You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/03/20 06:25:16 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@fc2a9e50afd03adba9839b94ef6d10145be5fc37)
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 570bcbb98e deploying docs (apache/tvm@fc2a9e50afd03adba9839b94ef6d10145be5fc37)
570bcbb98e is described below
commit 570bcbb98e2f2cdfcf57427f28066dac5f0004cb
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Mar 20 06:25:10 2023 +0000
deploying docs (apache/tvm@fc2a9e50afd03adba9839b94ef6d10145be5fc37)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 337291 -> 312563 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24331 -> 22858 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_model_on_adreno_tvmc.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 | 22 +-
.../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 | 271 ++++++++++++---------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 22 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 89 +++----
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 ++---
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 48 ++--
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 12 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_adreno_tvmc.html | 29 +--
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 50 ++--
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 ++-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../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 | 267 +++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 22 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 89 +++----
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
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 | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +--
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 ++---
docs/reference/api/typedoc/classes/memory.html | 34 +--
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +--
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 124 +++++-----
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 266 ++++++++++----------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 48 ++--
131 files changed, 1266 insertions(+), 1200 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index b0d90a1aba..793f3e36e6 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 029d81d2c2..94f0e4545f 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 d0c7db6f39..25163332be 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.698 seconds)
+ **Total running time of the script:** ( 1 minutes 20.335 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 805cfbfaa9..b35ce3d87e 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 972ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 956ms/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 ff388dc7c8..c17b447987 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.zip35c63c99-f7f4-4606-8467-222552f3b069 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip251b0ea1-bcf0-4833-9cbe-c6bf4f384760 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 28d6111ac1..82d5c21a88 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 56.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 60.2MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 64.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 64.8MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 69.7MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 68.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 49.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 56.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 54.6MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.3MB/s]
90%|######### | 37.5M/41.5M [00:00<00:00, 54.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 56.2MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 61c171e4a6..1140d6464a 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]
18%|#7 | 7.99M/44.7M [00:00<00:00, 72.1MB/s]
50%|####9 | 22.2M/44.7M [00:00<00:00, 114MB/s]
75%|#######4 | 33.4M/44.7M [00:00<00:00, 104MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 112MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 55.9MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 64.8MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 70.1MB/s]
87%|########6 | 38.8M/44.7M [00:00<00:00, 90.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 85.6MB/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 f12241b6bf..679f8d9e3e 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.871 seconds)
+ **Total running time of the script:** ( 1 minutes 23.848 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 b85c10a211..136777ef6b 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
=================
-**06:46.308** total execution time for **how_to_compile_models** files:
+**06:42.385** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:25.871 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:23.848 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:20.698 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:20.335 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:58.193 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:56.963 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.760 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.542 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.660 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.642 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.302 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.765 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.534 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.519 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.274 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.252 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.945 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.813 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.764 | 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 f03343c803..b22b2a42f0 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
@@ -637,7 +637,7 @@ 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)
- 2750.3303 2749.6866 2752.7384 2748.2985 1.6465
+ 2677.7677 2677.2289 2681.0580 2676.1151 1.5808
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
index c22fe83f9f..a8cba52c0f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
@@ -127,7 +127,7 @@ Make a Keras Resnet50 Model
.. code-block:: none
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
-
8192/102967424 [..............................] - ETA: 0s
8118272/102967424 [=>............................] - ETA: 0s
13099008/102967424 [==>...........................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
23412736/102967424 [=====>........................] - ETA: 0s
28278784/102967424 [=======>......................] - ETA: 0s
36749312/102967424 [=========>....................] - ETA: 0s
41713664/102967424 [===========>..................] - ETA: 0s
46718976/102967424 [============>.................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
55574528/102967424 [===============>..............] - ETA: 0s
56623104/102967424 [===============>..............] - ETA: 0s
66600960/102967424 [==================>...........] - ETA: 0s
68362240/102967424 [==================>...........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
84795392/102967424 [=======================>......] -
ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
98607104/102967424 [===========================>..] - ETA: 0s
102916096/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
25157632/102967424 [======>.......................] - ETA: 0s
28663808/102967424 [=======>......................] - ETA: 0s
33546240/102967424 [========>.....................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 0s
48578560/102967424 [=============>................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
55771136/102967424 [===============>..............] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] - ETA: 0s
72540160/102967424 [====================>.........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
82124800/102967424 [======================>.......] -
ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
100630528/102967424 [============================>.] - ETA: 0s
102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
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 e0449e4981..21e3ef7a67 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1432 16.0046 17.1164 15.9001 0.3423
+ 15.7724 15.7627 15.8659 15.6972 0.0532
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 b2bbf0fc30..876e674001 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 71.9MB/s]
10%|9 | 16.9M/170M [00:00<00:01, 83.8MB/s]
15%|#4 | 25.0M/170M [00:00<00:02, 72.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 58.1MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 62.0MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 61.4MB/s]
33%|###2 | 56.0M/170M [00:00<00:01, 66.8MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 60.3MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 65.4MB/s]
46%|####6 | 78.5M/170M [00:01<00:01, 64.4MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 62.5MB/s]
54%|#####4 | 92.4M/170M [00:01<00:01, 62.6MB/s]
58%|#####7 | 98.5M/170M [00:01<00:01, 56.1MB/s]
61%|######1 | 104M/170M [00:01<00:01, 56.1MB/s]
66%|######5 | 112M/170M [00:01<00:00, 62.3MB/s]
71%|####### | 120M/170M [00:01<00:00, 66.0MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 68.4MB/s]
80%|######## | 136M/170M [00:02<00:00, 71.1MB/s]
85%|########4 | 144M/170M [00:02<00:00, 74.7MB/s]
89%|########9 | 152M/170M [00:02<00:00, 66.6MB/s]
94%|#########4| 160M/170M [00:02<00:00, 59.6MB/s]
99%|#########8| 168M/170M [00:02<00:00, 65.5MB/s]
100%|##########| 170M/170M [00:02<00:00, 65.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 65.6MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 55.2MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 53.1MB/s]
18%|#7 | 30.3M/170M [00:00<00:03, 45.8MB/s]
20%|## | 34.8M/170M [00:00<00:03, 45.3MB/s]
27%|##6 | 45.2M/170M [00:00<00:02, 61.7MB/s]
