 GFLOPS | Progress: (20/20) | 40.04 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 19.29/ 19.29 GFLOPS | Progress: (4/20) | 7.56 s
[Task 1/25] Current/Best: 18.49/ 19.29 GFLOPS | Progress: (8/20) | 10.65 s
[Task 1/25] Current/Best: 14.25/ 19.29 GFLOPS | Progress: (12/20) | 13.05 s
[Task 1/25] Current/Best: 9.48/ 19.29 GFLOPS | Progress: (16/20) | 16.38 s
[Task 1/25] Current/Best: 10.72/ 22.48 GFLOPS | Progress: (20/20) | 18.81 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 5.67/ 14.05 GFLOPS | Progress: (4/20) | 4.11 s
[Task 2/25] Current/Best: 5.59/ 15.44 GFLOPS | Progress: (8/20) | 6.17 s
[Task 2/25] Current/Best: 13.89/ 17.40 GFLOPS | Progress: (12/20) | 8.09 s
[Task 2/25] Current/Best: 11.54/ 17.40 GFLOPS | Progress: (16/20) | 10.20 s
[Task 2/25] Current/Best: 18.11/ 20.80 GFLOPS | Progress: (20/20) | 11.75 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.87/ 17.53 GFLOPS | Progress: (4/20) | 5.43 s
[Task 3/25] Current/Best: 7.09/ 19.21 GFLOPS | Progress: (8/20) | 7.92 s
[Task 3/25] Current/Best: 17.15/ 19.21 GFLOPS | Progress: (12/20) | 10.10 s
[Task 3/25] Current/Best: 14.24/ 19.64 GFLOPS | Progress: (16/20) | 12.52 s
[Task 3/25] Current/Best: 6.61/ 22.40 GFLOPS | Progress: (20/20) | 15.34 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 6.13/ 15.63 GFLOPS | Progress: (4/20) | 4.03 s
[Task 4/25] Current/Best: 13.02/ 16.84 GFLOPS | Progress: (8/20) | 9.08 s
[Task 4/25] Current/Best: 8.04/ 17.08 GFLOPS | Progress: (12/20) | 11.96 s
[Task 4/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (16/20) | 13.89 s
[Task 4/25] Current/Best: 2.08/ 21.29 GFLOPS | Progress: (20/20) | 17.52 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.22/ 16.40 GFLOPS | Progress: (4/20) | 4.36 s
[Task 5/25] Current/Best: 3.72/ 16.40 GFLOPS | Progress: (8/20) | 6.55 s
[Task 5/25] Current/Best: 13.44/ 17.12 GFLOPS | Progress: (12/20) | 9.29 s
[Task 5/25] Current/Best: 11.64/ 20.07 GFLOPS | Progress: (16/20) | 11.22 s
[Task 5/25] Current/Best: 12.75/ 20.07 GFLOPS | Progress: (20/20) | 13.58 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.76/ 19.40 GFLOPS | Progress: (4/20) | 4.15 s
[Task 6/25] Current/Best: 4.16/ 19.40 GFLOPS | Progress: (8/20) | 7.24 s
[Task 6/25] Current/Best: 18.78/ 19.40 GFLOPS | Progress: (12/20) | 10.46 s
[Task 6/25] Current/Best: 6.21/ 19.40 GFLOPS | Progress: (16/20) | 13.47 s
[Task 6/25] Current/Best: 6.61/ 19.40 GFLOPS | Progress: (20/20) | 16.04 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.67/ 20.90 GFLOPS | Progress: (4/20) | 5.32 s
[Task 7/25] Current/Best: 12.08/ 20.90 GFLOPS | Progress: (8/20) | 8.23 s
[Task 7/25] Current/Best: 9.08/ 20.90 GFLOPS | Progress: (12/20) | 10.40 s
[Task 7/25] Current/Best: 17.61/ 20.90 GFLOPS | Progress: (16/20) | 12.38 s
[Task 7/25] Current/Best: 18.28/ 20.90 GFLOPS | Progress: (20/20) | 15.59 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.21/ 11.12 GFLOPS | Progress: (4/20) | 4.54 s
[Task 8/25] Current/Best: 4.00/ 16.99 GFLOPS | Progress: (8/20) | 7.27 s
[Task 8/25] Current/Best: 8.20/ 16.99 GFLOPS | Progress: (12/20) | 11.21 s
[Task 8/25] Current/Best: 14.13/ 16.99 GFLOPS | Progress: (16/20) | 14.43 s
[Task 8/25] Current/Best: 17.81/ 17.81 GFLOPS | Progress: (20/20) | 16.88 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.47/ 16.30 GFLOPS | Progress: (4/20) | 4.11 s
[Task 9/25] Current/Best: 13.72/ 16.30 GFLOPS | Progress: (8/20) | 9.85 s
[Task 9/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (12/20) | 12.90 s
[Task 9/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (16/20) | 14.82 s
[Task 9/25] Current/Best: 17.76/ 19.68 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.62/ 22.30 GFLOPS | Progress: (4/20) | 3.63 s
[Task 10/25] Current/Best: 3.13/ 22.66 GFLOPS | Progress: (8/20) | 5.73 s
[Task 10/25] Current/Best: 14.39/ 22.66 GFLOPS | Progress: (12/20) | 8.20 s
[Task 10/25] Current/Best: 4.73/ 22.66 GFLOPS | Progress: (16/20) | 11.34 s
[Task 10/25] Current/Best: 14.63/ 22.66 GFLOPS | Progress: (20/20) | 14.94 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 14.53/ 14.53 GFLOPS | Progress: (4/20) | 4.63 s
[Task 11/25] Current/Best: 5.62/ 16.32 GFLOPS | Progress: (8/20) | 7.00 s
[Task 11/25] Current/Best: 12.30/ 18.08 GFLOPS | Progress: (12/20) | 9.29 s
[Task 11/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (16/20) | 11.76 s
[Task 11/25] Current/Best: 9.78/ 18.53 GFLOPS | Progress: (20/20) | 15.13 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.51/ 16.09 GFLOPS | Progress: (4/20) | 4.57 s
[Task 12/25] Current/Best: 1.61/ 16.09 GFLOPS | Progress: (8/20) | 8.20 s
[Task 12/25] Current/Best: 10.58/ 16.09 GFLOPS | Progress: (12/20) | 16.33 s
[Task 12/25] Current/Best: 9.71/ 16.71 GFLOPS | Progress: (16/20) | 19.53 s
[Task 12/25] Current/Best: 12.98/ 16.71 GFLOPS | Progress: (20/20) | 22.54 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.67/ 18.36 GFLOPS | Progress: (4/20) | 4.59 s
[Task 13/25] Current/Best: 9.87/ 18.36 GFLOPS | Progress: (8/20) | 8.99 s
[Task 13/25] Current/Best: 11.88/ 18.36 GFLOPS | Progress: (12/20) | 13.31 s
[Task 13/25] Current/Best: 9.34/ 20.57 GFLOPS | Progress: (16/20) | 16.63 s
[Task 13/25] Current/Best: 5.62/ 21.53 GFLOPS | Progress: (20/20) | 19.94 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.30/ 15.72 GFLOPS | Progress: (4/20) | 7.50 s
[Task 14/25] Current/Best: 7.57/ 15.72 GFLOPS | Progress: (8/20) | 10.25 s
[Task 14/25] Current/Best: 6.24/ 18.13 GFLOPS | Progress: (12/20) | 13.56 s
[Task 14/25] Current/Best: 3.05/ 18.13 GFLOPS | Progress: (16/20) | 17.87 s
[Task 14/25] Current/Best: 6.14/ 18.13 GFLOPS | Progress: (20/20) | 21.00 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.70/ 18.81 GFLOPS | Progress: (4/20) | 6.52 s Done.
+
[Task 15/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (8/20) | 7.97 s
[Task 15/25] Current/Best: 23.32/ 23.32 GFLOPS | Progress: (12/20) | 9.79 s
[Task 15/25] Current/Best: 19.94/ 23.32 GFLOPS | Progress: (16/20) | 11.95 s
[Task 15/25] Current/Best: 11.46/ 23.32 GFLOPS | Progress: (20/20) | 15.58 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 14.44/ 19.10 GFLOPS | Progress: (4/20) | 3.73 s
[Task 16/25] Current/Best: 3.04/ 19.10 GFLOPS | Progress: (8/20) | 7.31 s
[Task 16/25] Current/Best: 7.11/ 19.10 GFLOPS | Progress: (12/20) | 9.20 s
[Task 16/25] Current/Best: 12.23/ 19.10 GFLOPS | Progress: (16/20) | 12.06 s
[Task 16/25] Current/Best: 13.41/ 19.10 GFLOPS | Progress: (20/20) | 14.06 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 4.21 s
[Task 17/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (8/20) | 8.21 s
[Task 17/25] Current/Best: 11.50/ 20.03 GFLOPS | Progress: (12/20) | 10.78 s
[Task 17/25] Current/Best: 16.63/ 20.03 GFLOPS | Progress: (16/20) | 14.08 s
[Task 17/25] Current/Best: 8.55/ 21.18 GFLOPS | Progress: (20/20) | 16.68 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.45/ 17.53 GFLOPS | Progress: (4/20) | 3.96 s
[Task 18/25] Current/Best: 15.93/ 17.53 GFLOPS | Progress: (8/20) | 7.26 s
[Task 18/25] Current/Best: 14.98/ 17.53 GFLOPS | Progress: (12/20) | 11.47 s
[Task 18/25] Current/Best: 7.74/ 19.04 GFLOPS | Progress: (16/20) | 13.75 s
[Task 18/25] Current/Best: 12.20/ 21.34 GFLOPS | Progress: (20/20) | 15.90 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 12.75/ 17.58 GFLOPS | Progress: (4/20) | 4.33 s
[Task 19/25] Current/Best: 17.11/ 17.58 GFLOPS | Progress: (8/20) | 9.34 s
[Task 19/25] Current/Best: 17.45/ 17.58 GFLOPS | Progress: (12/20) | 13.13 s
[Task 19/25] Current/Best: 10.53/ 18.06 GFLOPS | Progress: (16/20) | 15.91 s
[Task 19/25] Current/Best: 9.45/ 19.98 GFLOPS | Progress: (20/20) | 20.66 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.14/ 11.14 GFLOPS | Progress: (4/20) | 4.74 s
[Task 20/25] Current/Best: 11.78/ 18.45 GFLOPS | Progress: (8/20) | 7.65 s
[Task 20/25] Current/Best: 8.73/ 19.92 GFLOPS | Progress: (12/20) | 11.77 s
[Task 20/25] Current/Best: 2.67/ 19.92 GFLOPS | Progress: (16/20) | 14.54 s
[Task 20/25] Current/Best: 18.92/ 19.92 GFLOPS | Progress: (20/20) | 16.80 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.52/ 18.95 GFLOPS | Progress: (4/20) | 4.74 s
[Task 21/25] Current/Best: 7.01/ 18.95 GFLOPS | Progress: (8/20) | 7.07 s
[Task 21/25] Current/Best: 15.41/ 21.33 GFLOPS | Progress: (12/20) | 8.70 s
[Task 21/25] Current/Best: 19.22/ 21.33 GFLOPS | Progress: (16/20) | 10.31 s
[Task 21/25] Current/Best: 11.81/ 21.33 GFLOPS | Progress: (20/20)
| 13.55 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 5.37/ 18.80 GFLOPS | Progress: (4/20) | 5.27 s
[Task 22/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (8/20) | 7.89 s
[Task 22/25] Current/Best: 8.21/ 20.75 GFLOPS | Progress: (12/20) | 9.64 s
[Task 22/25] Current/Best: 10.06/ 20.75 GFLOPS | Progress: (16/20) | 14.84 s
[Task 22/25] Current/Best: 10.64/ 20.75 GFLOPS | Progress: (20/20) | 16.46 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.32/ 19.53 GFLOPS | Progress: (4/20) | 4.51 s
[Task 23/25] Current/Best: 22.72/ 23.79 GFLOPS | Progress: (8/20) | 7.18 s
[Task 23/25] Current/Best: 20.43/ 23.79 GFLOPS | Progress: (12/20) | 10.07 s
[Task 23/25] Current/Best: 3.68/ 23.79 GFLOPS | Progress: (16/20) | 13.37 s
[Task 23/25] Current/Best: 9.54/ 23.79 GFLOPS | Progress: (20/20) | 17.44 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 2.92/ 3.13 GFLOPS | Progress: (4/20) | 12.79 s Done.
+ Done.
+ Done.
+
[Task 24/25] Current/Best: 6.05/ 6.05 GFLOPS | Progress: (8/20) | 23.73 s
[Task 24/25] Current/Best: 3.00/ 6.05 GFLOPS | Progress: (12/20) | 34.39 s
[Task 24/25] Current/Best: 8.54/ 8.89 GFLOPS | Progress: (16/20) | 45.04 s
[Task 24/25] Current/Best: 3.18/ 10.18 GFLOPS | Progress: (20/20) | 50.77 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 8.16/ 8.16 GFLOPS | Progress: (4/20) | 12.82 s
[Task 25/25] Current/Best: 5.20/ 8.16 GFLOPS | Progress: (8/20) | 23.77 s
[Task 25/25] Current/Best: 3.00/ 8.16 GFLOPS | Progress: (12/20) | 25.84 s
[Task 25/25] Current/Best: 4.18/ 9.20 GFLOPS | Progress: (16/20) | 29.30 s
[Task 25/25] Current/Best: 5.66/ 9.20 GFLOPS | Progress: (20/20) | 40.25 s
@@ -663,8 +664,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621102
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -721,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 413.88311280999915, 'median': 413.60596074999876, 'std': 1.6160087440403037}
- unoptimized: {'mean': 477.48544495999687, 'median': 477.1313110499932, 'std': 1.163654270518335}
+ optimized: {'mean': 416.60222960998, 'median': 416.48454939995645, 'std': 1.852629075858513}
+ unoptimized: {'mean': 514.3162037599905, 'median': 514.0795248999893, 'std': 2.380002958562946}
@@ -745,7 +746,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 26.752 seconds)
+ **Total running time of the script:** ( 11 minutes 38.584 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 535d194b18..249a986fac 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.308e-07 secs/op
+ 1.337e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index e9d91e8c1d..387c0b0edb 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -268,7 +268,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x22bcd1f0)), stage(b, placeholder(b, 0x21d8d400)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0x19f394e0)), stage(b, placeholder(b, 0xd5ca1d0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index dbb9de6f38..d0cde70a5c 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:55.935** total execution time for **tutorial** files:
+**15:04.335** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:26.752 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:38.584 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:30.420 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:30.223 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.900 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.089 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.825 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.627 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.680 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:16.188 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.379 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.827 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.819 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.612 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.159 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.183 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 7235d27187..310c4d3a1f 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,7 +285,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000008
naive: 0.000007
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000011
+ parallel: 0.000012
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000046
@I.ir_module
class Module:
@T.prim_func
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.256909998432093e-06 1.0
- naive 6.6563999999999995e-06 0.9172499040828896
- parallel 1.126e-05 1.551624589864392
- vector 2.45527e-05 3.3833546241175356
+ numpy 7.6238400106376505e-06 1.0
+ naive 6.6943e-06 0.8780745648727346
+ parallel 1.17693e-05 1.5437496043434975
+ vector 4.62778e-05 6.070143121501492
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017994
+ Numpy running time: 0.018552
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.258496
+ none: 3.458278
@@ -1077,7 +1077,7 @@ schedule.
.. code-block:: none
- blocking: 0.297530
+ blocking: 0.313893
@@ -1158,7 +1158,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.330118
+ vectorization: 0.349831
@I.ir_module
class Module:
@T.prim_func
@@ -1221,7 +1221,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119767
+ loop permutation: 0.123109
@I.ir_module
class Module:
@T.prim_func
@@ -1309,7 +1309,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109910
+ array packing: 0.109124
@I.ir_module
class Module:
@T.prim_func
@@ -1389,7 +1389,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110722
+ block caching: 0.111100
@I.ir_module
class Module:
@T.prim_func
@@ -1460,7 +1460,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146423
+ parallelization: 0.148550
@I.ir_module
class Module:
@T.prim_func
@@ -1527,13 +1527,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2584962005 1.0
- blocking 0.297529924 0.09130896760117305
- vectorization 0.3301182801 0.10131000921509282
- loop permutation 0.11976749480000001 0.03675545019252202
- array packing 0.1099097601 0.03373020968480334
- block caching 0.11072204810000001 0.033979492774308055
- parallelization 0.1464230078 0.04493576140353704
+ none 3.4582784937 1.0
+ blocking 0.3138928144 0.09076562658901631
+ vectorization 0.3498312842 0.10115763806682808
+ loop permutation 0.1231090829 0.03559837159565655
+ array packing 0.1091240935 0.03155445511366221
+ block caching 0.1110999699 0.03212580192786456
+ parallelization 0.1485501092 0.042954929590146095
@@ -1573,6 +1573,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.089 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 9260decc08..af9b7cbe11 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-6c2d485a011fbfbd426353c6fc1254f3385d826e
+5e36ae331cab8a310b7f5202fc5830787b5bd6d4
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index bf01b558c0..13737cefc0 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.727 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.684 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index bb9ebcf6a8..f88e264bf1 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 938ms/step
+1/1 [==============================] - 1s 929ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index b6b7aac5e7..30d733e79a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip281edc03-6311-457c-b054-e2f5809f278a 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.zip9024e707-0efc-4cb7-aea5-7978f97ab1ee 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 4b89f675d4..50765696cd 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,13 +449,12 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 51.0MB/s]
- 33%|###3 | 13.9M/41.5M [00:00<00:00, 65.7MB/s]
- 49%|####8 | 20.3M/41.5M [00:00<00:00, 51.4MB/s]
- 62%|######1 | 25.6M/41.5M [00:00<00:00, 50.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 52.8MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 45.2MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 49.6MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 48.0MB/s]
+ 35%|###4 | 14.5M/41.5M [00:00<00:00, 57.1MB/s]
+ 51%|#####1 | 21.4M/41.5M [00:00<00:00, 62.9MB/s]
+ 67%|######6 | 27.6M/41.5M [00:00<00:00, 51.0MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 56.1MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 59.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index fd3b06245a..536986fb5d 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,10 +432,12 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 23%|##2 | 10.1M/44.7M [00:00<00:00, 74.9MB/s]
- 50%|##### | 22.4M/44.7M [00:00<00:00, 102MB/s]
- 73%|#######3 | 32.6M/44.7M [00:00<00:00, 87.4MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 98.9MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 72.9MB/s]
+ 36%|###5 | 16.0M/44.7M [00:00<00:00, 63.2MB/s]
+ 54%|#####3 | 24.0M/44.7M [00:00<00:00, 67.0MB/s]
+ 72%|#######1 | 32.0M/44.7M [00:00<00:00, 58.2MB/s]
+ 90%|########9 | 40.0M/44.7M [00:00<00:00, 65.3MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 69.0MB/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 b2a35a7cc1..1c056fbda4 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ 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 18.160 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.050 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 4f30f972c5..8b583f517f 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:07.945</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:14.168</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:18.160</p></td>
+<td><p>01:19.050</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>01:13.727</p></td>
+<td><p>01:14.684</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>00:50.305</p></td>
+<td><p>00:51.843</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>00:34.517</p></td>
+<td><p>00:34.853</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.818</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:30.362</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:29.515</p></td>
+<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>00:29.853</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>00:26.227</p></td>
+<td><p>00:26.635</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>00:23.431</p></td>
+<td><p>00:24.524</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>00:19.695</p></td>
+<td><p>00:19.747</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>00:02.550</p></td>
+<td><p>00:02.617</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index cef60e39a3..9bcf2ffe93 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2758.3525 2758.4177 2760.3811 2755.1281 1.6989
+ 2544.5655 2544.3349 2547.9377 2542.5576 1.3979
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 01992373b2..b9a5484537 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6184 15.5163 16.1542 15.4111 0.2631
+ 16.3751 16.3681 16.4464 16.3137 0.0501
</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 41d1422989..5120777629 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,24 +454,28 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 6%|5 | 10.1M/170M [00:00<00:01, 86.0MB/s]
- 12%|#2 | 21.2M/170M [00:00<00:01, 97.2MB/s]
- 18%|#7 | 30.5M/170M [00:00<00:01, 97.6MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:01, 80.4MB/s]
- 32%|###1 | 53.9M/170M [00:00<00:01, 101MB/s]
- 38%|###7 | 64.1M/170M [00:00<00:01, 83.8MB/s]
- 43%|####2 | 72.8M/170M [00:00<00:01, 81.9MB/s]
- 48%|####7 | 81.0M/170M [00:01<00:01, 75.3MB/s]
- 53%|#####3 | 90.6M/170M [00:01<00:01, 81.0MB/s]
- 59%|#####8 | 99.7M/170M [00:01<00:00, 84.7MB/s]
- 64%|######3 | 108M/170M [00:01<00:00, 76.1MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 82.0MB/s]
- 75%|#######5 | 128M/170M [00:01<00:00, 74.7MB/s]
- 80%|######## | 136M/170M [00:01<00:00, 67.7MB/s]
- 86%|########5 | 146M/170M [00:01<00:00, 75.6MB/s]
- 90%|######### | 153M/170M [00:02<00:00, 64.2MB/s]
- 95%|#########5| 162M/170M [00:02<00:00, 68.0MB/s]
-100%|##########| 170M/170M [00:02<00:00, 78.6MB/s]
+ 5%|4 | 8.02M/170M [00:00<00:02, 84.1MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 77.5MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 74.1MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 70.2MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:01, 72.2MB/s]
+ 30%|##9 | 50.2M/170M [00:00<00:01, 83.0MB/s]
+ 35%|###5 | 59.5M/170M [00:00<00:01, 87.5MB/s]
+ 40%|#### | 68.7M/170M [00:00<00:01, 90.0MB/s]
+ 46%|####5 | 77.3M/170M [00:00<00:01, 87.6MB/s]
+ 51%|##### | 85.8M/170M [00:01<00:01, 82.2MB/s]
+ 55%|#####5 | 93.7M/170M [00:01<00:01, 75.6MB/s]
+ 61%|###### | 103M/170M [00:01<00:00, 82.0MB/s]
+ 65%|######5 | 111M/170M [00:01<00:00, 77.9MB/s]
+ 70%|######9 | 119M/170M [00:01<00:00, 75.3MB/s]
+ 74%|#######4 | 126M/170M [00:01<00:00, 67.7MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 68.7MB/s]
+ 82%|########2 | 140M/170M [00:01<00:00, 67.1MB/s]
+ 86%|########6 | 146M/170M [00:02<00:00, 67.0MB/s]
+ 90%|########9 | 153M/170M [00:02<00:00, 61.1MB/s]
+ 93%|#########3| 158M/170M [00:02<00:00, 50.3MB/s]
+ 96%|#########6| 164M/170M [00:02<00:00, 49.0MB/s]
+100%|##########| 170M/170M [00:02<00:00, 70.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -569,7 +573,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 21.632 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 26.947 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 45578ed3cd..1f4b31639f 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,8 +495,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 76.8MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 103MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 57.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 64.9MB/s]
</pre></div>
</div>
</div>
@@ -587,7 +587,7 @@ 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)
- 90.1720 90.1005 91.6585 89.8012 0.3037
+ 90.2445 90.1774 91.3289 90.0707 0.2111
</pre></div>
</div>
<div class="admonition note">
@@ -626,7 +626,7 @@ 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 10.916 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.274 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 6e678ab148..234520147d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ 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)
- 118.3536 118.3627 119.9356 117.1745 0.4004
+ 120.1613 120.1603 125.3032 118.4185 0.7664
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 25.221 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.873 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 9a88f9abac..ad7c7f9e16 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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 32.344 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 28.191 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 47f5d0bb06..77c368f1c4 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|3 | 4409/132723 [00:00<00:02, 43293.70KB/s]
- 8%|8 | 10936/132723 [00:00<00:02, 56120.51KB/s]
- 14%|#3 | 18550/132723 [00:00<00:01, 65219.72KB/s]
- 20%|#9 | 26096/132723 [00:00<00:01, 69251.04KB/s]
- 25%|##5 | 33696/132723 [00:00<00:01, 71679.02KB/s]
- 31%|###1 | 41335/132723 [00:00<00:01, 73276.82KB/s]
- 37%|###6 | 48867/132723 [00:00<00:01, 73941.19KB/s]
- 43%|####2 | 56468/132723 [00:00<00:01, 74596.86KB/s]
- 48%|####8 | 64162/132723 [00:00<00:00, 75327.52KB/s]
- 54%|#####4 | 71814/132723 [00:01<00:00, 75692.40KB/s]
- 60%|#####9 | 79443/132723 [00:01<00:00, 75873.67KB/s]
- 66%|######5 | 87088/132723 [00:01<00:00, 76047.17KB/s]
- 71%|#######1 | 94694/132723 [00:01<00:00, 76034.39KB/s]
- 77%|#######7 | 102397/132723 [00:01<00:00, 76333.30KB/s]
- 83%|########2 | 110031/132723 [00:01<00:00, 76333.69KB/s]
- 89%|########8 | 117703/132723 [00:01<00:00, 76447.67KB/s]
- 94%|#########4| 125369/132723 [00:01<00:00, 76510.11KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 73840.87KB/s]
+ 5%|5 | 7055/132723 [00:00<00:01, 70545.69KB/s]
+ 12%|#1 | 15672/132723 [00:00<00:01, 79733.93KB/s]
+ 18%|#8 | 24274/132723 [00:00<00:01, 82598.57KB/s]
+ 25%|##4 | 32757/132723 [00:00<00:01, 75041.68KB/s]
+ 31%|### | 40975/132723 [00:00<00:01, 77440.29KB/s]
+ 37%|###7 | 49561/132723 [00:00<00:01, 80169.48KB/s]
+ 44%|####3 | 58086/132723 [00:00<00:00, 81776.65KB/s]
+ 50%|##### | 66736/132723 [00:00<00:00, 83245.14KB/s]
+ 57%|#####6 | 75347/132723 [00:00<00:00, 84125.03KB/s]
+ 63%|######3 | 83931/132723 [00:01<00:00, 84639.48KB/s]
+ 70%|######9 | 92493/132723 [00:01<00:00, 84935.51KB/s]
+ 76%|#######6 | 101214/132723 [00:01<00:00, 85622.34KB/s]
+ 83%|########2 | 109868/132723 [00:01<00:00, 85897.02KB/s]
+ 89%|########9 | 118543/132723 [00:01<00:00, 86152.00KB/s]
+ 96%|#########5| 127216/132723 [00:01<00:00, 86323.34KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83272.90KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +517,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 26.377 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 32.040 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 ba211fb55f..d1a0ced402 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:22.337</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:43.681</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:26.377</p></td>
+<td><p>03:32.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:21.632</p></td>
+<td><p>03:26.947</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:25.221</p></td>
+<td><p>02:32.873</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>01:32.344</p></td>
+<td><p>01:28.191</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>01:10.916</p></td>
+<td><p>01:13.274</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.272</p></td>
+<td><p>00:53.396</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:38.670</p></td>
+<td><p>00:41.364</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:26.085</p></td>
+<td><p>00:28.162</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:25.814</p></td>
+<td><p>00:27.427</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 5835b09540..ab70dbf42f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ 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.zip07fb9aa0-cc7e-474e-ab93-9e3af8a9a86f 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.zipf0648fd1-8d92-4104-b906-1105398fbcbc 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 a8372c5eb6..9bd4267c9e 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:50.546</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:52.197</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:46.963</p></td>
+<td><p>00:48.515</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>00:02.544</p></td>
+<td><p>00:02.615</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.033</p></td>
+<td><p>00:01.060</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 81870de64a..f1b8bef606 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ 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: 17614us [17614us] (48.44%; 48.44%)
-FoldScaleAxis: 18746us [6us] (51.56%; 51.56%)
- FoldConstant: 18740us [1648us] (51.54%; 99.97%)
- InferType: 17091us [17091us] (47.00%; 91.20%)
+InferType: 19102us [19102us] (49.49%; 49.49%)
+FoldScaleAxis: 19494us [9us] (50.51%; 50.51%)
+ FoldConstant: 19485us [2040us] (50.48%; 99.95%)
+ InferType: 17444us [17444us] (45.20%; 89.53%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ 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: 17137us [17137us] (47.94%; 47.94%)
-FoldScaleAxis: 18611us [5us] (52.06%; 52.06%)
- FoldConstant: 18606us [1663us] (52.05%; 99.97%)
- InferType: 16943us [16943us] (47.40%; 91.06%)
+InferType: 17425us [17425us] (47.84%; 47.84%)
+FoldScaleAxis: 18998us [6us] (52.16%; 52.16%)
+ FoldConstant: 18992us [1712us] (52.14%; 99.97%)
+ InferType: 17280us [17280us] (47.44%; 90.99%)
</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 f8ac9dede1..9fcea8f939 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ 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: 54.217983 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.135360 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 28f20bd46a..37c921e91e 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -861,7 +861,7 @@ 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: 6.685200 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.441040 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 03c4eb6c55..9cf2f9a469 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ 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: 0.018060
-Baseline: 3.197752
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019009
+Baseline: 3.357877
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -529,7 +529,7 @@ 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: 0.296106
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.318953
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -583,7 +583,7 @@ 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: 0.333387
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347315
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -635,7 +635,7 @@ 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: 0.114968
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.124776
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -709,7 +709,7 @@ 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: 0.108361
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109624
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -784,7 +784,7 @@ 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: 0.111469
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111574
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -861,7 +861,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146623
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147443
</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 cdf500a5be..10d8b35b9d 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:33.932</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.447</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.481</p></td>
+<td><p>00:32.743</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>00:01.426</p></td>
+<td><p>00:01.558</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.025</p></td>
+<td><p>00:01.147</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 e364ff44c8..f2d4f882f6 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:06.030</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:13.498</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:27.031</p></td>
+<td><p>05:30.275</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:36.571</p></td>
+<td><p>01:40.071</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:04.732</p></td>
+<td><p>01:06.565</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>00:31.554</p></td>
+<td><p>00:29.263</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:13.565</p></td>
+<td><p>00:14.191</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:12.577</p></td>
+<td><p>00:13.132</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 a4f618dbfb..c55bb57d41 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
@@ -1011,7 +1011,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.355 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.356 ms
</pre></div>
</div>
</div>
@@ -1574,7 +1574,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 27.031 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 30.275 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 70b66e25b1..492ee89577 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8663 7.8661 7.8708 7.8619 0.0036
+ 7.9210 7.9195 7.9253 7.9182 0.0031
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ 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 4.732 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.565 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index da6fc105a6..9238fcc8bf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
- 750.0263 750.0990 750.6909 749.2892 0.5746
+ 757.7189 759.5375 759.7802 753.8389 2.7453