30%|### | 51.5M/170M [00:00<00:02, 57.0MB/s]
34%|###3 | 57.3M/170M [00:01<00:02, 57.7MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 54.9MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 54.6MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 61.3MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 59.1MB/s]
54%|#####4 | 92.4M/170M [00:01<00:01, 60.4MB/s]
58%|#####7 | 98.3M/170M [00:01<00:01, 60.6MB/s]
61%|######1 | 104M/170M [00:02<00:01, 47.2MB/s]
66%|######5 | 112M/170M [00:02<00:01, 54.0MB/s]
71%|####### | 120M/170M [00:02<00:00, 57.5MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 56.6MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 59.5MB/s]
83%|########2 | 140M/170M [00:02<00:00, 57.7MB/s]
86%|########5 | 146M/170M [00:02<00:00, 57.8MB/s]
89%|########9 | 152M/170M [00:02<00:00, 46.1MB/s]
95%|#########4| 161M/170M [00:03<00:00, 56.0MB/s]
98%|#########8| 167M/170M [00:03<00:00, 49.7MB/s]
100%|##########| 170M/170M [00:03<00:00, 54.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 42.801 seconds)
+ **Total running time of the script:** ( 3 minutes 36.832 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 bb556d5e44..bb090a727c 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]
1%| | 120k/13.6M [00:00<00:13, 1.05MB/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 45.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 58.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 98.5MB/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)
- 90.3799 90.2302 96.6319 90.0786 0.6925
+ 90.3195 90.1863 92.1042 90.0481 0.3192
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.539 seconds)
+ **Total running time of the script:** ( 1 minutes 17.287 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 f54e34d9e0..7cd3bf4bed 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)
- 120.5675 120.5660 123.1183 119.6611 0.5511
+ 120.5631 120.5275 121.4506 119.9558 0.2801
@@ -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 35.964 seconds)
+ **Total running time of the script:** ( 2 minutes 31.193 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 8b97c743b5..9c3acb543b 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 33.635 seconds)
+ **Total running time of the script:** ( 1 minutes 32.153 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 3b93b2a6aa..f86aaad709 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]
4%|4 | 5413/132723 [00:00<00:02, 54122.70KB/s]
10%|# | 13505/132723 [00:00<00:01, 69881.84KB/s]
16%|#5 | 21141/132723 [00:00<00:01, 72835.10KB/s]
22%|##1 | 28828/132723 [00:00<00:01, 74426.13KB/s]
27%|##7 | 36461/132723 [00:00<00:01, 75108.98KB/s]
33%|###3 | 44048/132723 [00:00<00:01, 75365.35KB/s]
39%|###9 | 51991/132723 [00:00<00:01, 76691.90KB/s]
45%|####5 | 60016/132723 [00:00<00:00, 77821.86KB/s]
51%|#####1 | 68036/132723 [00:00<00:00, 78560.36KB/s]
57%|#####7 | 76079/132723 [00:01<00:00, 79134.79KB/s]
63%|######3 | 84017/132723 [00:01<00:00, 79203.32KB/s]
69%|######9 | 92056/132723 [00:01<00:00, 79563.03KB/s]
75%|#######5 | 100119/132723 [00:01<00:00, 79879.33KB/s]
82%|########1 | 108219/132723 [00:01<00:00, 80216.65KB/s]
88%|########7 | 116295/132723 [00:01<00:00, 80375.93KB/s]
94%|########
#3| 124333/132723 [00:01<00:00, 77405.07KB/s]
100%|#########9| 132583/132723 [00:01<00:00, 78888.64KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77294.67KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6402/132723 [00:00<00:01, 64016.55KB/s]
11%|#1 | 15224/132723 [00:00<00:01, 78250.42KB/s]
18%|#8 | 23971/132723 [00:00<00:01, 82457.74KB/s]
25%|##4 | 32858/132723 [00:00<00:01, 84985.89KB/s]
31%|###1 | 41741/132723 [00:00<00:01, 86368.13KB/s]
38%|###8 | 50608/132723 [00:00<00:00, 87145.52KB/s]
45%|####4 | 59385/132723 [00:00<00:00, 87344.79KB/s]
51%|#####1 | 68237/132723 [00:00<00:00, 87707.53KB/s]
58%|#####8 | 77118/132723 [00:00<00:00, 88050.77KB/s]
65%|######4 | 85970/132723 [00:01<00:00, 88192.72KB/s]
71%|#######1 | 94790/132723 [00:01<00:00, 87865.08KB/s]
78%|#######8 | 103649/132723 [00:01<00:00, 88082.88KB/s]
85%|########4 | 112508/132723 [00:01<00:00, 88234.33KB/s]
91%|#########1| 121401/132723 [00:01<00:00, 88441.02KB/s]
98%|#########8| 130299/132723 [00:01<00:00, 88600.18KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86686.14KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 50.751 seconds)
+ **Total running time of the script:** ( 3 minutes 47.037 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 cb15c4dacf..d95e643b9b 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
@@ -5,28 +5,28 @@
Computation times
=================
-**16:33.494** total execution time for **how_to_deploy_models** files:
+**16:12.688** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:50.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:47.037 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:42.801 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:36.832 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:35.964 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:31.193 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:33.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.153 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:18.539 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.287 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:57.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.956 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:52.226 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:51.751 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.825 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.992 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:29.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.544 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.937 | 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 34f0d35b58..8df278a24e 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.zipf49bae85-3e3b-4cb2-b55b-d91a2410f97c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip789d493e-d870-4c98-81f0-67341f07999a 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 efb499062a..2b0bb76e61 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:56.061** total execution time for **how_to_extend_tvm** files:
+**00:54.635** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:52.156 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.763 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.795 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.773 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.093 | 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 92d84bfa4d..64a24d36b6 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: 22291us [22291us] (48.83%; 48.83%)
- FoldScaleAxis: 23356us [8us] (51.17%; 51.17%)
- FoldConstant: 23348us [1691us] (51.15%; 99.97%)
- InferType: 21657us [21657us] (47.44%; 92.76%)
+ InferType: 22487us [22487us] (48.96%; 48.96%)
+ FoldScaleAxis: 23444us [7us] (51.04%; 51.04%)
+ FoldConstant: 23437us [1679us] (51.03%; 99.97%)
+ InferType: 21758us [21758us] (47.37%; 92.83%)
@@ -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: 21746us [21746us] (48.17%; 48.17%)
- FoldScaleAxis: 23394us [7us] (51.83%; 51.83%)
- FoldConstant: 23388us [1831us] (51.81%; 99.97%)
- InferType: 21557us [21557us] (47.75%; 92.17%)
+ InferType: 22690us [22690us] (49.18%; 49.18%)
+ FoldScaleAxis: 23445us [6us] (50.82%; 50.82%)
+ FoldConstant: 23439us [1722us] (50.81%; 99.98%)
+ InferType: 21718us [21718us] (47.07%; 92.65%)
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 9cc338909a..cb342e77a4 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: 34.260864 ms
+ Convolution: 54.075454 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 63bd83c3d6..cf0ef81c2b 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.345917 ms
+ conv2d with tensor core: 6.809395 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 33fac15481..85ebfa8bbe 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: 0.019561
- Baseline: 3.353592
+ Numpy running time: 0.019272
+ Baseline: 3.350613
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.331504
+ Opt1: 0.296082
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.357202
+ Opt2: 0.345343
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.130327
+ Opt3: 0.120812
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110347
+ Opt4: 0.110296
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111157
+ Opt5: 0.111122
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147754
+ Opt6: 0.146888
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 c6df8c5d87..aea94972d2 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.795** total execution time for **how_to_optimize_operators** files:
+**00:34.875** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.334 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.594 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.495 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.046 | 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 7398b7cd66..dcca0f50b3 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**10:09.171** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:57.816** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:13.892 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:07.791 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:44.714 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:42.015 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.258 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:07.344 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:33.961 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.704 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.546 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.264 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.801 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.699 | 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 23ced914c0..2ed6253fd6 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
@@ -209,6 +209,13 @@ file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ .T
+
+
@@ -243,11 +250,11 @@ cooperative fetching, unrolling and operator fusion.