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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 36.571 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 40.071 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 1fe48bf1a3..e3fff5f2a1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -629,407 +629,74 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.buffer_decl((512,), data=compute_1)
- for i_outer_inner, nb_j_inner in T.grid(2, 2):
- cse_var_2: T.int32 = i_outer_inner * 256 + nb_j_inner * 16
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- compute_2[cse_var_2] = T.float32(0)
- compute_2[cse_var_2 + 1] = T.float32(0)
- compute_2[cse_var_2 + 2] = T.float32(0)
- compute_2[cse_var_2 + 3] = T.float32(0)
- compute_2[cse_var_2 + 4] = T.float32(0)
- compute_2[cse_var_2 + 5] = T.float32(0)
- compute_2[cse_var_2 + 6] = T.float32(0)
- compute_2[cse_var_2 + 7] = T.float32(0)
- compute_2[cse_var_2 + 8] = T.float32(0)
- compute_2[cse_var_2 + 9] = T.float32(0)
- compute_2[cse_var_2 + 10] = T.float32(0)
- compute_2[cse_var_2 + 11] = T.float32(0)
- compute_2[cse_var_2 + 12] = T.float32(0)
- compute_2[cse_var_2 + 13] = T.float32(0)
- compute_2[cse_var_2 + 14] = T.float32(0)
- compute_2[cse_var_2 + 15] = T.float32(0)
- compute_2[cse_var_2 + 32] = T.float32(0)
- compute_2[cse_var_2 + 33] = T.float32(0)
- compute_2[cse_var_2 + 34] = T.float32(0)
- compute_2[cse_var_2 + 35] = T.float32(0)
- compute_2[cse_var_2 + 36] = T.float32(0)
- compute_2[cse_var_2 + 37] = T.float32(0)
- compute_2[cse_var_2 + 38] = T.float32(0)
- compute_2[cse_var_2 + 39] = T.float32(0)
- compute_2[cse_var_2 + 40] = T.float32(0)
- compute_2[cse_var_2 + 41] = T.float32(0)
- compute_2[cse_var_2 + 42] = T.float32(0)
- compute_2[cse_var_2 + 43] = T.float32(0)
- compute_2[cse_var_2 + 44] = T.float32(0)
- compute_2[cse_var_2 + 45] = T.float32(0)
- compute_2[cse_var_2 + 46] = T.float32(0)
- compute_2[cse_var_2 + 47] = T.float32(0)
- compute_2[cse_var_2 + 64] = T.float32(0)
- compute_2[cse_var_2 + 65] = T.float32(0)
- compute_2[cse_var_2 + 66] = T.float32(0)
- compute_2[cse_var_2 + 67] = T.float32(0)
- compute_2[cse_var_2 + 68] = T.float32(0)
- compute_2[cse_var_2 + 69] = T.float32(0)
- compute_2[cse_var_2 + 70] = T.float32(0)
- compute_2[cse_var_2 + 71] = T.float32(0)
- compute_2[cse_var_2 + 72] = T.float32(0)
- compute_2[cse_var_2 + 73] = T.float32(0)
- compute_2[cse_var_2 + 74] = T.float32(0)
- compute_2[cse_var_2 + 75] = T.float32(0)
- compute_2[cse_var_2 + 76] = T.float32(0)
- compute_2[cse_var_2 + 77] = T.float32(0)
- compute_2[cse_var_2 + 78] = T.float32(0)
- compute_2[cse_var_2 + 79] = T.float32(0)
- compute_2[cse_var_2 + 96] = T.float32(0)
- compute_2[cse_var_2 + 97] = T.float32(0)
- compute_2[cse_var_2 + 98] = T.float32(0)
- compute_2[cse_var_2 + 99] = T.float32(0)
- compute_2[cse_var_2 + 100] = T.float32(0)
- compute_2[cse_var_2 + 101] = T.float32(0)
- compute_2[cse_var_2 + 102] = T.float32(0)
- compute_2[cse_var_2 + 103] = T.float32(0)
- compute_2[cse_var_2 + 104] = T.float32(0)
- compute_2[cse_var_2 + 105] = T.float32(0)
- compute_2[cse_var_2 + 106] = T.float32(0)
- compute_2[cse_var_2 + 107] = T.float32(0)
- compute_2[cse_var_2 + 108] = T.float32(0)
- compute_2[cse_var_2 + 109] = T.float32(0)
- compute_2[cse_var_2 + 110] = T.float32(0)
- compute_2[cse_var_2 + 111] = T.float32(0)
- compute_2[cse_var_2 + 128] = T.float32(0)
- compute_2[cse_var_2 + 129] = T.float32(0)
- compute_2[cse_var_2 + 130] = T.float32(0)
- compute_2[cse_var_2 + 131] = T.float32(0)
- compute_2[cse_var_2 + 132] = T.float32(0)
- compute_2[cse_var_2 + 133] = T.float32(0)
- compute_2[cse_var_2 + 134] = T.float32(0)
- compute_2[cse_var_2 + 135] = T.float32(0)
- compute_2[cse_var_2 + 136] = T.float32(0)
- compute_2[cse_var_2 + 137] = T.float32(0)
- compute_2[cse_var_2 + 138] = T.float32(0)
- compute_2[cse_var_2 + 139] = T.float32(0)
- compute_2[cse_var_2 + 140] = T.float32(0)
- compute_2[cse_var_2 + 141] = T.float32(0)
- compute_2[cse_var_2 + 142] = T.float32(0)
- compute_2[cse_var_2 + 143] = T.float32(0)
- compute_2[cse_var_2 + 160] = T.float32(0)
- compute_2[cse_var_2 + 161] = T.float32(0)
- compute_2[cse_var_2 + 162] = T.float32(0)
- compute_2[cse_var_2 + 163] = T.float32(0)
- compute_2[cse_var_2 + 164] = T.float32(0)
- compute_2[cse_var_2 + 165] = T.float32(0)
- compute_2[cse_var_2 + 166] = T.float32(0)
- compute_2[cse_var_2 + 167] = T.float32(0)
- compute_2[cse_var_2 + 168] = T.float32(0)
- compute_2[cse_var_2 + 169] = T.float32(0)
- compute_2[cse_var_2 + 170] = T.float32(0)
- compute_2[cse_var_2 + 171] = T.float32(0)
- compute_2[cse_var_2 + 172] = T.float32(0)
- compute_2[cse_var_2 + 173] = T.float32(0)
- compute_2[cse_var_2 + 174] = T.float32(0)
- compute_2[cse_var_2 + 175] = T.float32(0)
- compute_2[cse_var_2 + 192] = T.float32(0)
- compute_2[cse_var_2 + 193] = T.float32(0)
- compute_2[cse_var_2 + 194] = T.float32(0)
- compute_2[cse_var_2 + 195] = T.float32(0)
- compute_2[cse_var_2 + 196] = T.float32(0)
- compute_2[cse_var_2 + 197] = T.float32(0)
- compute_2[cse_var_2 + 198] = T.float32(0)
- compute_2[cse_var_2 + 199] = T.float32(0)
- compute_2[cse_var_2 + 200] = T.float32(0)
- compute_2[cse_var_2 + 201] = T.float32(0)
- compute_2[cse_var_2 + 202] = T.float32(0)
- compute_2[cse_var_2 + 203] = T.float32(0)
- compute_2[cse_var_2 + 204] = T.float32(0)
- compute_2[cse_var_2 + 205] = T.float32(0)
- compute_2[cse_var_2 + 206] = T.float32(0)
- compute_2[cse_var_2 + 207] = T.float32(0)
- compute_2[cse_var_2 + 224] = T.float32(0)
- compute_2[cse_var_2 + 225] = T.float32(0)
- compute_2[cse_var_2 + 226] = T.float32(0)
- compute_2[cse_var_2 + 227] = T.float32(0)
- compute_2[cse_var_2 + 228] = T.float32(0)
- compute_2[cse_var_2 + 229] = T.float32(0)
- compute_2[cse_var_2 + 230] = T.float32(0)
- compute_2[cse_var_2 + 231] = T.float32(0)
- compute_2[cse_var_2 + 232] = T.float32(0)
- compute_2[cse_var_2 + 233] = T.float32(0)
- compute_2[cse_var_2 + 234] = T.float32(0)
- compute_2[cse_var_2 + 235] = T.float32(0)
- compute_2[cse_var_2 + 236] = T.float32(0)
- compute_2[cse_var_2 + 237] = T.float32(0)
- compute_2[cse_var_2 + 238] = T.float32(0)
- compute_2[cse_var_2 + 239] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ for i0_outer_i1_outer_fused in T.parallel(512):
+ compute_1 = T.allocate([128], "float32", "global")
+ compute_2 = T.buffer_decl((128,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init in range(4):
+ cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ compute_2[cse_var_1 + 13] = T.float32(0)
+ compute_2[cse_var_1 + 14] = T.float32(0)
+ compute_2[cse_var_1 + 15] = T.float32(0)
+ for elem_idx, i_inner in T.grid(T.let(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 4):
+ cse_var_2 = T.var("int32")
placeholder_5 = T.buffer_decl((33,), "int32", data=placeholder_3.data)
- cse_var_131: T.int32 = elem_idx * 16
- cse_var_130: T.int32 = cse_var_2 + 99
- cse_var_129: T.int32 = cse_var_2 + 98
- cse_var_128: T.int32 = cse_var_2 + 97
- cse_var_127: T.int32 = cse_var_2 + 96
- cse_var_126: T.int32 = cse_var_2 + 9
- cse_var_125: T.int32 = cse_var_2 + 8
- cse_var_124: T.int32 = cse_var_2 + 79
- cse_var_123: T.int32 = cse_var_2 + 78
- cse_var_122: T.int32 = cse_var_2 + 77
- cse_var_121: T.int32 = cse_var_2 + 76
- cse_var_120: T.int32 = cse_var_2 + 75
- cse_var_119: T.int32 = cse_var_2 + 74
- cse_var_118: T.int32 = cse_var_2 + 73
- cse_var_117: T.int32 = cse_var_2 + 72
- cse_var_116: T.int32 = cse_var_2 + 71
- cse_var_115: T.int32 = cse_var_2 + 70
- cse_var_114: T.int32 = cse_var_2 + 7
- cse_var_113: T.int32 = cse_var_2 + 69
- cse_var_112: T.int32 = cse_var_2 + 68
- cse_var_111: T.int32 = cse_var_2 + 67
- cse_var_110: T.int32 = cse_var_2 + 66
- cse_var_109: T.int32 = cse_var_2 + 65
- cse_var_108: T.int32 = cse_var_2 + 64
- cse_var_107: T.int32 = cse_var_2 + 6
- cse_var_106: T.int32 = cse_var_2 + 5
- cse_var_105: T.int32 = cse_var_2 + 47
- cse_var_104: T.int32 = cse_var_2 + 46
- cse_var_103: T.int32 = cse_var_2 + 45
- cse_var_102: T.int32 = cse_var_2 + 44
- cse_var_101: T.int32 = cse_var_2 + 43
- cse_var_100: T.int32 = cse_var_2 + 42
- cse_var_99: T.int32 = cse_var_2 + 41
- cse_var_98: T.int32 = cse_var_2 + 40
- cse_var_97: T.int32 = cse_var_2 + 4
- cse_var_96: T.int32 = cse_var_2 + 39
- cse_var_95: T.int32 = cse_var_2 + 38
- cse_var_94: T.int32 = cse_var_2 + 37
- cse_var_93: T.int32 = cse_var_2 + 36
- cse_var_92: T.int32 = cse_var_2 + 35
- cse_var_91: T.int32 = cse_var_2 + 34
- cse_var_90: T.int32 = cse_var_2 + 33
- cse_var_89: T.int32 = cse_var_2 + 32
- cse_var_88: T.int32 = cse_var_2 + 3
- cse_var_87: T.int32 = cse_var_2 + 239
- cse_var_86: T.int32 = cse_var_2 + 238
- cse_var_85: T.int32 = cse_var_2 + 237
- cse_var_84: T.int32 = cse_var_2 + 236
- cse_var_83: T.int32 = cse_var_2 + 235
- cse_var_82: T.int32 = cse_var_2 + 234
- cse_var_81: T.int32 = cse_var_2 + 233
- cse_var_80: T.int32 = cse_var_2 + 232
- cse_var_79: T.int32 = cse_var_2 + 231
- cse_var_78: T.int32 = cse_var_2 + 230
- cse_var_77: T.int32 = cse_var_2 + 229
- cse_var_76: T.int32 = cse_var_2 + 228
- cse_var_75: T.int32 = cse_var_2 + 227
- cse_var_74: T.int32 = cse_var_2 + 226
- cse_var_73: T.int32 = cse_var_2 + 225
- cse_var_72: T.int32 = cse_var_2 + 224
- cse_var_71: T.int32 = cse_var_2 + 207
- cse_var_70: T.int32 = cse_var_2 + 206
- cse_var_69: T.int32 = cse_var_2 + 205
- cse_var_68: T.int32 = cse_var_2 + 204
- cse_var_67: T.int32 = cse_var_2 + 203
- cse_var_66: T.int32 = cse_var_2 + 202
- cse_var_65: T.int32 = cse_var_2 + 201
- cse_var_64: T.int32 = cse_var_2 + 200
- cse_var_63: T.int32 = cse_var_2 + 2
- cse_var_62: T.int32 = cse_var_2 + 199
- cse_var_61: T.int32 = cse_var_2 + 198
- cse_var_60: T.int32 = cse_var_2 + 197
- cse_var_59: T.int32 = cse_var_2 + 196
- cse_var_58: T.int32 = cse_var_2 + 195
- cse_var_57: T.int32 = cse_var_2 + 194
- cse_var_56: T.int32 = cse_var_2 + 193
- cse_var_55: T.int32 = cse_var_2 + 192
- cse_var_54: T.int32 = cse_var_2 + 175
- cse_var_53: T.int32 = cse_var_2 + 174
- cse_var_52: T.int32 = cse_var_2 + 173
- cse_var_51: T.int32 = cse_var_2 + 172
- cse_var_50: T.int32 = cse_var_2 + 171
- cse_var_49: T.int32 = cse_var_2 + 170
- cse_var_48: T.int32 = cse_var_2 + 169
- cse_var_47: T.int32 = cse_var_2 + 168
- cse_var_46: T.int32 = cse_var_2 + 167
- cse_var_45: T.int32 = cse_var_2 + 166
- cse_var_44: T.int32 = cse_var_2 + 165
- cse_var_43: T.int32 = cse_var_2 + 164
- cse_var_42: T.int32 = cse_var_2 + 163
- cse_var_41: T.int32 = cse_var_2 + 162
- cse_var_40: T.int32 = cse_var_2 + 161
- cse_var_39: T.int32 = cse_var_2 + 160
- cse_var_38: T.int32 = cse_var_2 + 15
- cse_var_37: T.int32 = cse_var_2 + 143
- cse_var_36: T.int32 = cse_var_2 + 142
- cse_var_35: T.int32 = cse_var_2 + 141
- cse_var_34: T.int32 = cse_var_2 + 140
- cse_var_33: T.int32 = cse_var_2 + 14
- cse_var_32: T.int32 = cse_var_2 + 139
- cse_var_31: T.int32 = cse_var_2 + 138
- cse_var_30: T.int32 = cse_var_2 + 137
- cse_var_29: T.int32 = cse_var_2 + 136
- cse_var_28: T.int32 = cse_var_2 + 135
- cse_var_27: T.int32 = cse_var_2 + 134
- cse_var_26: T.int32 = cse_var_2 + 133
- cse_var_25: T.int32 = cse_var_2 + 132
- cse_var_24: T.int32 = cse_var_2 + 131
- cse_var_23: T.int32 = cse_var_2 + 130
- cse_var_22: T.int32 = cse_var_2 + 13
- cse_var_21: T.int32 = cse_var_2 + 129
- cse_var_20: T.int32 = cse_var_2 + 128
- cse_var_19: T.int32 = cse_var_2 + 12
- cse_var_18: T.int32 = cse_var_2 + 111
- cse_var_17: T.int32 = cse_var_2 + 110
- cse_var_16: T.int32 = cse_var_2 + 11
- cse_var_15: T.int32 = cse_var_2 + 109
- cse_var_14: T.int32 = cse_var_2 + 108
- cse_var_13: T.int32 = cse_var_2 + 107
- cse_var_12: T.int32 = cse_var_2 + 106
- cse_var_11: T.int32 = cse_var_2 + 105
- cse_var_10: T.int32 = cse_var_2 + 104
- cse_var_9: T.int32 = cse_var_2 + 103
- cse_var_8: T.int32 = cse_var_2 + 102
- cse_var_7: T.int32 = cse_var_2 + 101
- cse_var_6: T.int32 = cse_var_2 + 100
- cse_var_5: T.int32 = cse_var_2 + 10
- cse_var_4: T.int32 = cse_var_2 + 1
- cse_var_3: T.int32 = i0_outer_i1_outer_fused // 16 * 4096 + i_outer_inner * 2048
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 1024 + i_inner * 256
+ cse_var_17: T.int32 = cse_var_20 + 9
+ cse_var_16: T.int32 = cse_var_20 + 8
+ cse_var_15: T.int32 = cse_var_20 + 7
+ cse_var_14: T.int32 = cse_var_20 + 6
+ cse_var_13: T.int32 = cse_var_20 + 5
+ cse_var_12: T.int32 = cse_var_20 + 4
+ cse_var_11: T.int32 = cse_var_20 + 3
+ cse_var_10: T.int32 = cse_var_20 + 2
+ cse_var_9: T.int32 = cse_var_20 + 15
+ cse_var_8: T.int32 = cse_var_20 + 14
+ cse_var_7: T.int32 = cse_var_20 + 13
+ cse_var_6: T.int32 = cse_var_20 + 12
+ cse_var_5: T.int32 = cse_var_20 + 11
+ cse_var_4: T.int32 = cse_var_20 + 10
+ cse_var_3: T.int32 = cse_var_20 + 1
placeholder_6 = T.buffer_decl((78656,), data=placeholder_1.data)
placeholder_7 = T.buffer_decl((32768,), data=placeholder.data)
placeholder_8 = T.buffer_decl((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_63] = compute_2[cse_var_63] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_88] = compute_2[cse_var_88] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_97] = compute_2[cse_var_97] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_106] = compute_2[cse_var_106] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_107] = compute_2[cse_var_107] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_114] = compute_2[cse_var_114] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_125] = compute_2[cse_var_125] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_126] = compute_2[cse_var_126] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_22] = compute_2[cse_var_22] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_33] = compute_2[cse_var_33] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_38] = compute_2[cse_var_38] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- compute_2[cse_var_89] = compute_2[cse_var_89] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_90] = compute_2[cse_var_90] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_91] = compute_2[cse_var_91] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_92] = compute_2[cse_var_92] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_93] = compute_2[cse_var_93] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_94] = compute_2[cse_var_94] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_95] = compute_2[cse_var_95] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_96] = compute_2[cse_var_96] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_98] = compute_2[cse_var_98] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_99] = compute_2[cse_var_99] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_100] = compute_2[cse_var_100] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_101] = compute_2[cse_var_101] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_102] = compute_2[cse_var_102] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_103] = compute_2[cse_var_103] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_104] = compute_2[cse_var_104] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_105] = compute_2[cse_var_105] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- compute_2[cse_var_108] = compute_2[cse_var_108] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_109] = compute_2[cse_var_109] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_110] = compute_2[cse_var_110] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_111] = compute_2[cse_var_111] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_112] = compute_2[cse_var_112] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_113] = compute_2[cse_var_113] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_115] = compute_2[cse_var_115] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_116] = compute_2[cse_var_116] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_117] = compute_2[cse_var_117] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_118] = compute_2[cse_var_118] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_119] = compute_2[cse_var_119] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_120] = compute_2[cse_var_120] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_121] = compute_2[cse_var_121] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_122] = compute_2[cse_var_122] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_123] = compute_2[cse_var_123] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_124] = compute_2[cse_var_124] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 512], T.float32(0))
- compute_2[cse_var_127] = compute_2[cse_var_127] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_128] = compute_2[cse_var_128] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_129] = compute_2[cse_var_129] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_130] = compute_2[cse_var_130] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 768], T.float32(0))
- compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_21] = compute_2[cse_var_21] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_23] = compute_2[cse_var_23] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_24] = compute_2[cse_var_24] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_25] = compute_2[cse_var_25] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_26] = compute_2[cse_var_26] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_27] = compute_2[cse_var_27] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_28] = compute_2[cse_var_28] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_29] = compute_2[cse_var_29] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_30] = compute_2[cse_var_30] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_31] = compute_2[cse_var_31] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_32] = compute_2[cse_var_32] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_34] = compute_2[cse_var_34] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_35] = compute_2[cse_var_35] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_36] = compute_2[cse_var_36] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_37] = compute_2[cse_var_37] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1024], T.float32(0))
- compute_2[cse_var_39] = compute_2[cse_var_39] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_40] = compute_2[cse_var_40] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_41] = compute_2[cse_var_41] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_42] = compute_2[cse_var_42] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_43] = compute_2[cse_var_43] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_44] = compute_2[cse_var_44] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_45] = compute_2[cse_var_45] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_46] = compute_2[cse_var_46] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_47] = compute_2[cse_var_47] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_48] = compute_2[cse_var_48] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_49] = compute_2[cse_var_49] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_50] = compute_2[cse_var_50] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_51] = compute_2[cse_var_51] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_52] = compute_2[cse_var_52] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_53] = compute_2[cse_var_53] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_54] = compute_2[cse_var_54] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1280], T.float32(0))