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ blockIdx_x = T.launch_thread("blockIdx.x", 56)
conv2d_nchw = T.allocate([7], "float32", "local")
- pad_temp_shared = T.allocate([648], "float32", "shared")
- kernel_shared = T.allocate([1152], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ pad_temp_shared = T.allocate([168], "float32", "shared")
+ kernel_shared = T.allocate([1536], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 64)
conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
@@ -256,64 +263,80 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- for rc_outer_outer in range(64):
+ for rc_outer_outer, rx_outer_outer in T.grid(64, 3):
cse_var_2: T.int32 = rc_outer_outer * 392
cse_var_1: T.int32 = rc_outer_outer * 72
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((648,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((168,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(9 <= (threadIdx_x_1 + 12) % 81 and (threadIdx_x_1 + 12) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 81 * 49 + (threadIdx_x_1 + 12) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- if T.likely(threadIdx_x_1 < 88):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 21 // 7 + blockIdx_x % 7 and threadIdx_x_1 % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + threadIdx_x_1 % 21 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ pad_temp_shared_1[threadIdx_x_1 + 64] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 21 // 7 + blockIdx_x % 7 and (threadIdx_x_1 + 1) % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + (threadIdx_x_1 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 + 1) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 64) // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + (threadIdx_x_1 + 1) % 21 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ if T.likely(threadIdx_x_1 < 40):
+ pad_temp_shared_1[threadIdx_x_1 + 128] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 21 // 7 + blockIdx_x % 7 and (threadIdx_x_1 + 2) % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + (threadIdx_x_1 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 128) // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + (threadIdx_x_1 + 2) % 21 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((1536,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 336) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 16) % 24 * 3 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 56) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 672) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 24 * 3 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 896) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72 + 64512]
- with T.launch_thread(threadIdx_x_2, 112):
- if T.likely(threadIdx_x_2 < 32):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1120) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- for ry_outer_inner, rx_outer_inner, yy_outer_inner in T.grid(3, 3, 7):
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 9]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 18]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 27]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 36]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 45]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 54]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 63]
- for i2_inner in range(7):
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2:threadIdx_x_2 * 2 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 128:threadIdx_x_2 * 2 + 128 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 128) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 128) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 256:threadIdx_x_2 * 2 + 256 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 256) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 256) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 384:threadIdx_x_2 * 2 + 384 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 73728:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 73728 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 512:threadIdx_x_2 * 2 + 512 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 512) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 512) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 640:threadIdx_x_2 * 2 + 640 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 640) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 640) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 768:threadIdx_x_2 * 2 + 768 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 147456:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 147456 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 896:threadIdx_x_2 * 2 + 896 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 896) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 896) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1024:threadIdx_x_2 * 2 + 1024 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1024) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1024) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1152:threadIdx_x_2 * 2 + 1152 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 221184:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 221184 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1280:threadIdx_x_2 * 2 + 1280 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1280) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1280) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1408:threadIdx_x_2 * 2 + 1408 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1408) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1408) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ for rc_outer_inner, ry_outer_inner in T.grid(2, 3):
+ cse_var_3: T.int32 = rc_outer_inner * 84 + ry_outer_inner * 7
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 21] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 42] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 63] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 1] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 22] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 43] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 64] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 2] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 23] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 44] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 65] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 3] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 24] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 45] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 66] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 4] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 25] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 46] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 67] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 5] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 26] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 47] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 68] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 6] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 27] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 48] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 69] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ for i3_inner in range(7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
+ compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i3_inner] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x], T.float32(0))
@@ -363,7 +386,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.330 ms
+ Execution time of this operator: 0.367 ms
@@ -413,34 +436,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -458,16 +481,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=2)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -485,10 +508,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __shared__ float pad_temp_shared[168];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -497,46 +520,74 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 7) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 21)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 1) % 21) / 7) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 1) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) + 1) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) + 1) % 21)) [...]
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 2) % 21) / 7) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 2) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) + 2) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) + 2) % [...]
+ }
+ int2 v_ = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + (((int)threadIdx.x) * 2)) = make_float2(kernel[v_.x],kernel[v_.y]);
+ int2 v__1 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 128)) = make_float2(kernel[v__1.x],kernel[v__1.y]);
+ int2 v__2 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 256)) = make_float2(kernel[v__2.x],kernel[v__2.y]);
+ int2 v__3 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 73728))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 73728))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 384)) = make_float2(kernel[v__3.x],kernel[v__3.y]);
+ int2 v__4 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 512)) = make_float2(kernel[v__4.x],kernel[v__4.y]);
+ int2 v__5 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 640)) = make_float2(kernel[v__5.x],kernel[v__5.y]);
+ int2 v__6 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 147456))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 147456))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 768)) = make_float2(kernel[v__6.x],kernel[v__6.y]);
+ int2 v__7 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 896)) = make_float2(kernel[v__7.x],kernel[v__7.y]);
+ int2 v__8 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1024)) = make_float2(kernel[v__8.x],kernel[v__8.y]);
+ int2 v__9 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 221184))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 221184))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1152)) = make_float2(kernel[v__9.x],kernel[v__9.y]);
+ int2 v__10 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1280)) = make_float2(kernel[v__10.x],kernel[v__10.y]);
+ int2 v__11 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1408)) = make_float2(kernel[v__11.x],kernel[v__11.y]);
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 84) + (ry_outer_inner * 7))] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 22)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 43)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 23)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 44)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 3)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 24)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 66)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 4)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 25)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 67)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 5)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 26)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 68)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 6)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 48)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 69)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
}
@@ -596,7 +647,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 13.892 seconds)
+ **Total running time of the script:** ( 6 minutes 7.791 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 b9880e9d95..863162b4f8 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)
- 7.9269 7.9243 7.9336 7.9228 0.0048
+ 7.9078 7.9097 7.9148 7.8990 0.0066
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.258 seconds)
+ **Total running time of the script:** ( 1 minutes 7.344 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 7c348b3ad4..57aabdd35a 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)
- 754.2379 755.4227 756.2502 751.0409 2.2858
+ 747.6164 747.7624 748.2666 746.8201 0.5995
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 44.714 seconds)
+ **Total running time of the script:** ( 1 minutes 42.015 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 b4da9a674c..1b35fde7fd 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -389,23 +389,23 @@ 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((512,), data=compute_1)
+ for i0_outer_i1_outer_fused in T.parallel(32):
+ compute_1 = T.allocate([2048], "float32", "global")
+ compute_2 = T.Buffer((2048,), data=compute_1)
for i_outer_inner, nb_j_inner in T.grid(4, 2):
- for i_inner_init, j_init in T.grid(4, 16):
- compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 4, 16):
+ for i_inner_init, j_init in T.grid(16, 16):
+ compute_2[i_outer_inner * 512 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 16, 16):
cse_var_1 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
+ cse_var_2: T.int32 = i_outer_inner * 512 + i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 4096 + i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 16384 + i_outer_inner * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
@@ -458,7 +458,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.485 ms
+ Execution time of this operator: 1.499 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 3a7deed7d2..86c4152b26 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.251** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.693** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.659 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index c6068bcd75..81686ee257 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