- compute_2[cse_var_55] = compute_2[cse_var_55] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_56] = compute_2[cse_var_56] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_57] = compute_2[cse_var_57] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_58] = compute_2[cse_var_58] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_59] = compute_2[cse_var_59] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_60] = compute_2[cse_var_60] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_61] = compute_2[cse_var_61] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_62] = compute_2[cse_var_62] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_64] = compute_2[cse_var_64] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_65] = compute_2[cse_var_65] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_66] = compute_2[cse_var_66] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_67] = compute_2[cse_var_67] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_68] = compute_2[cse_var_68] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_69] = compute_2[cse_var_69] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_70] = compute_2[cse_var_70] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_71] = compute_2[cse_var_71] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1536], T.float32(0))
- compute_2[cse_var_72] = compute_2[cse_var_72] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_73] = compute_2[cse_var_73] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 1] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_74] = compute_2[cse_var_74] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 2] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_75] = compute_2[cse_var_75] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 3] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_76] = compute_2[cse_var_76] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 4] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_77] = compute_2[cse_var_77] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 5] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_78] = compute_2[cse_var_78] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 6] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_79] = compute_2[cse_var_79] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 7] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_80] = compute_2[cse_var_80] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 8] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_81] = compute_2[cse_var_81] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 9] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_82] = compute_2[cse_var_82] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 10] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_83] = compute_2[cse_var_83] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 11] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_84] = compute_2[cse_var_84] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 12] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_85] = compute_2[cse_var_85] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 13] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_86] = compute_2[cse_var_86] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 14] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- compute_2[cse_var_87] = compute_2[cse_var_87] + placeholder_6[placeholder_5[cse_var_1] * 16 + cse_var_131 + 15] * T.max(placeholder_7[cse_var_3 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 1792], T.float32(0))
- for i0_inner in range(16):
- cse_var_132: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ for i0_inner in range(4):
+ cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 2048 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.buffer_decl((65536,), data=compute.data)
placeholder_5 = T.buffer_decl((65536,), data=placeholder_4.data)
- compute_3[cse_var_132:cse_var_132 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_132:cse_var_132 + 32], T.Broadcast(T.float32(0), 32))
+ compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
</pre></div>
</div>
</div>
@@ -1063,7 +730,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.768 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.848 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 acca44ffab..1e6e645655 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.552</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:42.629</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</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>00:41.519</p></td>
+<td><p>00:42.596</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>
@@ -361,7 +361,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.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 7373724608..6c5c13ab58 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -568,8 +568,9 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 7.75/7.75 result: MeasureResult(costs=(0.0298710955,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.783884048461914, timestamp=1674185426.5654202) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,41550
-No: 2 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+No: 1 GFLOPS: 224.33/224.33 result: MeasureResult(costs=(0.0010319512178217822,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0957257747650146, timestamp=1674208851.3760052) [('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2521220
+No: 2 GFLOPS: 5.65/224.33 result: MeasureResult(costs=(0.0409666975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.2628161907196045, timestamp=1674208852.342046) [('tile_f', [-1, 1, 4, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7945067
+No: 3 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -691,8 +692,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1224397
-No: 3 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3153438
+No: 4 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -814,8 +815,161 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10372241
-No: 4 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9153133
+No: 5 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 4: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f95217c5fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
+
+Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 8, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5489408
+No: 6 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -937,8 +1091,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10342327
-No: 5 GFLOPS: 0.00/7.75 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10277052
+No: 7 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1060,9 +1214,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4392618
-No: 6 GFLOPS: 127.76/127.76 result: MeasureResult(costs=(0.0018119425555555557,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.839144229888916, timestamp=1674185434.4324708) [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9502410
-No: 7 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1459555
+No: 8 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1184,8 +1337,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6022183
-No: 8 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10210078
+No: 9 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1307,8 +1460,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2289829
-No: 9 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2937055
+No: 10 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1430,26 +1583,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7162656
-No: 10 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9195726
-No: 11 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8708587
+No: 11 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1571,8 +1706,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5058574
-No: 12 GFLOPS: 0.00/127.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7064602
+No: 12 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9952904
+No: 13 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1694,10 +1847,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2190495
-No: 13 GFLOPS: 2.71/127.76 result: MeasureResult(costs=(0.08529100775000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.805093050003052, timestamp=1674185450.5576441) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7325263
-No: 14 GFLOPS: 299.03/299.03 result: MeasureResult(costs=(0.000774184811594203,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5905015468597412, timestamp=1674185451.5622723) [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,436081
-No: 15 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2108670
+No: 14 GFLOPS: 31.44/224.33 result: MeasureResult(costs=(0.007363165714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9638252258300781, timestamp=1674208874.2653227) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6995175
+No: 15 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1819,8 +1971,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2864031
-No: 16 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8128400
+No: 16 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1942,8 +2094,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5632838
-No: 17 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7031901
+No: 17 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2065,8 +2217,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2313260
-No: 18 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,477880
+No: 18 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2188,8 +2340,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9836868
-No: 19 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,116947
+No: 19 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2311,8 +2463,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7970924
-No: 20 GFLOPS: 0.00/299.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6647737
+No: 20 GFLOPS: 0.00/224.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2434,7 +2586,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3935986
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7368198
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2473,9 +2625,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,436081
+[('tile_f', [-1, 2, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2521220
Finish loading 20 records
-Time cost of this operator: 0.001133
+Time cost of this operator: 0.001407
</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 ad7b4284a0..403307437d 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -647,10 +647,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 307.8 98.719 (1, 2, 10, 10, 3) 2 1 [307.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.969 (1, 6, 10, 10) 1 1 [3.021]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.972 0.312 (1, 1, 10, 10, 3) 1 1 [0.972]
-Total_time - 311.793 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.9 98.729 (1, 2, 10, 10, 3) 2 1 [310.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.966 (1, 6, 10, 10) 1 1 [3.042]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.305 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 314.902 - - - - -
</pre></div>
</div>
</div>
@@ -702,10 +702,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 104.8 97.555 (1, 6, 10, 10, 1) 2 1 [104.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.776 1.653 (1, 6, 10, 10) 1 1 [1.776]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.851 0.792 (1, 3, 10, 10, 1) 1 1 [0.851]
-Total_time - 107.426 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.7 97.488 (1, 6, 10, 10, 1) 2 1 [103.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.817 1.708 (1, 6, 10, 10) 1 1 [1.817]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.855 0.804 (1, 3, 10, 10, 1) 1 1 [0.855]
+Total_time - 106.372 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 8702f07960..4d74c1d1b4 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,7 +454,8 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 137MB/s]
+ 88%|########8 | 3.02M/3.42M [00:00<00:00, 31.7MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 35.2MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -578,7 +579,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.086 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.733 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 9d30173986..6f646756c3 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -524,7 +524,7 @@ 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/tmpiql0qhf6/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmppak212zv/images/random'
</pre></div>
</div>
</div>
@@ -584,8 +584,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpiql0qhf6/images/target contains 8144 images
-/tmp/tmpiql0qhf6/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmppak212zv/images/target contains 8144 images
+/tmp/tmppak212zv/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -697,13 +697,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2138 - accuracy: 0.9251 - val_loss: 0.1147 - val_accuracy: 0.9562 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2188 - accuracy: 0.9257 - val_loss: 0.1318 - val_accuracy: 0.9585 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0960 - accuracy: 0.9631 - val_loss: 0.0898 - val_accuracy: 0.9671 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0977 - accuracy: 0.9653 - val_loss: 0.1354 - val_accuracy: 0.9569 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0588 - accuracy: 0.9798 - val_loss: 0.1360 - val_accuracy: 0.9528 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0697 - accuracy: 0.9748 - val_loss: 0.1547 - val_accuracy: 0.9543 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f6b69639fd0>
+<keras.callbacks.History object at 0x7f1da663ca10>
</pre></div>
</div>
</div>
@@ -963,7 +963,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 19.926 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 23.628 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 6b95e2c6b5..22dce9d818 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:30.155</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:39.732</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:19.926</p></td>
+<td><p>04:23.628</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:07.086</p></td>
+<td><p>01:09.733</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:50.864</p></td>
+<td><p>00:53.336</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.512</p></td>
+<td><p>00:09.093</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.768</p></td>
+<td><p>00:03.942</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 1f2bdd12a7..bbdaf4c765 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.680</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.586</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.973</p></td>
+<td><p>00:33.387</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.161</p></td>
+<td><p>00:10.602</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>00:01.541</p></td>
+<td><p>00:01.591</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 04d480eec7..72078e6422 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f6bc0351440>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f1da6dbe8c0>
</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 80deb40a55..3caf00176f 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.523</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.376</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.064</p></td>
+<td><p>00:04.689</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.119</p></td>
+<td><p>00:01.247</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>00:00.570</p></td>
+<td><p>00:00.614</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>00:00.549</p></td>
+<td><p>00:00.597</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>00:00.116</p></td>
+<td><p>00:00.121</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.049</p></td>
+<td><p>00:00.052</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.031</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.025</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 13a699c5cc..d25d027cfd 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -574,7 +574,7 @@ class Module:
def main(A: T.Buffer((1024, 64), "float32"), B: T.Buffer((512, 64), "float32"), C: T.Buffer((1024, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpqmz888xx/input0.cc'\nsource_filename = \"/tmp/tmpqmz888xx/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 [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpo8jl13gc/input0.cc'\nsource_filename = \"/tmp/tmpo8jl13gc/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 [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B.data, j_outer * 1024, 1024, 1), 16, 64, 64)
</pre></div>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
index 83d29f9160..0da10d85d1 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode-members.html
@@ -84,7 +84,7 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a7eafc8f0a4962114332a6a34289ff80e">Annotate</a>(const BlockRV &block_rv, const String &ann_key, const ObjectRef &ann_val)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a7eae30e3d365afebdc96b58eac6fd731">Bind</a>(const LoopRV &loop_rv, const String &thread_axis)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#ad519f290c705afd441eaf683c4e24693">Blockize</a>(const LoopRV &loop_rv, bool preserve_unit_iters=true)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa">CacheIndex</a>(const BlockRV &block_rv, int buffer_index)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1">CacheIndex</a>(const BlockRV &block_rv, const String &storage_scope, int cse_thresh)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818">CacheInplace</a>(const BlockRV &block_rv, int read_buffer_index, const String &storage_scope)=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a55bf333c162865fa4d18eb20ecf9a9a7">CacheRead</a>(const BlockRV &block_rv, int read_buffer_index, const String &storage_scope, const Array< BlockRV > consumer_blocks={})=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a9f43b2ddd6e3b3bab64671345ecba72d">CacheWrite</a>(const BlockRV &block_rv, int write_buffer_index, const String &storage_scope, const Array< BlockRV > consumer_blocks={})=0</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html">tvm::tir::ScheduleNode</a></td><td class="entry"><span class="mlabel">pure virtual</span></td></tr>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
index dd8d209d62..8d35e3a590 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1ScheduleNode.html
@@ -210,9 +210,9 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:abefe28d441bad8fc4b276e1bb35f9818"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818">CacheInplace</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &blo [...]