@@ -268,7 +268,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 317.62/317.62 result: MeasureResult(costs=(0.0007288700240384615,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.4993369579315186, timestamp=1679290499.8290403) [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7457151
+ No: 2 GFLOPS: 0.00/317.62 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
@@ -390,8 +391,9 @@ 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, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6151453
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1263842
+ No: 3 GFLOPS: 267.09/317.62 result: MeasureResult(costs=(0.0008667391459854014,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.049680709838867, timestamp=1679290502.3445191) [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,595226
+ No: 4 GFLOPS: 0.00/317.62 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
@@ -513,8 +515,9 @@ 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, 128, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7020886
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10292832
+ No: 5 GFLOPS: 1.98/317.62 result: MeasureResult(costs=(0.11678472125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7827577590942383, timestamp=1679290506.7678058) [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554282
+ No: 6 GFLOPS: 0.00/317.62 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
@@ -636,8 +639,8 @@ 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, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9179262
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6291829
+ No: 7 GFLOPS: 0.00/317.62 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
@@ -759,8 +762,8 @@ 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, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7465413
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3651692
+ No: 8 GFLOPS: 0.00/317.62 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
@@ -882,8 +885,8 @@ 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, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9473543
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4274178
+ No: 9 GFLOPS: 0.00/317.62 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
@@ -1005,8 +1008,9 @@ 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, 2, 128, 1]), ('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', 1500), ('unroll_explicit', 1)],None,10122910
- No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4170455
+ No: 10 GFLOPS: 37.78/317.62 result: MeasureResult(costs=(0.00612788452,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.192796945571899, timestamp=1679290515.6579175) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3220460
+ No: 11 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1128,8 +1132,8 @@ 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, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3934519
- No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3354089
+ No: 12 GFLOPS: 0.00/317.62 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
@@ -1251,9 +1255,9 @@ 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, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3034895
- No: 9 GFLOPS: 2.57/2.57 result: MeasureResult(costs=(0.090049858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.986830472946167, timestamp=1679262911.0680068) [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6584057
- No: 10 GFLOPS: 0.00/2.57 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5701868
+ No: 13 GFLOPS: 6.20/317.62 result: MeasureResult(costs=(0.03733391175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5725536346435547, timestamp=1679290518.4227517) [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2393461
+ No: 14 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1375,8 +1379,8 @@ 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, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3831935
- No: 11 GFLOPS: 0.00/2.57 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5965141
+ No: 15 GFLOPS: 0.00/317.62 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
@@ -1498,28 +1502,8 @@ 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, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4962951
- No: 12 GFLOPS: 107.28/107.28 result: MeasureResult(costs=(0.0021579820212765956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6963624954223633, timestamp=1679262911.930655) [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8906424
- No: 13 GFLOPS: 0.00/107.28 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, 8, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7958127
- No: 14 GFLOPS: 231.27/231.27 result: MeasureResult(costs=(0.0010010168496732024,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.923830509185791, timestamp=1679262923.2302449) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8790474
- No: 15 GFLOPS: 0.00/231.27 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, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6214415
+ No: 16 GFLOPS: 0.00/317.62 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
@@ -1641,10 +1625,8 @@ 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, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6840537
- No: 16 GFLOPS: 238.78/238.78 result: MeasureResult(costs=(0.0009695047530120482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8221814632415771, timestamp=1679262924.362877) [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3718091
- No: 17 GFLOPS: 40.20/238.78 result: MeasureResult(costs=(0.005758930863636364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.500558853149414, timestamp=1679262930.0089822) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9122960
- No: 18 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5156099
+ No: 17 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1766,8 +1748,8 @@ 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4510176
- No: 19 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2877909
+ No: 18 GFLOPS: 0.00/317.62 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
@@ -1889,8 +1871,8 @@ 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1401158
- No: 20 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9512448
+ No: 19 GFLOPS: 0.00/317.62 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
@@ -2012,7 +1994,8 @@ 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, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2215056
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5087984
+ No: 20 GFLOPS: 4.28/317.62 result: MeasureResult(costs=(0.054125968749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.200007438659668, timestamp=1679290520.8900924) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5552142
@@ -2067,9 +2050,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3718091
+ [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7457151
Finish loading 20 records
- Time cost of this operator: 0.001346
+ Time cost of this operator: 0.001105
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 71aa39e8fe..cab9eea651 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -360,10 +360,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.1 98.736 (1, 2, 10, 10, 3) 2 1 [315.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.966 (1, 6, 10, 10) 1 1 [3.082]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.298 (1, 1, 10, 10, 3) 1 1 [0.953]
- Total_time - 319.134 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.7 98.735 (1, 2, 10, 10, 3) 2 1 [315.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.964 (1, 6, 10, 10) 1 1 [3.082]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.301 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 319.745 - - - - -
@@ -428,10 +428,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 140.0 98.17 (1, 6, 10, 10, 1) 2 1 [140.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.239 (1, 6, 10, 10) 1 1 [1.767]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.591 (1, 3, 10, 10, 1) 1 1 [0.843]
- Total_time - 142.61 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.354 (1, 6, 10, 10, 1) 2 1 [100.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.713 (1, 6, 10, 10) 1 1 [1.765]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.933 (1, 1, 10, 10, 3) 1 1 [0.961]
+ Total_time - 103.026 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.968 seconds)
+ **Total running time of the script:** ( 1 minutes 21.200 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 6b04005ccc..801f1090d2 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 97.9MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 17.8MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 27.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.006 seconds)
+ **Total running time of the script:** ( 1 minutes 18.810 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 f63214cbe5..cbb98bfd0a 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/tmp_bmuqz83/images/random'
+ '/tmp/tmp9u61sxi2/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
: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/tmp_bmuqz83/images/target contains 8144 images
- /tmp/tmp_bmuqz83/images/random contains 5000 images
+ /tmp/tmp9u61sxi2/images/target contains 8144 images
+ /tmp/tmp9u61sxi2/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 48s - loss: 0.2120 - accuracy: 0.9281 - val_loss: 0.1464 - val_accuracy: 0.9471 - 48s/epoch - 146ms/step
+ 328/328 - 47s - loss: 0.2170 - accuracy: 0.9257 - val_loss: 0.1426 - val_accuracy: 0.9486 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0950 - accuracy: 0.9642 - val_loss: 0.1288 - val_accuracy: 0.9566 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.1015 - accuracy: 0.9630 - val_loss: 0.0951 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0648 - accuracy: 0.9767 - val_loss: 0.1331 - val_accuracy: 0.9551 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0763 - accuracy: 0.9722 - val_loss: 0.0741 - val_accuracy: 0.9721 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f08bcb16a90>
+ <keras.callbacks.History object at 0x7fc372b69ed0>
@@ -861,7 +861,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 30.158 seconds)
+ **Total running time of the script:** ( 4 minutes 25.470 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 2014d2db7f..bd17975580 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
@@ -5,20 +5,20 @@
Computation times
=================
-**07:40.424** total execution time for **how_to_work_with_microtvm** files:
+**07:30.895** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:30.158 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:25.470 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:22.968 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:21.200 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:21.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:18.810 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.601 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.225 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.073 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:07.926 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.264 | 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 cefad9d710..fc14177669 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:47.236** total execution time for **how_to_work_with_relay** files:
+**00:46.529** 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``) | 00:35.123 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.475 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.482 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.301 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.624 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.747 | 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 |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 68354af515..776a87b1d5 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 0x7f0772068440>
+ <function my_cuda_math_rule at 0x7fc227366680>
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 d818ee1888..a4b47ec41c 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
=================
-**00:07.626** total execution time for **how_to_work_with_schedules** files:
+**00:08.534** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.977 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.932 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.179 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.598 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.591 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.574 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.060 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.053 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 4be1f6a576..38ecfc6541 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
=================
-**00:31.349** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.261** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.343 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.254 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 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 c9495a6174..1f221807a5 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 34.65s!
+ resnet18_v1 inference graph built in 33.52s!
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 042c19f724..0dd75f01ef 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 23.41s!
+ yolov3-tiny inference graph built in 22.96s!
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 10fbf3cd99..cfb005993b 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
=================
-**01:41.930** total execution time for **topic_vta_tutorials_frontend** files:
+**01:40.089** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.549 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.380 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.709 | 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 1f288d8852..76a9f29743 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
=================
-**00:03.234** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.171** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.760 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.716 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.474 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.455 | 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 82307d5759..aa676a0f84 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
=================
-**00:00.818** total execution time for **topic_vta_tutorials** files:
+**00:00.766** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.424 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.396 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.394 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.370 | 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 35086f7636..116dc3506d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 92.922 ms
+ Execution time of this operator: 96.210 ms
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 28.627 seconds)
+ **Total running time of the script:** ( 1 minutes 32.606 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 f261e01a16..d60311b5ae 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: 2.56/2.56 result: MeasureResult(costs=(0.10481578059999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9299747943878174, timestamp=1679261250.4601374) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 2 GFLOPS: 11.17/11.17 result: MeasureResult(costs=(0.0240278978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6562690734863281, timestamp=1679261251.103908) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
- No: 3 GFLOPS: 11.02/11.17 result: MeasureResult(costs=(0.0243674976,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.657681941986084, timestamp=1679261253.0391736) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
- No: 4 GFLOPS: 10.52/11.17 result: MeasureResult(costs=(0.025511033,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6848843097686768, timestamp=1679261253.710547) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
- No: 5 GFLOPS: 3.21/11.17 result: MeasureResult(costs=(0.0836588114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5874269008636475, timestamp=1679261255.6157768) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
- No: 6 GFLOPS: 8.51/11.17 result: MeasureResult(costs=(0.0315388392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9475069046020508, timestamp=1679261257.6437771) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
- No: 7 GFLOPS: 11.55/11.55 result: MeasureResult(costs=(0.0232429748,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6359972953796387, timestamp=1679261259.5818357) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
- No: 8 GFLOPS: 9.64/11.55 result: MeasureResult(costs=(0.027853055199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8461730480194092, timestamp=1679261260.2910635) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
- No: 9 GFLOPS: 10.38/11.55 result: MeasureResult(costs=(0.025871637800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6416771411895752, timestamp=1679261261.0467536) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 10 GFLOPS: 3.05/11.55 result: MeasureResult(costs=(0.0880257072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6226708889007568, timestamp=1679261262.7169578) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
+ No: 1 GFLOPS: 0.87/0.87 result: MeasureResult(costs=(0.3093766536,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.16783332824707, timestamp=1679288853.1301324) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 2 GFLOPS: 3.90/3.90 result: MeasureResult(costs=(0.0688476878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3839094638824463, timestamp=1679288854.4881644) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 3 GFLOPS: 11.32/11.32 result: MeasureResult(costs=(0.023705878000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.625053882598877, timestamp=1679288856.401491) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
+ No: 4 GFLOPS: 1.84/11.32 result: MeasureResult(costs=(0.1458902282,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5751214027404785, timestamp=1679288860.2716515) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 5 GFLOPS: 9.11/11.32 result: MeasureResult(costs=(0.029479459800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8053863048553467, timestamp=1679288861.429877) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
+ No: 6 GFLOPS: 8.92/11.32 result: MeasureResult(costs=(0.0300845576,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0568006038665771, timestamp=1679288862.1740427) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+ No: 7 GFLOPS: 1.54/11.32 result: MeasureResult(costs=(0.1746959444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.057299852371216, timestamp=1679288866.5027487) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 8 GFLOPS: 1.97/11.32 result: MeasureResult(costs=(0.1361779494,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4306042194366455, timestamp=1679288868.9372778) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+ No: 9 GFLOPS: 8.65/11.32 result: MeasureResult(costs=(0.031021369800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7098093032836914, timestamp=1679288869.7760813) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 10 GFLOPS: 0.50/11.32 result: MeasureResult(costs=(0.5377059849999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.824166774749756, timestamp=1679288878.6373215) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 410017e0af..08ad74a9de 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': 516.5989671299997, 'median': 516.4876506499979, 'std': 1.4108379840399878}
+ {'mean': 515.5682691700019, 'median': 515.9838409999963, 'std': 1.7782090558300219}
@@ -545,31 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 5.68/ 9.00 GFLOPS | Progress: (4/20) | 13.03 s
[Task 1/25] Current/Best: 16.01/ 22.35 GFLOPS | Progress: (8/20) | 16.96 s
[Task 1/25] Current/Best: 17.51/ 22.35 GFLOPS | Progress: (12/20) | 19.59 s
[Task 1/25] Current/Best: 11.31/ 22.35 GFLOPS | Progress: (16/20) | 22.45 s
[Task 1/25] Current/Best: 21.91/ 22.35 GFLOPS | Progress: (20/20) | 25.14 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.47/ 15.10 GFLOPS | Progress: (4/20) | 4.66 s
[Task 2/25] Current/Best: 12.16/ 15.26 GFLOPS | Progress: (8/20) | 6.34 s
[Task 2/25] Current/Best: 16.45/ 16.93 GFLOPS | Progress: (12/20) | 9.50 s
[Task 2/25] Current/Best: 15.18/ 19.09 GFLOPS | Progress: (16/20) | 11.00 s
[Task 2/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (20/20) | 12.36 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.35/ 24.19 GFLOPS | Progress: (4/20) | 5.49 s
[Task 3/25] Current/Best: 15.25/ 24.19 GFLOPS | Progress: (8/20) | 7.93 s
[Task 3/25] Current/Best: 9.27/ 24.19 GFLOPS | Progress: (12/20) | 10.20 s
[Task 3/25] Current/Best: 6.58/ 24.19 GFLOPS | Progress: (16/20) | 12.50 s
[Task 3/25] Current/Best: 6.08/ 24.19 GFLOPS | Progress: (20/20) | 15.15 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.20/ 17.73 GFLOPS | Progress: (4/20) | 7.68 s
[Task 4/25] Current/Best: 7.96/ 18.20 GFLOPS | Progress: (8/20) | 14.59 s
[Task 4/25] Current/Best: 12.83/ 18.20 GFLOPS | Progress: (12/20) | 16.64 s
[Task 4/25] Current/Best: 9.66/ 18.20 GFLOPS | Progress: (16/20) | 22.69 s
[Task 4/25] Current/Best: 10.44/ 18.20 GFLOPS | Progress: (20/20) | 24.91 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 3.39/ 15.16 GFLOPS | Progress: (4/20) | 5.56 s
[Task 5/25] Current/Best: 5.26/ 16.04 GFLOPS | Progress: (8/20) | 8.39 s
[Task 5/25] Current/Best: 11.62/ 16.04 GFLOPS | Progress: (12/20) | 10.47 s
[Task 5/25] Current/Best: 16.34/ 21.01 GFLOPS | Progress: (16/20) | 12.36 s
[Task 5/25] Current/Best: 9.45/ 21.01 GFLOPS | Progress: (20/20) | 14.85 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 4.70/ 15.10 GFLOPS | Progress: (4/20) | 10.34 s
[Task 6/25] Current/Best: 5.24/ 15.85 GFLOPS | Progress: (8/20) | 13.36 s
[Task 6/25] Current/Best: 5.54/ 15.85 GFLOPS | Progress: (12/20) | 17.75 s
[Task 6/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (16/20) | 20.32 s
[Task 6/25] Current/Best: 9.18/ 17.85 GFLOPS | Progress: (20/20) | 22.94 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.22/ 17.07 GFLOPS | Progress: (4/20) | 5.11 s
[Task 7/25] Current/Best: 17.46/ 17.46 GFLOPS | Progress: (8/20) | 7.75 s
[Task 7/25] Current/Best: 11.95/ 20.42 GFLOPS | Progress: (12/20) | 10.35 s
[Task 7/25] Current/Best: 19.99/ 20.42 GFLOPS | Progress: (16/20) | 12.47 s
[Task 7/25] Current/Best: 7.85/ 20.42 GFLOPS | Progress: (20/20) | 14.76 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 5.72/ 13.96 GFLOPS | Progress: (4/20) | 6.49 s
[Task 8/25] Current/Best: 16.06/ 16.06 GFLOPS | Progress: (8/20) | 10.05 s
[Task 8/25] Current/Best: 10.63/ 16.06 GFLOPS | Progress: (12/20) | 14.28 s
[Task 8/25] Current/Best: 12.35/ 22.53 GFLOPS | Progress: (16/20) | 16.93 s
[Task 8/25] Current/Best: 10.89/ 22.53 GFLOPS | Progress: (20/20) | 22.22 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (4/20) | 5.85 s
[Task 9/25] Current/Best: 14.18/ 22.51 GFLOPS | Progress: (8/20) | 16.91 s
[Task 9/25] Current/Best: 11.40/ 22.51 GFLOPS | Progress: (12/20) | 21.54 s
[Task 9/25] Current/Best: 10.78/ 22.51 GFLOPS | Progress: (16/20) | 27.11 s
[Task 9/25] Current/Best: 13.60/ 22.87 GFLOPS | Progress: (20/20) | 31.33 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.14/ 14.19 GFLOPS | Progress: (4/20) | 7.33 s Done.