<tr class="memdesc:abefe28d441bad8fc4b276e1bb35f9818"><td class="mdescLeft"> </td><td class="mdescRight">Create 2 blocks that read&write a buffer region into a read/write cache. It requires the the target block both read & write the target buffer. <a href="#abefe28d441bad8fc4b276e1bb35f9818">More...</a><br /></td></tr>
<tr class="separator:abefe28d441bad8fc4b276e1bb35f9818"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a3b1d3ae0b3d145cbe33a8162723aa9aa"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa">CacheIndex</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &block [...]
-<tr class="memdesc:a3b1d3ae0b3d145cbe33a8162723aa9aa"><td class="mdescLeft"> </td><td class="mdescRight">Create a block to cache precomputed index for later use. if there is no index computation, keep unchanged. <a href="#a3b1d3ae0b3d145cbe33a8162723aa9aa">More...</a><br /></td></tr>
-<tr class="separator:a3b1d3ae0b3d145cbe33a8162723aa9aa"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a22353e0eac6afe97fb0f0b2da9ab4da1"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> > </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1">CacheIndex</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &block [...]
+<tr class="memdesc:a22353e0eac6afe97fb0f0b2da9ab4da1"><td class="mdescLeft"> </td><td class="mdescRight">Create a block to cache precomputed index for later use. if there is no index computation, keep unchanged. <a href="#a22353e0eac6afe97fb0f0b2da9ab4da1">More...</a><br /></td></tr>
+<tr class="separator:a22353e0eac6afe97fb0f0b2da9ab4da1"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a9e36a8a0e37a76e55068dd534e28c8c5"><td class="memItemLeft" align="right" valign="top">virtual <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a9e36a8a0e37a76e55068dd534e28c8c5">ReIndex</a> (const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> &block_rv, int buffer_index, <a class="el" href="namespacetvm_1_1tir.html#a1c8232ed [...]
<tr class="memdesc:a9e36a8a0e37a76e55068dd534e28c8c5"><td class="mdescLeft"> </td><td class="mdescRight">Create a block that read/write a buffer region into a read/write cache with reindexing. The layout of the cache will be the same as by the iterators of the block that reads/writes the buffer. It requires: 1) There is only one block who reads/writes the target buffer 2) There is only one buffer load/store of this buffer in the block. <a href="#a9e36a8a0e37a76e55068dd534e28c8c5">M [...]
<tr class="separator:a9e36a8a0e37a76e55068dd534e28c8c5"><td class="memSeparator" colspan="2"> </td></tr>
@@ -670,8 +670,8 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a3b1d3ae0b3d145cbe33a8162723aa9aa"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a3b1d3ae0b3d145cbe33a8162723aa9aa">◆ </a></span>CacheIndex()</h2>
+<a id="a22353e0eac6afe97fb0f0b2da9ab4da1"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a22353e0eac6afe97fb0f0b2da9ab4da1">◆ </a></span>CacheIndex()</h2>
<div class="memitem">
<div class="memproto">
@@ -685,11 +685,17 @@ Additional Inherited Members</h2></td></tr>
<td class="paramtype">const <a class="el" href="classtvm_1_1tir_1_1BlockRV.html">BlockRV</a> & </td>
<td class="paramname"><em>block_rv</em>, </td>
</tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const <a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> & </td>
+ <td class="paramname"><em>storage_scope</em>, </td>
+ </tr>
<tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">int </td>
- <td class="paramname"><em>buffer_index</em> </td>
+ <td class="paramname"><em>cse_thresh</em> </td>
</tr>
<tr>
<td></td>
@@ -708,7 +714,8 @@ Additional Inherited Members</h2></td></tr>
<dl class="params"><dt>Parameters</dt><dd>
<table class="params">
<tr><td class="paramname">block_rv</td><td>The target block </td></tr>
- <tr><td class="paramname">buffer_index</td><td>The index of the target buffer in block's read region </td></tr>
+ <tr><td class="paramname">storage_scope</td><td>The storage scope of cached block </td></tr>
+ <tr><td class="paramname">cse_thresh</td><td>The repeat threshold that determines a common sub expr </td></tr>
</table>
</dd>
</dl>
diff --git a/docs/reference/api/doxygen/database_8h_source.html b/docs/reference/api/doxygen/database_8h_source.html
index f12a3daa70..88e0bd0829 100644
--- a/docs/reference/api/doxygen/database_8h_source.html
+++ b/docs/reference/api/doxygen/database_8h_source.html
@@ -85,7 +85,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadHash_html_a7cb09ddc6c76d9d00ddbeab8502d97cb"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadHash.html#a7cb09ddc6c76d9d00ddbeab8502d97cb">tvm::meta_schedule::WorkloadHash::operator()</a></div><div class="ttdeci">size_t operator()(const Workload &a) const</div><div class="ttdef"><b>Definition:</b> database.h:96</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html">tvm::meta_schedule::PyDatabaseNode</a></div><div class="ttdoc">The database with customized methods on the python-side. </div><div class="ttdef"><b>Definition:</b> database.h:272</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="structtvm_1_1meta__schedule_1_1WorkloadEqual_html_a49b0e137a01a278469ff63729afae804"><div class="ttname"><a href="structtvm_1_1meta__schedule_1_1WorkloadEqual.html#a49b0e137a01a278469ff63729afae804">tvm::meta_schedule::WorkloadEqual::WorkloadEqual</a></div><div class="ttdeci">WorkloadEqual(const ModuleEquality &mod_eq)</div><div class="ttdef"><b>Definition:</b> database.h:101</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuningRecordNode_html_a8cc2d64f796593a1a774eef259f17b29"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuningRecordNode.html#a8cc2d64f796593a1a774eef259f17b29">tvm::meta_schedule::TuningRecordNode::trace</a></div><div class="ttdeci">tir::Trace trace</div><div class="ttdoc">The trace tuned. </div><div class="ttdef"><b>Definition:</b> database.h:117</div></div>
<div class="ttc" id="arg__info_8h_html"><div class="ttname"><a href="arg__info_8h.html">arg_info.h</a></div></div>
diff --git a/docs/reference/api/doxygen/functions_c.html b/docs/reference/api/doxygen/functions_c.html
index 092e176175..3bf587259d 100644
--- a/docs/reference/api/doxygen/functions_c.html
+++ b/docs/reference/api/doxygen/functions_c.html
@@ -76,7 +76,7 @@ $(function() {
, <a class="el" href="classtvm_1_1te_1_1Schedule.html#ada9825f59ef130a0ab0b3a01ea348d71">tvm::te::Schedule</a>
</li>
<li>CacheIndex()
-: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa">tvm::tir::ScheduleNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1">tvm::tir::ScheduleNode</a>
</li>
<li>CacheInplace()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818">tvm::tir::ScheduleNode</a>
diff --git a/docs/reference/api/doxygen/functions_func_c.html b/docs/reference/api/doxygen/functions_func_c.html
index 6143ec9102..788a341a73 100644
--- a/docs/reference/api/doxygen/functions_func_c.html
+++ b/docs/reference/api/doxygen/functions_func_c.html
@@ -73,7 +73,7 @@ $(function() {
, <a class="el" href="classtvm_1_1te_1_1Schedule.html#ada9825f59ef130a0ab0b3a01ea348d71">tvm::te::Schedule</a>
</li>
<li>CacheIndex()
-: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa">tvm::tir::ScheduleNode</a>
+: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1">tvm::tir::ScheduleNode</a>
</li>
<li>CacheInplace()
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818">tvm::tir::ScheduleNode</a>
diff --git a/docs/reference/api/doxygen/measure__candidate_8h_source.html b/docs/reference/api/doxygen/measure__candidate_8h_source.html
index bcb6ce3b7b..beca3df3ce 100644
--- a/docs/reference/api/doxygen/measure__candidate_8h_source.html
+++ b/docs/reference/api/doxygen/measure__candidate_8h_source.html
@@ -71,7 +71,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html_a99858dbe74082cc52938ac942523d792"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html#a99858dbe74082cc52938ac942523d792">tvm::meta_schedule::MeasureCandidateNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> measure_candidate.h:40</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html_a6891e92cac8712bb690401ed121ae7e8"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html#a6891e92cac8712bb690401ed121ae7e8">tvm::meta_schedule::MeasureCandidateNode::args_info</a></div><div class="ttdeci">Array< ArgInfo > args_info</div><div class="ttdoc">The argument information, e.g., (shape, dtype) for tensors. </div><div class="ttdef"><b>Definition:</b> measure_candidate. [...]
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="arg__info_8h_html"><div class="ttname"><a href="arg__info_8h.html">arg_info.h</a></div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1MeasureCandidateNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1MeasureCandidateNode.html">tvm::meta_schedule::MeasureCandidateNode</a></div><div class="ttdoc">The schedule (with input shapes) to be measured. </div><div class="ttdef"><b>Definition:</b> measure_candidate.h:33</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
diff --git a/docs/reference/api/doxygen/postproc_8h_source.html b/docs/reference/api/doxygen/postproc_8h_source.html
index cd1650d3ca..ef1fc5aefc 100644
--- a/docs/reference/api/doxygen/postproc_8h_source.html
+++ b/docs/reference/api/doxygen/postproc_8h_source.html
@@ -75,7 +75,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyPostprocNode_html_a3771e585727ef6dfecc502ffe57fd2a2"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyPostprocNode.html#a3771e585727ef6dfecc502ffe57fd2a2">tvm::meta_schedule::PyPostprocNode::f_apply</a></div><div class="ttdeci">FApply f_apply</div><div class="ttdoc">The packed function to the Apply function. </div><div class="ttdef"><b>Definition:</b> postproc.h:190</div></div>
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:95</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1Postproc_html_a1b95aac48704d0c0740ede2040b942bb"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1Postproc.html#a1b95aac48704d0c0740ede2040b942bb">tvm::meta_schedule::Postproc::FAsString</a></div><div class="ttdeci">runtime::TypedPackedFunc< String()> FAsString</div><div class="ttdoc">Get the postprocessor function as string with name. </div><div class="ttdef"><b>Definition:</b> postproc.h:94</div></div>
diff --git a/docs/reference/api/doxygen/schedule__rule_8h_source.html b/docs/reference/api/doxygen/schedule__rule_8h_source.html
index aca563cb7d..c07d3e1b20 100644
--- a/docs/reference/api/doxygen/schedule__rule_8h_source.html
+++ b/docs/reference/api/doxygen/schedule__rule_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyScheduleRuleNode_html_a752192bcb5385b1ba72b7c1856c6f360"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyScheduleRuleNode.html#a752192bcb5385b1ba72b7c1856c6f360">tvm::meta_schedule::PyScheduleRuleNode::f_apply</a></div><div class="ttdeci">FApply f_apply</div><div class="ttdoc">The packed function to the Apply function. </div><div class="ttdef"><b>Definition:</b> schedule_rule.h:318</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TuneContext_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TuneContext.html">tvm::meta_schedule::TuneContext</a></div><div class="ttdoc">Managed reference to TuneContextNode. </div><div class="ttdef"><b>Definition:</b> tune_context.h:95</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
diff --git a/docs/reference/api/doxygen/search/all_4.js b/docs/reference/api/doxygen/search/all_4.js
index 9947779ce5..34f3e14b18 100644
--- a/docs/reference/api/doxygen/search/all_4.js
+++ b/docs/reference/api/doxygen/search/all_4.js
@@ -6,7 +6,7 @@ var searchData=
['cache_5fline_5fbytes',['cache_line_bytes',['../classtvm_1_1auto__scheduler_1_1HardwareParamsNode.html#a3ed41e95549c177c0e3cbafefc0f3959',1,'tvm::auto_scheduler::HardwareParamsNode']]],
['cache_5fread',['cache_read',['../classtvm_1_1auto__scheduler_1_1State.html#a4ff71b692f0eabfabf515ed91b59a116',1,'tvm::auto_scheduler::State::cache_read()'],['../classtvm_1_1te_1_1Schedule.html#a38ef95a62faf0c15f132847efa20249b',1,'tvm::te::Schedule::cache_read()']]],
['cache_5fwrite',['cache_write',['../classtvm_1_1auto__scheduler_1_1State.html#a385adc36d7cb242e8204fe14c4df8335',1,'tvm::auto_scheduler::State::cache_write()'],['../classtvm_1_1te_1_1Schedule.html#ada9825f59ef130a0ab0b3a01ea348d71',1,'tvm::te::Schedule::cache_write(const Array< Tensor > &tensor, const std::string &scope)'],['../classtvm_1_1te_1_1Schedule.html#a15582f96d0aaf9a2bd9f2afcad3935d4',1,'tvm::te::Schedule::cache_write(const Tensor &tensor, const std::string [...]
- ['cacheindex',['CacheIndex',['../classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa',1,'tvm::tir::ScheduleNode']]],
+ ['cacheindex',['CacheIndex',['../classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1',1,'tvm::tir::ScheduleNode']]],
['cacheinplace',['CacheInplace',['../classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818',1,'tvm::tir::ScheduleNode']]],
['cacheread',['CacheRead',['../classtvm_1_1tir_1_1ScheduleNode.html#a55bf333c162865fa4d18eb20ecf9a9a7',1,'tvm::tir::ScheduleNode']]],
['cachereadstep',['CacheReadStep',['../classtvm_1_1auto__scheduler_1_1CacheReadStep.html',1,'tvm::auto_scheduler::CacheReadStep'],['../classtvm_1_1auto__scheduler_1_1CacheReadStep.html#a5e0dd0b6d5f746e96e4fec058edc98dc',1,'tvm::auto_scheduler::CacheReadStep::CacheReadStep(int stage_id, String scope_name, const Array< Integer > &reader_stage_ids)'],['../classtvm_1_1auto__scheduler_1_1CacheReadStep.html#a6bc3dd6558c83d1d74cc7163cccbea7f',1,'tvm::auto_scheduler::CacheReadStep::C [...]
diff --git a/docs/reference/api/doxygen/search/functions_3.js b/docs/reference/api/doxygen/search/functions_3.js
index 0c2f00a5ba..65e7aadd31 100644
--- a/docs/reference/api/doxygen/search/functions_3.js
+++ b/docs/reference/api/doxygen/search/functions_3.js
@@ -3,7 +3,7 @@ var searchData=
['c_5fstr',['c_str',['../classtvm_1_1runtime_1_1String.html#ac785c91cb744c18f3ef21fab098d02b2',1,'tvm::runtime::String']]],
['cache_5fread',['cache_read',['../classtvm_1_1auto__scheduler_1_1State.html#a4ff71b692f0eabfabf515ed91b59a116',1,'tvm::auto_scheduler::State::cache_read()'],['../classtvm_1_1te_1_1Schedule.html#a38ef95a62faf0c15f132847efa20249b',1,'tvm::te::Schedule::cache_read()']]],
['cache_5fwrite',['cache_write',['../classtvm_1_1auto__scheduler_1_1State.html#a385adc36d7cb242e8204fe14c4df8335',1,'tvm::auto_scheduler::State::cache_write()'],['../classtvm_1_1te_1_1Schedule.html#ada9825f59ef130a0ab0b3a01ea348d71',1,'tvm::te::Schedule::cache_write(const Array< Tensor > &tensor, const std::string &scope)'],['../classtvm_1_1te_1_1Schedule.html#a15582f96d0aaf9a2bd9f2afcad3935d4',1,'tvm::te::Schedule::cache_write(const Tensor &tensor, const std::string [...]