-
[Task 10/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (8/20) | 11.76 s
[Task 10/25] Current/Best: 20.66/ 21.16 GFLOPS | Progress: (12/20) | 13.23 s
[Task 10/25] Current/Best: 20.35/ 21.16 GFLOPS | Progress: (16/20) | 15.59 s
[Task 10/25] Current/Best: 8.13/ 21.16 GFLOPS | Progress: (20/20) | 19.33 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 22.95/ 22.95 GFLOPS | Progress: (4/20) | 5.69 s
[Task 11/25] Current/Best: 9.44/ 22.95 GFLOPS | Progress: (8/20) | 9.77 s
[Task 11/25] Current/Best: 19.28/ 22.95 GFLOPS | Progress: (12/20) | 12.35 s
[Task 11/25] Current/Best: 12.90/ 22.95 GFLOPS | Progress: (16/20) | 15.29 s
[Task 11/25] Current/Best: 15.75/ 22.95 GFLOPS | Progress: (20/20) | 18.06 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 16.25/ 16.78 GFLOPS | Progress: (4/20) | 5.71 s
[Task 12/25] Current/Best: 8.05/ 16.78 GFLOPS | Progress: (8/20) | 8.73 s
[Task 12/25] Current/Best: 18.69/ 18.69 GFLOPS | Progress: (12/20) | 12.43 s
[Task 12/25] Current/Best: 13.50/ 18.69 GFLOPS | Progress: (16/20) | 15.23 s
[Task 12/25] Current/Best: 5.10/ 18.69 GFLOPS | Progress: (20/20) | 18.00 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 3.10/ 11.57 GFLOPS | Progress: (4/20) | 7.17 s
[Task 13/25] Current/Best: 8.86/ 22.73 GFLOPS | Progress: (8/20) | 12.41 s
[Task 13/25] Current/Best: 13.12/ 22.73 GFLOPS | Progress: (12/20) | 14.54 s
[Task 13/25] Current/Best: 14.13/ 22.73 GFLOPS | Progress: (16/20) | 16.87 s
[Task 13/25] Current/Best: 13.92/ 22.73 GFLOPS | Progress: (20/20) | 20.02 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.28/ 18.72 GFLOPS | Progress: (4/20) | 4.78 s
[Task 14/25] Current/Best: 9.37/ 18.72 GFLOPS | Progress: (8/20) | 7.59 s
[Task 14/25] Current/Best: 3.00/ 18.72 GFLOPS | Progress: (12/20) | 10.68 s
[Task 14/25] Current/Best: 8.16/ 18.72 GFLOPS | Progress: (16/20) | 13.40 s
[Task 14/25] Current/Best: 2.87/ 18.92 GFLOPS | Progress: (20/20) | 18.42 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (4/20) | 4.41 s
[Task 15/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (8/20) | 7.35 s
[Task 15/25] Current/Best: 14.29/ 19.30 GFLOPS | Progress: (12/20) | 12.17 s
[Task 15/25] Current/Best: 17.03/ 19.30 GFLOPS | Progress: (16/20) | 15.13 s
[Task 15/25] Current/Best: 11.65/ 19.30 GFLOPS | Progress: (20/20
) | 19.02 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.16/ 18.04 GFLOPS | Progress: (4/20) | 5.67 s
[Task 16/25] Current/Best: 15.03/ 18.04 GFLOPS | Progress: (8/20) | 8.63 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.79/ 13.48 GFLOPS | Progress: (4/20) | 11.07 s
[Task 1/25] Current/Best: 11.89/ 16.38 GFLOPS | Progress: (8/20) | 14.75 s
[Task 1/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (12/20) | 17.03 s
[Task 1/25] Current/Best: 8.84/ 16.75 GFLOPS | Progress: (16/20) | 20.34 s
[Task 1/25] Current/Best: 5.26/ 17.81 GFLOPS | Progress: (20/20) | 23.33 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.29/ 17.68 GFLOPS | Progress: (4/20) | 4.45 s
[Task 2/25] Current/Best: 4.20/ 17.68 GFLOPS | Progress: (8/20) | 6.47 s
[Task 2/25] Current/Best: 14.07/ 17.68 GFLOPS | Progress: (12/20) | 7.89 s
[Task 2/25] Current/Best: 16.67/ 17.68 GFLOPS | Progress: (16/20) | 9.35 s
[Task 2/25] Current/Best: 14.01/ 17.68 GFLOPS | Progress: (20/20) | 11.51 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.85/ 14.90 GFLOPS | Progress: (4/20) | 5.20 s
[Task 3/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (8/20) | 7.90 s
[Task 3/25] Current/Best: 17.91/ 18.44 GFLOPS | Progress: (12/20) | 10.74 s
[Task 3/25] Current/Best: 5.59/ 18.44 GFLOPS | Progress: (16/20) | 13.76 s
[Task 3/25] Current/Best: 12.39/ 18.44 GFLOPS | Progress: (20/20) | 15.92 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 5.76/ 19.89 GFLOPS | Progress: (4/20) | 4.72 s
[Task 4/25] Current/Best: 15.55/ 19.89 GFLOPS | Progress: (8/20) | 7.57 s
[Task 4/25] Current/Best: 19.31/ 19.89 GFLOPS | Progress: (12/20) | 9.87 s
[Task 4/25] Current/Best: 9.22/ 19.89 GFLOPS | Progress: (16/20) | 12.84 s
[Task 4/25] Current/Best: 12.00/ 19.89 GFLOPS | Progress: (20/20) | 15.61 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 5.16 s
[Task 5/25] Current/Best: 4.95/ 17.34 GFLOPS | Progress: (8/20) | 7.80 s
[Task 5/25] Current/Best: 3.41/ 17.34 GFLOPS | Progress: (12/20) | 10.66 s
[Task 5/25] Current/Best: 11.03/ 17.34 GFLOPS | Progress: (16/20) | 13.57 s
[Task 5/25] Current/Best: 5.93/ 17.41 GFLOPS | Progress: (20/20) | 15.40 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 17.32/ 17.91 GFLOPS | Progress: (4/20) | 5.53 s
[Task 6/25] Current/Best: 10.07/ 18.24 GFLOPS | Progress: (8/20) | 8.46 s
[Task 6/25] Current/Best: 16.03/ 18.81 GFLOPS | Progress: (12/20) | 11.98 s
[Task 6/25] Current/Best: 12.80/ 18.81 GFLOPS | Progress: (16/20) | 14.87 s
[Task 6/25] Current/Best: 13.45/ 18.81 GFLOPS | Progress: (20/20) | 18.24 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 13.19/ 21.40 GFLOPS | Progress: (4/20) | 6.57 s
[Task 7/25] Current/Best: 17.81/ 21.40 GFLOPS | Progress: (8/20) | 8.64 s
[Task 7/25] Current/Best: 16.32/ 21.40 GFLOPS | Progress: (12/20) | 10.55 s
[Task 7/25] Current/Best: 13.38/ 21.40 GFLOPS | Progress: (16/20) | 13.35 s
[Task 7/25] Current/Best: 5.87/ 21.40 GFLOPS | Progress: (20/20) | 16.30 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.79/ 13.54 GFLOPS | Progress: (4/20) | 5.46 s
[Task 8/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (8/20) | 7.83 s
[Task 8/25] Current/Best: 10.51/ 18.84 GFLOPS | Progress: (12/20) | 14.01 s
[Task 8/25] Current/Best: 11.93/ 18.84 GFLOPS | Progress: (16/20) | 17.01 s
[Task 8/25] Current/Best: 7.69/ 18.84 GFLOPS | Progress: (20/20) | 28.60 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 16.23/ 17.22 GFLOPS | Progress: (4/20) | 5.94 s
[Task 9/25] Current/Best: 12.60/ 17.22 GFLOPS | Progress: (8/20) | 17.10 s Done.