- ['cacheindex',['CacheIndex',['../classtvm_1_1tir_1_1ScheduleNode.html#a3b1d3ae0b3d145cbe33a8162723aa9aa',1,'tvm::tir::ScheduleNode']]],
+ ['cacheindex',['CacheIndex',['../classtvm_1_1tir_1_1ScheduleNode.html#a22353e0eac6afe97fb0f0b2da9ab4da1',1,'tvm::tir::ScheduleNode']]],
['cacheinplace',['CacheInplace',['../classtvm_1_1tir_1_1ScheduleNode.html#abefe28d441bad8fc4b276e1bb35f9818',1,'tvm::tir::ScheduleNode']]],
['cacheread',['CacheRead',['../classtvm_1_1tir_1_1ScheduleNode.html#a55bf333c162865fa4d18eb20ecf9a9a7',1,'tvm::tir::ScheduleNode']]],
['cachereadstep',['CacheReadStep',['../classtvm_1_1auto__scheduler_1_1CacheReadStep.html#a5e0dd0b6d5f746e96e4fec058edc98dc',1,'tvm::auto_scheduler::CacheReadStep::CacheReadStep(int stage_id, String scope_name, const Array< Integer > &reader_stage_ids)'],['../classtvm_1_1auto__scheduler_1_1CacheReadStep.html#a6bc3dd6558c83d1d74cc7163cccbea7f',1,'tvm::auto_scheduler::CacheReadStep::CacheReadStep(dmlc::JSONReader *reader)']]],
diff --git a/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html b/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
index e814a3082c..e05dd72cef 100644
--- a/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
+++ b/docs/reference/api/doxygen/tir_2schedule_2schedule_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">schedule.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="tir_2schedule_2schedule_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment [...]
+<a href="tir_2schedule_2schedule_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment [...]
<div class="ttc" id="namespacetvm_1_1script_1_1ir__builder_1_1tir_html_acd41556b0c4088d0f309ef5495aaebe3"><div class="ttname"><a href="namespacetvm_1_1script_1_1ir__builder_1_1tir.html#acd41556b0c4088d0f309ef5495aaebe3">tvm::script::ir_builder::tir::Unroll</a></div><div class="ttdeci">ForFrame Unroll(PrimExpr start, PrimExpr stop, Optional< Map< String, ObjectRef >> annotations=NullOpt)</div><div class="ttdoc">The unrolled For statement. </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1StmtNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1StmtNode.html">tvm::tir::StmtNode</a></div><div class="ttdoc">Base node of all statements. </div><div class="ttdef"><b>Definition:</b> stmt.h:38</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BlockRVNode_html_af90b398c502892d19ff3bdf6463d32ab"><div class="ttname"><a href="classtvm_1_1tir_1_1BlockRVNode.html#af90b398c502892d19ff3bdf6463d32ab">tvm::tir::BlockRVNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> schedule.h:53</div></div>
@@ -84,7 +84,7 @@ $(function() {
<div class="ttc" id="object_8h_html_aaaa3dc5b6dc33f84b2d28f9a81267212"><div class="ttname"><a href="object_8h.html#aaaa3dc5b6dc33f84b2d28f9a81267212">TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_MUTABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:744</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_a9ae244600a5e56c4adc9faf6d88f931e"><div class="ttname"><a href="namespacetvm_1_1tir.html#a9ae244600a5e56c4adc9faf6d88f931e">tvm::tir::ScheduleErrorRenderLevel</a></div><div class="ttdeci">ScheduleErrorRenderLevel</div><div class="ttdoc">The level of detailed error message rendering. </div><div class="ttdef"><b>Definition:</b> schedule.h:31</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_a9ae244600a5e56c4adc9faf6d88f931ead6733547bb237ce06cddf96357f1b66b"><div class="ttname"><a href="namespacetvm_1_1tir.html#a9ae244600a5e56c4adc9faf6d88f931ead6733547bb237ce06cddf96357f1b66b">tvm::tir::ScheduleErrorRenderLevel::kDetail</a></div><div class="ttdoc">Render a detailed error message. </div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="index__map_8h_html"><div class="ttname"><a href="index__map_8h.html">index_map.h</a></div><div class="ttdoc">Defines a remapping of buffer indices. </div></div>
<div class="ttc" id="classtvm_1_1support_1_1LinearCongruentialEngine_html_a4d3a3a94a3f3d2dfab4b5ccb1a7e97de"><div class="ttname"><a href="classtvm_1_1support_1_1LinearCongruentialEngine.html#a4d3a3a94a3f3d2dfab4b5ccb1a7e97de">tvm::support::LinearCongruentialEngine::TRandState</a></div><div class="ttdeci">int64_t TRandState</div><div class="ttdef"><b>Definition:</b> random_engine.h:46</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
diff --git a/docs/reference/api/doxygen/trace_8h_source.html b/docs/reference/api/doxygen/trace_8h_source.html
index 92d13f7d2b..afc62476b8 100644
--- a/docs/reference/api/doxygen/trace_8h_source.html
+++ b/docs/reference/api/doxygen/trace_8h_source.html
@@ -76,7 +76,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_html_a75918aeef1136f9d6308556902d5bcae"><div class="ttname"><a href="namespacetvm_1_1tir.html#a75918aeef1136f9d6308556902d5bcae">tvm::tir::FTraceDecisionProvider</a></div><div class="ttdeci">runtime::TypedPackedFunc< ObjectRef(const Instruction &inst, const Array< ObjectRef > &inputs, const Array< ObjectRef > &attrs, const Optional< ObjectRef > &decision)> FTraceDecisionProvider</div><div class="ttdoc">A cal [...]
<div class="ttc" id="instruction_8h_html"><div class="ttname"><a href="instruction_8h.html">instruction.h</a></div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Object_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></div><div class="ttdoc">base class of all object containers. </div><div class="ttdef"><b>Definition:</b> object.h:167</div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:736</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Schedule_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Schedule.html">tvm::tir::Schedule</a></div><div class="ttdoc">Managed reference to ScheduleNode. </div><div class="ttdef"><b>Definition:</b> schedule.h:738</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1TraceNode_html_ad6c859ed32b1e2ae076355eda37df0a2"><div class="ttname"><a href="classtvm_1_1tir_1_1TraceNode.html#ad6c859ed32b1e2ae076355eda37df0a2">tvm::tir::TraceNode::insts</a></div><div class="ttdeci">Array< Instruction > insts</div><div class="ttdoc">The instructions invoked so far in the program execution. </div><div class="ttdef"><b>Definition:</b> trace.h:61</div></div>
<div class="ttc" id="classtvm_1_1AttrVisitor_html"><div class="ttname"><a href="classtvm_1_1AttrVisitor.html">tvm::AttrVisitor</a></div><div class="ttdoc">Visitor class to get the attributes of an AST/IR node. The content is going to be called for each fie...</div><div class="ttdef"><b>Definition:</b> reflection.h:52</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1TraceNode_html_a764346045e536fa26b56c9e140de8e7b"><div class="ttname"><a href="classtvm_1_1tir_1_1TraceNode.html#a764346045e536fa26b56c9e140de8e7b">tvm::tir::TraceNode::ApplyToSchedule</a></div><div class="ttdeci">void ApplyToSchedule(Schedule sch, bool remove_postproc, FTraceDecisionProvider decision_provider=nullptr) const</div><div class="ttdoc">Apply the trace to a TensorIR schedule. </div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 6cd526ae9b..1add2a0e1c 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/tir.html b/docs/reference/api/python/tir.html
index 25ef22b78d..d70ba5c067 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -5824,7 +5824,7 @@ preserve the semantics of computation. Some example of schedules:
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.cache_inplace" title="tvm.tir.Schedule.cache_inplace"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cache_inplace</span></code></a>(block, read_buffer_index, ...)</p></td>
<td><p>Create blocks that reads & write a buffer region into a cache block.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.cache_index" title="tvm.tir.Schedule.cache_index"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cache_index</span></code></a>(block, buffer_index)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.Schedule.cache_index" title="tvm.tir.Schedule.cache_index"><code class="xref py py-obj docutils literal notranslate"><span class="pre">cache_index</span></code></a>(block, storage_scope[, cse_thresh])</p></td>
<td><p>Create a block to cache precomputed index for later use.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.Schedule.reindex" title="tvm.tir.Schedule.reindex"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reindex</span></code></a>(block, buffer)</p></td>
@@ -6793,14 +6793,16 @@ that is within the blocks read region.</p></li>
<dl class="py method">
<dt class="sig sig-object py" id="tvm.tir.Schedule.cache_index">
-<span class="sig-name descname"><span class="pre">cache_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><a class="reference external" href="https://docs.python.o [...]
+<span class="sig-name descname"><span class="pre">cache_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">tvm.tir.schedule.schedule.BlockRV</span><span class="p"><span class="pre">,</span> </span><a class="reference external" href="https://docs.python.o [...]
<dd><p>Create a block to cache precomputed index for later use.
if there is no index computation, keep unchanged.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>block</strong> (<em>Union</em><em>[</em><em>BlockRV</em><em>, </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.11)"><em>str</em></a><em>]</em>) – The target block operates on the target buffer.</p></li>
-<li><p><strong>buffer_index</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><em>int</em></a>) – The index of the target buffer in block’s read region</p></li>
+<li><p><strong>storage_scope</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.11)"><em>str</em></a>) – The storage scope of cached block.</p></li>
+<li><p><strong>cse_thresh</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><em>int</em></a>) – The repeat threshold that determines a common sub expr,
+default 0 means cache all index computation.</p></li>
</ul>
</dd>
<dt class="field-even">Returns</dt>
@@ -6825,7 +6827,7 @@ if there is no index computation, keep unchanged.</p>
<p>Create the schedule and cache_index:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">sch</span> <span class="o">=</span> <span class="n">tir</span><span class="o">.</span><span class="n">Schedule</span><span class="p">(</span><span class="n">resize</span><span class="p">)</span>
<span class="n">block_a</span> <span class="o">=</span> <span class="n">sch</span><span class="o">.</span><span class="n">get_block</span><span class="p">(</span><span class="s2">"A"</span><span class="p">)</span>
-<span class="n">sch</span><span class="o">.</span><span class="n">cache_index</span><span class="p">(</span><span class="n">block_a</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
+<span class="n">sch</span><span class="o">.</span><span class="n">cache_index</span><span class="p">(</span><span class="n">block_a</span><span class="p">,</span> <span class="s2">"global"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">sch</span><span class="o">.</span><span class="n">mod</span><span class="p">[</span><span class="s2">"main"</span><span class="p">]</span><span class="o">.</span><span class="n">script</span><span class="p">())</span>
</pre></div>
</div>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 1115707070..b8890629f6 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/6c2d485a0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 efc5a8a758..3ccadb3580 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/6c2d485a0/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 a373e77471..00398068cd 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/6c2d485a0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 79ed400577..2ddf998cfb 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/6c2d485a0/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 07941173b7..cec69b1c55 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/6c2d485a0/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 489ac4c338..9c8fec385e 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/6c2d485a0/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 3b5fa3c8cf..f1415272de 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/6c2d485a0/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 7c70323483..61a9f6b62a 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/6c2d485a0/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 23b43d500f..abe9ff85ac 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/6c2d485a0/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 4153d9519a..f6280c081d 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/6c2d485a0/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 a534fe8252..f42157cc72 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/6c2d485a0/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 71d55cd71d..765ccd0a67 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/6c2d485a0/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 428d4e30bf..8a66cd97e1 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/6c2d485a0/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 834769f59b..db13b83175 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/6c2d485a0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 70667fec2f..f65f0324d6 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/6c2d485a0/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/6c2d485a0/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 81dfcf1d6c..0a43d3619c 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/6c2d485a0/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 4de6e85e7c..4c30c4a1e0 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/6c2d485a0/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 fe4fb7708c..222ebb866e 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/6c2d485a0/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 127e3668db..01dc560fff 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/6c2d485a0/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 04f2c2c872..4c18f19c6f 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/6c2d485a0/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 895a1c7770..745f384040 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/6c2d485a0/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 655ad0a944..a4046bb7bb 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/6c2d485a0/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 5bc0586c1f..f36d4cc12a 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/6c2d485a0/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 632d5faeae..b0d51ee931 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/6c2d485a0/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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/6c2d485a0/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e36ae331/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 2d2f4276ed..023f2da989 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 c65026ed83..d6941d3d24 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:29.175</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:30.597</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:29.169</p></td>
+<td><p>00:30.590</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 dd63d0ad76..837fec1048 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ 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 30.69s!
+resnet18_v1 inference graph built in 31.73s!
</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 6cceb042ed..2ca5bdb9bb 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 21.09s!
+yolov3-tiny inference graph built in 21.78s!
</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 6d8ed16aa2..e91119c647 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:35.112</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:37.233</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -348,12 +348,12 @@
<col style="width: 7%" />
</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>00:47.673</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
+<td><p>00:48.654</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:47.439</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
+<td><p>00:48.579</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 09447c9d6a..0cb41cbcba 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.115</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.332</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.666</p></td>
+<td><p>00:02.829</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>00:00.448</p></td>
+<td><p>00:00.503</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 1e5cbb1767..15ceef0e30 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.786</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.872</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.413</p></td>
+<td><p>00:00.457</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>00:00.373</p></td>
+<td><p>00:00.415</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 ac66b8993d..6fc16e94ef 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -492,9 +492,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -569,7 +566,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.538 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.021 ms
</pre></div>
</div>
</div>
@@ -643,7 +640,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.420 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.223 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index a20cd48ad5..bc4b87e58e 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ 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: 4.18/4.18 result: MeasureResult(costs=(0.06415541500000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.287381649017334, timestamp=1674183947.8544009) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-No: 2 GFLOPS: 2.70/4.18 result: MeasureResult(costs=(0.099422066,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8374905586242676, timestamp=1674183949.698981) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
-No: 3 GFLOPS: 8.37/8.37 result: MeasureResult(costs=(0.032066305,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7405209541320801, timestamp=1674183951.2165217) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
-No: 4 GFLOPS: 3.71/8.37 result: MeasureResult(costs=(0.07238791139999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3979723453521729, timestamp=1674183953.3796506) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
-No: 5 GFLOPS: 10.89/10.89 result: MeasureResult(costs=(0.0246521962,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6746640205383301, timestamp=1674183954.9166691) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
-No: 6 GFLOPS: 1.77/10.89 result: MeasureResult(costs=(0.1514064862,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.660912036895752, timestamp=1674183957.5901525) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
-No: 7 GFLOPS: 1.33/10.89 result: MeasureResult(costs=(0.20251314800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4556992053985596, timestamp=1674183961.0785851) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
-No: 8 GFLOPS: 9.18/10.89 result: MeasureResult(costs=(0.029232778999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6821742057800293, timestamp=1674183961.7943165) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
-No: 9 GFLOPS: 13.50/13.50 result: MeasureResult(costs=(0.019883790800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5237207412719727, timestamp=1674183962.4325068) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
-No: 10 GFLOPS: 1.78/13.50 result: MeasureResult(costs=(0.1507603704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.611154317855835, timestamp=1674183965.0960453) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 1 GFLOPS: 12.49/12.49 result: MeasureResult(costs=(0.0214892088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5937304496765137, timestamp=1674207344.7230031) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+No: 2 GFLOPS: 12.93/12.93 result: MeasureResult(costs=(0.0207669992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5739247798919678, timestamp=1674207346.1109023) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+No: 3 GFLOPS: 11.78/12.93 result: MeasureResult(costs=(0.022784174799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6616606712341309, timestamp=1674207347.535165) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+No: 4 GFLOPS: 12.61/12.93 result: MeasureResult(costs=(0.0212889474,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6334853172302246, timestamp=1674207348.135068) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+No: 5 GFLOPS: 4.14/12.93 result: MeasureResult(costs=(0.0648186526,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2923367023468018, timestamp=1674207349.6181529) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
+No: 6 GFLOPS: 2.24/12.93 result: MeasureResult(costs=(0.1199507176,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1554558277130127, timestamp=1674207351.7927608) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+No: 7 GFLOPS: 12.46/12.93 result: MeasureResult(costs=(0.0215484072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5837976932525635, timestamp=1674207353.1999807) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 8 GFLOPS: 12.09/12.93 result: MeasureResult(costs=(0.0221962052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6870126724243164, timestamp=1674207353.8154304) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
+No: 9 GFLOPS: 3.85/12.93 result: MeasureResult(costs=(0.06976133640000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3460557460784912, timestamp=1674207355.2814348) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+No: 10 GFLOPS: 12.78/12.93 result: MeasureResult(costs=(0.021006779,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5583662986755371, timestamp=1674207355.8758848) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
</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 22f9b59e82..05c11f2451 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ 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': 477.48544495999687, 'median': 477.1313110499932, 'std': 1.163654270518335}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 514.3162037599905, 'median': 514.0795248999893, 'std': 2.380002958562946}
</pre></div>
</div>
</div>
@@ -710,177 +710,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 15.30/ 18.71 GFLOPS | Progress: (4/20) | 7.85 s
-[Task 1/25] Current/Best: 12.14/ 18.71 GFLOPS | Progress: (8/20) | 11.20 s
-[Task 1/25] Current/Best: 6.83/ 23.82 GFLOPS | Progress: (12/20) | 14.40 s
-[Task 1/25] Current/Best: 16.58/ 23.82 GFLOPS | Progress: (16/20) | 17.92 s
-[Task 1/25] Current/Best: 9.74/ 23.82 GFLOPS | Progress: (20/20) | 20.11 s Done.