+
[Task 9/25] Current/Best: 17.44/ 17.44 GFLOPS | Progress: (12/20) | 20.26 s
[Task 9/25] Current/Best: 10.89/ 17.44 GFLOPS | Progress: (16/20) | 25.63 s
[Task 9/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (20/20) | 27.64 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.89/ 10.50 GFLOPS | Progress: (4/20) | 7.21 s
[Task 10/25] Current/Best: 13.58/ 14.33 GFLOPS | Progress: (8/20) | 10.39 s
[Task 10/25] Current/Best: 16.59/ 16.59 GFLOPS | Progress: (12/20) | 12.22 s
[Task 10/25] Current/Best: 10.68/ 18.30 GFLOPS | Progress: (16/20) | 15.98 s
[Task 10/25] Current/Best: 2.96/ 18.30 GFLOPS | Progress: (20/20) | 19.64 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.40/ 17.65 GFLOPS | Progress: (4/20) | 5.50 s
[Task 11/25] Current/Best: 6.29/ 21.62 GFLOPS | Progress: (8/20) | 8.07 s
[Task 11/25] Current/Best: 16.32/ 21.62 GFLOPS | Progress: (12/20) | 10.90 s
[Task 11/25] Current/Best: 19.83/ 21.62 GFLOPS | Progress: (16/20) | 14.96 s
[Task 11/25] Current/Best: 13.74/ 21.62 GFLOPS | Progress: (20/20) | 17.54 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 3.14/ 14.25 GFLOPS | Progress: (4/20) | 6.45 s
[Task 12/25] Current/Best: 5.06/ 14.25 GFLOPS | Progress: (8/20) | 8.79 s
[Task 12/25] Current/Best: 11.92/ 15.45 GFLOPS | Progress: (12/20) | 11.78 s
[Task 12/25] Current/Best: 18.37/ 18.37 GFLOPS | Progress: (16/20) | 14.31 s
[Task 12/25] Current/Best: 14.35/ 18.37 GFLOPS | Progress: (20/20) | 17.06 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.18/ 18.55 GFLOPS | Progress: (4/20) | 5.28 s
[Task 13/25] Current/Best: 9.74/ 21.97 GFLOPS | Progress: (8/20) | 8.47 s
[Task 13/25] Current/Best: 11.90/ 21.97 GFLOPS | Progress: (12/20) | 11.04 s
[Task 13/25] Current/Best: 17.77/ 21.97 GFLOPS | Progress: (16/20) | 15.09 s
[Task 13/25] Current/Best: 8.53/ 22.23 GFLOPS | Progress: (20/20) | 18.67 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.59/ 12.28 GFLOPS | Progress: (4/20) | 6.47 s
[Task 14/25] Current/Best: 11.81/ 16.78 GFLOPS | Progress: (8/20) | 10.73 s
[Task 14/25] Current/Best: 11.69/ 18.46 GFLOPS | Progress: (12/20) | 13.89 s
[Task 14/25] Current/Best: 15.84/ 18.46 GFLOPS | Progress: (16/20) | 19.38 s
[Task 14/25] Current/Best: 11.21/ 18.46 GFLOPS | Progress: (20/20) | 21.50 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.02/ 15.03 GFLOPS | Progress: (4/20) | 5.56 s
[Task 15/25] Current/Best: 12.21/ 15.03 GFLOPS | Progress: (8/20) | 8.77 s
[Task 15/25] Current/Best: 13.91/ 18.66 GFLOPS | Progress: (12/20) | 11.98 s
[Task 15/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (16/20) | 13.62 s
[Task 15/25] Current/Best: 15.67/ 20.85 GFLOPS | Progress: (20/2
0) | 16.75 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 16/25] Current/Best: 17.21/ 18.04 GFLOPS | Progress: (12/20) | 11.60 s
[Task 16/25] Current/Best: 7.13/ 20.06 GFLOPS | Progress: (16/20) | 13.29 s
[Task 16/25] Current/Best: 7.05/ 20.06 GFLOPS | Progress: (20/20) | 16.91 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 16.41/ 16.47 GFLOPS | Progress: (4/20) | 5.21 s
[Task 17/25] Current/Best: 15.32/ 16.47 GFLOPS | Progress: (8/20) | 8.09 s
[Task 17/25] Current/Best: 10.85/ 21.72 GFLOPS | Progress: (12/20) | 11.29 s
[Task 17/25] Current/Best: 6.16/ 21.72 GFLOPS | Progress: (16/20) | 14.04 s
[Task 17/25] Current/Best: 21.27/ 23.22 GFLOPS | Progress: (20/20) | 17.14 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.30/ 18.61 GFLOPS | Progress: (4/20) | 6.04 s
[Task 18/25] Current/Best: 16.30/ 18.61 GFLOPS | Progress: (8/20) | 9.80 s
[Task 18/25] Current/Best: 6.56/ 18.61 GFLOPS | Progress: (12/20) | 11.98 s
[Task 18/25] Current/Best: 9.59/ 18.61 GFLOPS | Progress: (16/20) | 14.48 s
[Task 18/25] Current/Best: 6.43/ 18.61 GFLOPS | Progress: (20/20) | 19.83 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 17.95/ 17.95 GFLOPS | Progress: (4/20) | 6.07 s
[Task 19/25] Current/Best: 7.24/ 20.87 GFLOPS | Progress: (8/20) | 10.10 s
[Task 19/25] Current/Best: 16.93/ 20.87 GFLOPS | Progress: (12/20) | 14.02 s
[Task 19/25] Current/Best: 12.36/ 20.87 GFLOPS | Progress: (16/20) | 17.67 s
[Task 19/25] Current/Best: 7.88/ 20.87 GFLOPS | Progress: (20/20) | 21.60 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 4.59/ 11.61 GFLOPS | Progress: (4/20) | 6.02 s
[Task 20/25] Current/Best: 9.84/ 18.23 GFLOPS | Progress: (8/20) | 8.29 s
[Task 20/25] Current/Best: 2.52/ 18.23 GFLOPS | Progress: (12/20) | 12.67 s
[Task 20/25] Current/Best: 12.00/ 18.87 GFLOPS | Progress: (16/20) | 17.00 s
[Task 20/25] Current/Best: 17.37/ 18.87 GFLOPS | Progress: (20/20) | 19.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.70/ 17.82 GFLOPS | Progress: (4/20) | 5.11 s
[Task 21/25] Current/Best: 12.94/ 17.82 GFLOPS | Progress: (8/20) | 11.86 s
[Task 21/25] Current/Best: 16.54/ 17.82 GFLOPS | Progress: (12/20) | 14.79 s
[Task 21/25] Current/Best: 14.33/ 18.48 GFLOPS | Progress: (16/20) | 17.26 s
[Task 21/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (20/2
0) | 20.05 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (4/20) | 6.38 s
[Task 22/25] Current/Best: 10.50/ 18.05 GFLOPS | Progress: (8/20) | 8.30 s
[Task 22/25] Current/Best: 16.24/ 18.05 GFLOPS | Progress: (12/20) | 11.71 s
[Task 22/25] Current/Best: 12.49/ 18.05 GFLOPS | Progress: (16/20) | 15.16 s
[Task 22/25] Current/Best: 16.34/ 18.05 GFLOPS | Progress: (20/20) | 17.02 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.29/ 22.56 GFLOPS | Progress: (4/20) | 6.06 s
[Task 23/25] Current/Best: 18.68/ 22.56 GFLOPS | Progress: (8/20) | 8.95 s
[Task 23/25] Current/Best: 9.39/ 22.56 GFLOPS | Progress: (12/20) | 12.35 s
[Task 23/25] Current/Best: 11.73/ 22.56 GFLOPS | Progress: (16/20) | 15.77 s
[Task 23/25] Current/Best: 11.97/ 22.56 GFLOPS | Progress: (20/20) | 18.20 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.79/ 9.79 GFLOPS | Progress: (4/20) | 13.46 s Done.