+[Task 1/25] Current/Best: 19.29/ 19.29 GFLOPS | Progress: (4/20) | 7.56 s
+[Task 1/25] Current/Best: 18.49/ 19.29 GFLOPS | Progress: (8/20) | 10.65 s
+[Task 1/25] Current/Best: 14.25/ 19.29 GFLOPS | Progress: (12/20) | 13.05 s
+[Task 1/25] Current/Best: 9.48/ 19.29 GFLOPS | Progress: (16/20) | 16.38 s
+[Task 1/25] Current/Best: 10.72/ 22.48 GFLOPS | Progress: (20/20) | 18.81 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.60/ 14.27 GFLOPS | Progress: (4/20) | 3.90 s
-[Task 2/25] Current/Best: 6.61/ 19.78 GFLOPS | Progress: (8/20) | 5.90 s
-[Task 2/25] Current/Best: 11.01/ 19.78 GFLOPS | Progress: (12/20) | 7.84 s
-[Task 2/25] Current/Best: 6.19/ 19.78 GFLOPS | Progress: (16/20) | 10.69 s
-[Task 2/25] Current/Best: 14.99/ 19.92 GFLOPS | Progress: (20/20) | 11.99 s Done.
+[Task 2/25] Current/Best: 5.67/ 14.05 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 2/25] Current/Best: 5.59/ 15.44 GFLOPS | Progress: (8/20) | 6.17 s
+[Task 2/25] Current/Best: 13.89/ 17.40 GFLOPS | Progress: (12/20) | 8.09 s
+[Task 2/25] Current/Best: 11.54/ 17.40 GFLOPS | Progress: (16/20) | 10.20 s
+[Task 2/25] Current/Best: 18.11/ 20.80 GFLOPS | Progress: (20/20) | 11.75 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 15.85/ 18.87 GFLOPS | Progress: (4/20) | 4.02 s
-[Task 3/25] Current/Best: 18.06/ 18.87 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 3/25] Current/Best: 11.32/ 18.87 GFLOPS | Progress: (12/20) | 8.83 s
-[Task 3/25] Current/Best: 7.72/ 21.24 GFLOPS | Progress: (16/20) | 11.17 s
-[Task 3/25] Current/Best: 9.67/ 21.24 GFLOPS | Progress: (20/20) | 14.17 s Done.
+[Task 3/25] Current/Best: 12.87/ 17.53 GFLOPS | Progress: (4/20) | 5.43 s
+[Task 3/25] Current/Best: 7.09/ 19.21 GFLOPS | Progress: (8/20) | 7.92 s
+[Task 3/25] Current/Best: 17.15/ 19.21 GFLOPS | Progress: (12/20) | 10.10 s
+[Task 3/25] Current/Best: 14.24/ 19.64 GFLOPS | Progress: (16/20) | 12.52 s
+[Task 3/25] Current/Best: 6.61/ 22.40 GFLOPS | Progress: (20/20) | 15.34 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 13.41/ 16.65 GFLOPS | Progress: (4/20) | 6.52 s
-[Task 4/25] Current/Best: 14.24/ 16.65 GFLOPS | Progress: (8/20) | 8.66 s
-[Task 4/25] Current/Best: 18.32/ 18.32 GFLOPS | Progress: (12/20) | 10.77 s
-[Task 4/25] Current/Best: 11.23/ 18.32 GFLOPS | Progress: (16/20) | 13.68 s
-[Task 4/25] Current/Best: 14.60/ 18.47 GFLOPS | Progress: (20/20) | 15.37 s Done.
+[Task 4/25] Current/Best: 6.13/ 15.63 GFLOPS | Progress: (4/20) | 4.03 s
+[Task 4/25] Current/Best: 13.02/ 16.84 GFLOPS | Progress: (8/20) | 9.08 s
+[Task 4/25] Current/Best: 8.04/ 17.08 GFLOPS | Progress: (12/20) | 11.96 s
+[Task 4/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (16/20) | 13.89 s
+[Task 4/25] Current/Best: 2.08/ 21.29 GFLOPS | Progress: (20/20) | 17.52 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 6.07/ 16.00 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 5/25] Current/Best: 16.29/ 23.13 GFLOPS | Progress: (8/20) | 5.62 s
-[Task 5/25] Current/Best: 14.06/ 23.13 GFLOPS | Progress: (12/20) | 7.58 s
-[Task 5/25] Current/Best: 12.15/ 23.13 GFLOPS | Progress: (16/20) | 9.75 s
-[Task 5/25] Current/Best: 5.66/ 23.13 GFLOPS | Progress: (20/20) | 11.70 s Done.
+[Task 5/25] Current/Best: 5.22/ 16.40 GFLOPS | Progress: (4/20) | 4.36 s
+[Task 5/25] Current/Best: 3.72/ 16.40 GFLOPS | Progress: (8/20) | 6.55 s
+[Task 5/25] Current/Best: 13.44/ 17.12 GFLOPS | Progress: (12/20) | 9.29 s
+[Task 5/25] Current/Best: 11.64/ 20.07 GFLOPS | Progress: (16/20) | 11.22 s
+[Task 5/25] Current/Best: 12.75/ 20.07 GFLOPS | Progress: (20/20) | 13.58 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.17/ 23.11 GFLOPS | Progress: (4/20) | 4.11 s
-[Task 6/25] Current/Best: 13.31/ 23.11 GFLOPS | Progress: (8/20) | 6.51 s
-[Task 6/25] Current/Best: 15.13/ 23.11 GFLOPS | Progress: (12/20) | 9.36 s
-[Task 6/25] Current/Best: 4.13/ 23.11 GFLOPS | Progress: (16/20) | 13.20 s
-[Task 6/25] Current/Best: 2.81/ 23.11 GFLOPS | Progress: (20/20) | 17.23 s Done.
+[Task 6/25] Current/Best: 14.76/ 19.40 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 6/25] Current/Best: 4.16/ 19.40 GFLOPS | Progress: (8/20) | 7.24 s
+[Task 6/25] Current/Best: 18.78/ 19.40 GFLOPS | Progress: (12/20) | 10.46 s
+[Task 6/25] Current/Best: 6.21/ 19.40 GFLOPS | Progress: (16/20) | 13.47 s
+[Task 6/25] Current/Best: 6.61/ 19.40 GFLOPS | Progress: (20/20) | 16.04 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 15.43/ 18.22 GFLOPS | Progress: (4/20) | 4.48 s
-[Task 7/25] Current/Best: 13.84/ 18.22 GFLOPS | Progress: (8/20) | 6.79 s
-[Task 7/25] Current/Best: 12.23/ 20.78 GFLOPS | Progress: (12/20) | 8.84 s
-[Task 7/25] Current/Best: 23.29/ 23.29 GFLOPS | Progress: (16/20) | 10.72 s
-[Task 7/25] Current/Best: 9.72/ 23.29 GFLOPS | Progress: (20/20) | 12.77 s Done.
+[Task 7/25] Current/Best: 11.67/ 20.90 GFLOPS | Progress: (4/20) | 5.32 s
+[Task 7/25] Current/Best: 12.08/ 20.90 GFLOPS | Progress: (8/20) | 8.23 s
+[Task 7/25] Current/Best: 9.08/ 20.90 GFLOPS | Progress: (12/20) | 10.40 s
+[Task 7/25] Current/Best: 17.61/ 20.90 GFLOPS | Progress: (16/20) | 12.38 s
+[Task 7/25] Current/Best: 18.28/ 20.90 GFLOPS | Progress: (20/20) | 15.59 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 3.62/ 11.80 GFLOPS | Progress: (4/20) | 11.38 s
-[Task 8/25] Current/Best: 7.33/ 12.44 GFLOPS | Progress: (8/20) | 16.47 s
-[Task 8/25] Current/Best: 5.14/ 13.67 GFLOPS | Progress: (12/20) | 21.18 s
-[Task 8/25] Current/Best: 10.57/ 13.67 GFLOPS | Progress: (16/20) | 26.95 s
-[Task 8/25] Current/Best: 2.81/ 18.58 GFLOPS | Progress: (20/20) | 34.54 s Done.
+[Task 8/25] Current/Best: 8.21/ 11.12 GFLOPS | Progress: (4/20) | 4.54 s
+[Task 8/25] Current/Best: 4.00/ 16.99 GFLOPS | Progress: (8/20) | 7.27 s
+[Task 8/25] Current/Best: 8.20/ 16.99 GFLOPS | Progress: (12/20) | 11.21 s
+[Task 8/25] Current/Best: 14.13/ 16.99 GFLOPS | Progress: (16/20) | 14.43 s
+[Task 8/25] Current/Best: 17.81/ 17.81 GFLOPS | Progress: (20/20) | 16.88 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 11.01/ 13.89 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 9/25] Current/Best: 12.57/ 22.75 GFLOPS | Progress: (8/20) | 16.29 s
-[Task 9/25] Current/Best: 16.27/ 22.75 GFLOPS | Progress: (12/20) | 27.37 s
-[Task 9/25] Current/Best: 16.64/ 22.75 GFLOPS | Progress: (16/20) | 30.03 s
-[Task 9/25] Current/Best: 13.22/ 22.75 GFLOPS | Progress: (20/20) | 32.51 s
+[Task 9/25] Current/Best: 13.47/ 16.30 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 9/25] Current/Best: 13.72/ 16.30 GFLOPS | Progress: (8/20) | 9.85 s
+[Task 9/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (12/20) | 12.90 s
+[Task 9/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (16/20) | 14.82 s
+[Task 9/25] Current/Best: 17.76/ 19.68 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 7.16/ 12.91 GFLOPS | Progress: (4/20) | 3.86 s
-[Task 10/25] Current/Best: 9.49/ 13.08 GFLOPS | Progress: (8/20) | 6.51 s
-[Task 10/25] Current/Best: 9.40/ 22.06 GFLOPS | Progress: (12/20) | 8.95 s
-[Task 10/25] Current/Best: 14.26/ 22.06 GFLOPS | Progress: (16/20) | 11.30 s
-[Task 10/25] Current/Best: 11.07/ 22.57 GFLOPS | Progress: (20/20) | 13.49 s Done.
+[Task 10/25] Current/Best: 10.62/ 22.30 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 10/25] Current/Best: 3.13/ 22.66 GFLOPS | Progress: (8/20) | 5.73 s
+[Task 10/25] Current/Best: 14.39/ 22.66 GFLOPS | Progress: (12/20) | 8.20 s
+[Task 10/25] Current/Best: 4.73/ 22.66 GFLOPS | Progress: (16/20) | 11.34 s
+[Task 10/25] Current/Best: 14.63/ 22.66 GFLOPS | Progress: (20/20) | 14.94 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 17.02/ 17.02 GFLOPS | Progress: (4/20) | 4.13 s
-[Task 11/25] Current/Best: 10.07/ 22.61 GFLOPS | Progress: (8/20) | 6.58 s
-[Task 11/25] Current/Best: 16.71/ 22.61 GFLOPS | Progress: (12/20) | 10.58 s
-[Task 11/25] Current/Best: 19.73/ 22.61 GFLOPS | Progress: (16/20) | 12.70 s
-[Task 11/25] Current/Best: 19.42/ 22.61 GFLOPS | Progress: (20/20) | 15.44 s Done.
+[Task 11/25] Current/Best: 14.53/ 14.53 GFLOPS | Progress: (4/20) | 4.63 s
+[Task 11/25] Current/Best: 5.62/ 16.32 GFLOPS | Progress: (8/20) | 7.00 s
+[Task 11/25] Current/Best: 12.30/ 18.08 GFLOPS | Progress: (12/20) | 9.29 s
+[Task 11/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (16/20) | 11.76 s
+[Task 11/25] Current/Best: 9.78/ 18.53 GFLOPS | Progress: (20/20) | 15.13 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 16.42/ 17.67 GFLOPS | Progress: (4/20) | 3.98 s
-[Task 12/25] Current/Best: 13.24/ 18.53 GFLOPS | Progress: (8/20) | 7.47 s
-[Task 12/25] Current/Best: 11.77/ 18.53 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 12/25] Current/Best: 4.57/ 18.53 GFLOPS | Progress: (16/20) | 12.81 s
-[Task 12/25] Current/Best: 5.08/ 20.63 GFLOPS | Progress: (20/20) | 15.29 s Done.
+[Task 12/25] Current/Best: 9.51/ 16.09 GFLOPS | Progress: (4/20) | 4.57 s
+[Task 12/25] Current/Best: 1.61/ 16.09 GFLOPS | Progress: (8/20) | 8.20 s
+[Task 12/25] Current/Best: 10.58/ 16.09 GFLOPS | Progress: (12/20) | 16.33 s
+[Task 12/25] Current/Best: 9.71/ 16.71 GFLOPS | Progress: (16/20) | 19.53 s
+[Task 12/25] Current/Best: 12.98/ 16.71 GFLOPS | Progress: (20/20) | 22.54 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 9.86/ 20.33 GFLOPS | Progress: (4/20) | 4.75 s
-[Task 13/25] Current/Best: 21.82/ 21.82 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 13/25] Current/Best: 16.97/ 21.82 GFLOPS | Progress: (12/20) | 11.23 s
-[Task 13/25] Current/Best: 12.25/ 23.21 GFLOPS | Progress: (16/20) | 13.92 s
-[Task 13/25] Current/Best: 12.19/ 23.21 GFLOPS | Progress: (20/20) | 16.11 s Done.
+[Task 13/25] Current/Best: 11.67/ 18.36 GFLOPS | Progress: (4/20) | 4.59 s
+[Task 13/25] Current/Best: 9.87/ 18.36 GFLOPS | Progress: (8/20) | 8.99 s
+[Task 13/25] Current/Best: 11.88/ 18.36 GFLOPS | Progress: (12/20) | 13.31 s
+[Task 13/25] Current/Best: 9.34/ 20.57 GFLOPS | Progress: (16/20) | 16.63 s
+[Task 13/25] Current/Best: 5.62/ 21.53 GFLOPS | Progress: (20/20) | 19.94 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.29/ 17.68 GFLOPS | Progress: (4/20) | 3.95 s
-[Task 14/25] Current/Best: 8.59/ 17.68 GFLOPS | Progress: (8/20) | 6.34 s
-[Task 14/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (12/20) | 9.78 s Done.
-
-[Task 14/25] Current/Best: 10.30/ 22.75 GFLOPS | Progress: (16/20) | 12.37 s
-[Task 14/25] Current/Best: 4.55/ 22.75 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
+[Task 14/25] Current/Best: 9.30/ 15.72 GFLOPS | Progress: (4/20) | 7.50 s
+[Task 14/25] Current/Best: 7.57/ 15.72 GFLOPS | Progress: (8/20) | 10.25 s
+[Task 14/25] Current/Best: 6.24/ 18.13 GFLOPS | Progress: (12/20) | 13.56 s
+[Task 14/25] Current/Best: 3.05/ 18.13 GFLOPS | Progress: (16/20) | 17.87 s
+[Task 14/25] Current/Best: 6.14/ 18.13 GFLOPS | Progress: (20/20) | 21.00 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 8.87/ 12.81 GFLOPS | Progress: (4/20) | 4.85 s
-[Task 15/25] Current/Best: 15.48/ 18.88 GFLOPS | Progress: (8/20) | 6.43 s
-[Task 15/25] Current/Best: 13.28/ 18.88 GFLOPS | Progress: (12/20) | 9.06 s
-[Task 15/25] Current/Best: 15.18/ 20.23 GFLOPS | Progress: (16/20) | 10.78 s
-[Task 15/25] Current/Best: 10.95/ 20.23 GFLOPS | Progress: (20/20) | 13.09 s
+[Task 15/25] Current/Best: 10.70/ 18.81 GFLOPS | Progress: (4/20) | 6.52 s Done.
+
+[Task 15/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (8/20) | 7.97 s
+[Task 15/25] Current/Best: 23.32/ 23.32 GFLOPS | Progress: (12/20) | 9.79 s
+[Task 15/25] Current/Best: 19.94/ 23.32 GFLOPS | Progress: (16/20) | 11.95 s
+[Task 15/25] Current/Best: 11.46/ 23.32 GFLOPS | Progress: (20/20) | 15.58 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 7.67/ 19.12 GFLOPS | Progress: (4/20) | 4.20 s
-[Task 16/25] Current/Best: 17.02/ 19.12 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 16/25] Current/Best: 14.04/ 19.12 GFLOPS | Progress: (12/20) | 10.29 s
-[Task 16/25] Current/Best: 18.09/ 19.12 GFLOPS | Progress: (16/20) | 11.79 s
-[Task 16/25] Current/Best: 16.36/ 19.12 GFLOPS | Progress: (20/20) | 15.41 s Done.
+[Task 16/25] Current/Best: 14.44/ 19.10 GFLOPS | Progress: (4/20) | 3.73 s
+[Task 16/25] Current/Best: 3.04/ 19.10 GFLOPS | Progress: (8/20) | 7.31 s
+[Task 16/25] Current/Best: 7.11/ 19.10 GFLOPS | Progress: (12/20) | 9.20 s
+[Task 16/25] Current/Best: 12.23/ 19.10 GFLOPS | Progress: (16/20) | 12.06 s
+[Task 16/25] Current/Best: 13.41/ 19.10 GFLOPS | Progress: (20/20) | 14.06 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 6.22/ 20.51 GFLOPS | Progress: (4/20) | 4.28 s
-[Task 17/25] Current/Best: 12.27/ 20.51 GFLOPS | Progress: (8/20) | 7.48 s
-[Task 17/25] Current/Best: 15.02/ 20.51 GFLOPS | Progress: (12/20) | 9.84 s
-[Task 17/25] Current/Best: 16.16/ 20.51 GFLOPS | Progress: (16/20) | 12.51 s
-[Task 17/25] Current/Best: 16.17/ 20.51 GFLOPS | Progress: (20/20) | 15.24 s Done.
+[Task 17/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (4/20) | 4.21 s
+[Task 17/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (8/20) | 8.21 s
+[Task 17/25] Current/Best: 11.50/ 20.03 GFLOPS | Progress: (12/20) | 10.78 s
+[Task 17/25] Current/Best: 16.63/ 20.03 GFLOPS | Progress: (16/20) | 14.08 s
+[Task 17/25] Current/Best: 8.55/ 21.18 GFLOPS | Progress: (20/20) | 16.68 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 17.44/ 17.44 GFLOPS | Progress: (4/20) | 6.42 s
-[Task 18/25] Current/Best: 12.29/ 19.96 GFLOPS | Progress: (8/20) | 9.49 s
-[Task 18/25] Current/Best: 20.27/ 20.27 GFLOPS | Progress: (12/20) | 11.30 s
-[Task 18/25] Current/Best: 11.19/ 21.02 GFLOPS | Progress: (16/20) | 17.84 s
-[Task 18/25] Current/Best: 7.88/ 21.02 GFLOPS | Progress: (20/20) | 21.90 s Done.
+[Task 18/25] Current/Best: 17.45/ 17.53 GFLOPS | Progress: (4/20) | 3.96 s
+[Task 18/25] Current/Best: 15.93/ 17.53 GFLOPS | Progress: (8/20) | 7.26 s
+[Task 18/25] Current/Best: 14.98/ 17.53 GFLOPS | Progress: (12/20) | 11.47 s
+[Task 18/25] Current/Best: 7.74/ 19.04 GFLOPS | Progress: (16/20) | 13.75 s
+[Task 18/25] Current/Best: 12.20/ 21.34 GFLOPS | Progress: (20/20) | 15.90 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (4/20) | 5.47 s
-[Task 19/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (8/20) | 9.26 s
-[Task 19/25] Current/Best: 18.07/ 21.10 GFLOPS | Progress: (12/20) | 12.50 s
-[Task 19/25] Current/Best: 6.11/ 21.10 GFLOPS | Progress: (16/20) | 16.33 s
-[Task 19/25] Current/Best: 20.04/ 21.10 GFLOPS | Progress: (20/20) | 19.24 s Done.
+[Task 19/25] Current/Best: 12.75/ 17.58 GFLOPS | Progress: (4/20) | 4.33 s
+[Task 19/25] Current/Best: 17.11/ 17.58 GFLOPS | Progress: (8/20) | 9.34 s
+[Task 19/25] Current/Best: 17.45/ 17.58 GFLOPS | Progress: (12/20) | 13.13 s
+[Task 19/25] Current/Best: 10.53/ 18.06 GFLOPS | Progress: (16/20) | 15.91 s
+[Task 19/25] Current/Best: 9.45/ 19.98 GFLOPS | Progress: (20/20) | 20.66 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 18.49/ 20.04 GFLOPS | Progress: (4/20) | 4.58 s
-[Task 20/25] Current/Best: 16.62/ 20.04 GFLOPS | Progress: (8/20) | 7.52 s
-[Task 20/25] Current/Best: 6.20/ 20.04 GFLOPS | Progress: (12/20) | 9.30 s
-[Task 20/25] Current/Best: 8.57/ 20.04 GFLOPS | Progress: (16/20) | 11.33 s Done.
-
-[Task 20/25] Current/Best: 11.29/ 20.06 GFLOPS | Progress: (20/20) | 14.35 s
+[Task 20/25] Current/Best: 11.14/ 11.14 GFLOPS | Progress: (4/20) | 4.74 s
+[Task 20/25] Current/Best: 11.78/ 18.45 GFLOPS | Progress: (8/20) | 7.65 s
+[Task 20/25] Current/Best: 8.73/ 19.92 GFLOPS | Progress: (12/20) | 11.77 s
+[Task 20/25] Current/Best: 2.67/ 19.92 GFLOPS | Progress: (16/20) | 14.54 s
+[Task 20/25] Current/Best: 18.92/ 19.92 GFLOPS | Progress: (20/20) | 16.80 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 9.45/ 18.85 GFLOPS | Progress: (4/20) | 3.79 s
-[Task 21/25] Current/Best: 22.47/ 22.47 GFLOPS | Progress: (8/20) | 5.72 s
-[Task 21/25] Current/Best: 10.95/ 22.47 GFLOPS | Progress: (12/20) | 8.91 s
-[Task 21/25] Current/Best: 6.93/ 22.47 GFLOPS | Progress: (16/20) | 11.23 s
-[Task 21/25] Current/Best: 17.10/ 22.47 GFLOPS | Progress: (20/20) | 12.82 s
+[Task 21/25] Current/Best: 7.52/ 18.95 GFLOPS | Progress: (4/20) | 4.74 s
+[Task 21/25] Current/Best: 7.01/ 18.95 GFLOPS | Progress: (8/20) | 7.07 s
+[Task 21/25] Current/Best: 15.41/ 21.33 GFLOPS | Progress: (12/20) | 8.70 s
+[Task 21/25] Current/Best: 19.22/ 21.33 GFLOPS | Progress: (16/20) | 10.31 s
+[Task 21/25] Current/Best: 11.81/ 21.33 GFLOPS | Progress: (20/20) | 13.55 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 15.99 GFLOPS | Progress: (4/20) | 5.03 s
-[Task 22/25] Current/Best: 12.40/ 15.99 GFLOPS | Progress: (8/20) | 7.28 s
-[Task 22/25] Current/Best: 16.05/ 16.05 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 22/25] Current/Best: 16.57/ 18.99 GFLOPS | Progress: (16/20) | 11.17 s
-[Task 22/25] Current/Best: 11.23/ 18.99 GFLOPS | Progress: (20/20) | 13.02 s Done.
+[Task 22/25] Current/Best: 5.37/ 18.80 GFLOPS | Progress: (4/20) | 5.27 s
+[Task 22/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (8/20) | 7.89 s
+[Task 22/25] Current/Best: 8.21/ 20.75 GFLOPS | Progress: (12/20) | 9.64 s
+[Task 22/25] Current/Best: 10.06/ 20.75 GFLOPS | Progress: (16/20) | 14.84 s
+[Task 22/25] Current/Best: 10.64/ 20.75 GFLOPS | Progress: (20/20) | 16.46 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 8.38/ 18.13 GFLOPS | Progress: (4/20) | 5.09 s
-[Task 23/25] Current/Best: 12.32/ 18.98 GFLOPS | Progress: (8/20) | 8.03 s
-[Task 23/25] Current/Best: 11.99/ 18.98 GFLOPS | Progress: (12/20) | 10.97 s
-[Task 23/25] Current/Best: 22.52/ 22.52 GFLOPS | Progress: (16/20) | 13.97 s
-[Task 23/25] Current/Best: 14.05/ 22.52 GFLOPS | Progress: (20/20) | 16.69 s Done.
+[Task 23/25] Current/Best: 12.32/ 19.53 GFLOPS | Progress: (4/20) | 4.51 s
+[Task 23/25] Current/Best: 22.72/ 23.79 GFLOPS | Progress: (8/20) | 7.18 s
+[Task 23/25] Current/Best: 20.43/ 23.79 GFLOPS | Progress: (12/20) | 10.07 s
+[Task 23/25] Current/Best: 3.68/ 23.79 GFLOPS | Progress: (16/20) | 13.37 s
+[Task 23/25] Current/Best: 9.54/ 23.79 GFLOPS | Progress: (20/20) | 17.44 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.61/ 9.73 GFLOPS | Progress: (4/20) | 12.76 s
-[Task 24/25] Current/Best: 0.54/ 9.73 GFLOPS | Progress: (8/20) | 20.64 s
-[Task 24/25] Current/Best: 3.01/ 10.69 GFLOPS | Progress: (12/20) | 22.00 s
-[Task 24/25] Current/Best: 6.27/ 10.69 GFLOPS | Progress: (16/20) | 32.92 s Done.
-
-[Task 24/25] Current/Best: 3.29/ 10.69 GFLOPS | Progress: (20/20) | 44.62 s
+[Task 24/25] Current/Best: 2.92/ 3.13 GFLOPS | Progress: (4/20) | 12.79 s Done.
+ Done.
+ Done.
+
+[Task 24/25] Current/Best: 6.05/ 6.05 GFLOPS | Progress: (8/20) | 23.73 s
+[Task 24/25] Current/Best: 3.00/ 6.05 GFLOPS | Progress: (12/20) | 34.39 s
+[Task 24/25] Current/Best: 8.54/ 8.89 GFLOPS | Progress: (16/20) | 45.04 s
+[Task 24/25] Current/Best: 3.18/ 10.18 GFLOPS | Progress: (20/20) | 50.77 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 5.42/ 6.08 GFLOPS | Progress: (4/20) | 13.52 s
-[Task 25/25] Current/Best: 6.15/ 9.80 GFLOPS | Progress: (8/20) | 24.48 s
-[Task 25/25] Current/Best: 7.84/ 9.80 GFLOPS | Progress: (12/20) | 26.91 s
-[Task 25/25] Current/Best: 9.10/ 9.80 GFLOPS | Progress: (16/20) | 37.87 s
-[Task 25/25] Current/Best: 7.96/ 9.80 GFLOPS | Progress: (20/20) | 40.04 s
+[Task 25/25] Current/Best: 8.16/ 8.16 GFLOPS | Progress: (4/20) | 12.82 s
+[Task 25/25] Current/Best: 5.20/ 8.16 GFLOPS | Progress: (8/20) | 23.77 s
+[Task 25/25] Current/Best: 3.00/ 8.16 GFLOPS | Progress: (12/20) | 25.84 s
+[Task 25/25] Current/Best: 4.18/ 9.20 GFLOPS | Progress: (16/20) | 29.30 s
+[Task 25/25] Current/Best: 5.66/ 9.20 GFLOPS | Progress: (20/20) | 40.25 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -941,8 +942,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -979,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 413.88311280999915, 'median': 413.60596074999876, 'std': 1.6160087440403037}
-unoptimized: {'mean': 477.48544495999687, 'median': 477.1313110499932, 'std': 1.163654270518335}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 416.60222960998, 'median': 416.48454939995645, 'std': 1.852629075858513}
+unoptimized: {'mean': 514.3162037599905, 'median': 514.0795248999893, 'std': 2.380002958562946}
</pre></div>
</div>
</div>
@@ -994,7 +995,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 26.752 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 38.584 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 cdfcc1eb8c..cac82f6198 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ 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>1.308e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.337e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 16832e064c..fc314d2866 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -506,7 +506,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x22bcd1f0)), stage(b, placeholder(b, 0x21d8d400)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x19f394e0)), stage(b, placeholder(b, 0xd5ca1d0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 1821593099..fc975d5857 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:55.935</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:04.335</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:26.752</p></td>
+<td><p>11:38.584</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:30.420</p></td>
+<td><p>01:30.223</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:58.900</p></td>
+<td><p>01:02.089</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>00:34.825</p></td>
+<td><p>00:35.627</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>00:22.680</p></td>
+<td><p>00:16.188</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.379</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.827</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.819</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.612</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>00:00.159</p></td>
+<td><p>00:00.183</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
@@ -388,11 +388,11 @@
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="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>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d5085f812f..4e8a9f6785 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -549,7 +549,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
naive: 0.000007
</pre></div>
</div>
@@ -605,7 +605,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000011
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000012
</pre></div>
</div>
</div>
@@ -644,7 +644,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000046
@I.ir_module
class Module:
@T.prim_func
@@ -681,10 +681,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.256909998432093e-06 1.0
- naive 6.6563999999999995e-06 0.9172499040828896
-parallel 1.126e-05 1.551624589864392
- vector 2.45527e-05 3.3833546241175356
+ numpy 7.6238400106376505e-06 1.0
+ naive 6.6943e-06 0.8780745648727346
+parallel 1.17693e-05 1.5437496043434975
+ vector 4.62778e-05 6.070143121501492
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1000,7 +1000,7 @@ 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: 0.017994
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018552
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1041,7 +1041,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.258496
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.458278
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1102,7 +1102,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.297530
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.313893
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1148,7 +1148,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.330118
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.349831
@I.ir_module
class Module:
@T.prim_func
@@ -1194,7 +1194,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119767
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.123109
@I.ir_module
class Module:
@T.prim_func
@@ -1261,7 +1261,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109910
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109124
@I.ir_module
class Module:
@T.prim_func
@@ -1324,7 +1324,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110722
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111100
@I.ir_module
class Module:
@T.prim_func
@@ -1378,7 +1378,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146423
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.148550
@I.ir_module
class Module:
@T.prim_func
@@ -1428,13 +1428,13 @@ 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 3.2584962005 1.0
- blocking 0.297529924 0.09130896760117305
- vectorization 0.3301182801 0.10131000921509282
-loop permutation 0.11976749480000001 0.03675545019252202
- array packing 0.1099097601 0.03373020968480334
- block caching 0.11072204810000001 0.033979492774308055
- parallelization 0.1464230078 0.04493576140353704
+ none 3.4582784937 1.0
+ blocking 0.3138928144 0.09076562658901631
+ vectorization 0.3498312842 0.10115763806682808
+loop permutation 0.1231090829 0.03559837159565655
+ array packing 0.1091240935 0.03155445511366221
+ block caching 0.1110999699 0.03212580192786456
+ parallelization 0.1485501092 0.042954929590146095
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1466,6 +1466,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.089 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>