+
[Task 16/25] Current/Best: 15.32/ 15.32 GFLOPS | Progress: (4/20) | 4.88 s
[Task 16/25] Current/Best: 12.55/ 16.88 GFLOPS | Progress: (8/20) | 8.08 s
[Task 16/25] Current/Best: 3.05/ 16.88 GFLOPS | Progress: (12/20) | 10.74 s
[Task 16/25] Current/Best: 10.57/ 16.88 GFLOPS | Progress: (16/20) | 13.38 s
[Task 16/25] Current/Best: 16.23/ 16.88 GFLOPS | Progress: (20/20) | 15.37 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.08/ 13.08 GFLOPS | Progress: (4/20) | 5.91 s
[Task 17/25] Current/Best: 15.33/ 17.22 GFLOPS | Progress: (8/20) | 9.81 s
[Task 17/25] Current/Best: 12.43/ 20.17 GFLOPS | Progress: (12/20) | 12.33 s
[Task 17/25] Current/Best: 18.84/ 20.17 GFLOPS | Progress: (16/20) | 15.68 s
[Task 17/25] Current/Best: 10.07/ 20.17 GFLOPS | Progress: (20/20) | 19.22 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 19.81/ 20.53 GFLOPS | Progress: (4/20) | 5.85 s
[Task 18/25] Current/Best: 18.20/ 20.53 GFLOPS | Progress: (8/20) | 9.18 s
[Task 18/25] Current/Best: 16.80/ 20.53 GFLOPS | Progress: (12/20) | 12.41 s
[Task 18/25] Current/Best: 12.22/ 20.53 GFLOPS | Progress: (16/20) | 14.59 s
[Task 18/25] Current/Best: 11.41/ 20.99 GFLOPS | Progress: (20/20) | 18.09 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 22.18/ 22.18 GFLOPS | Progress: (4/20) | 6.99 s
[Task 19/25] Current/Best: 18.73/ 22.18 GFLOPS | Progress: (8/20) | 9.85 s
[Task 19/25] Current/Best: 16.99/ 22.18 GFLOPS | Progress: (12/20) | 12.98 s
[Task 19/25] Current/Best: 6.13/ 22.18 GFLOPS | Progress: (16/20) | 16.60 s
[Task 19/25] Current/Best: 20.73/ 22.18 GFLOPS | Progress: (20/20) | 19.06 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 4.93/ 14.75 GFLOPS | Progress: (4/20) | 6.28 s
[Task 20/25] Current/Best: 9.94/ 14.75 GFLOPS | Progress: (8/20) | 10.00 s
[Task 20/25] Current/Best: 4.51/ 20.46 GFLOPS | Progress: (12/20) | 12.36 s
[Task 20/25] Current/Best: 16.35/ 20.46 GFLOPS | Progress: (16/20) | 14.33 s
[Task 20/25] Current/Best: 2.43/ 20.46 GFLOPS | Progress: (20/20) | 18.57 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 13.21/ 20.42 GFLOPS | Progress: (4/20) | 4.79 s
[Task 21/25] Current/Best: 14.03/ 20.42 GFLOPS | Progress: (8/20) | 7.58 s
[Task 21/25] Current/Best: 16.66/ 20.42 GFLOPS | Progress: (12/20) | 9.24 s
[Task 21/25] Current/Best: 14.10/ 20.42 GFLOPS | Progress: (16/20) | 12.53 s
[Task 21/25] Current/Best: 11.02/ 22.81 GFLOPS | Progress: (20/20
) | 15.39 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 6.15/ 11.66 GFLOPS | Progress: (4/20) | 4.95 s
[Task 22/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (8/20) | 6.95 s
[Task 22/25] Current/Best: 15.09/ 20.86 GFLOPS | Progress: (12/20) | 8.75 s
[Task 22/25] Current/Best: 10.56/ 20.86 GFLOPS | Progress: (16/20) | 10.60 s
[Task 22/25] Current/Best: 14.48/ 20.86 GFLOPS | Progress: (20/20) | 12.82 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.06/ 12.06 GFLOPS | Progress: (4/20) | 12.15 s
[Task 23/25] Current/Best: 16.85/ 18.27 GFLOPS | Progress: (8/20) | 14.79 s
[Task 23/25] Current/Best: 17.75/ 22.36 GFLOPS | Progress: (12/20) | 17.72 s
[Task 23/25] Current/Best: 21.49/ 22.81 GFLOPS | Progress: (16/20) | 21.61 s
[Task 23/25] Current/Best: 2.69/ 22.81 GFLOPS | Progress: (20/20) | 24.95 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.55/ 3.26 GFLOPS | Progress: (4/20) | 10.17 s
[Task 24/25] Current/Best: 9.92/ 9.92 GFLOPS | Progress: (8/20) | 21.13 s
[Task 24/25] Current/Best: 6.31/ 9.92 GFLOPS | Progress: (12/20) | 32.12 s Done.
Done.
-
[Task 24/25] Current/Best: 7.31/ 9.79 GFLOPS | Progress: (8/20) | 25.72 s
[Task 24/25] Current/Best: 3.07/ 9.79 GFLOPS | Progress: (12/20) | 38.42 s
[Task 24/25] Current/Best: 0.00/ 9.79 GFLOPS | Progress: (16/20) | 50.48 s
[Task 24/25] Current/Best: 4.38/ 9.79 GFLOPS | Progress: (20/20) | 63.46 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.51/ 8.15 GFLOPS | Progress: (4/20) | 6.35 s Done.
-
[Task 25/25] Current/Best: 3.51/ 8.15 GFLOPS | Progress: (8/20) | 11.40 s
[Task 25/25] Current/Best: 4.56/ 9.25 GFLOPS | Progress: (12/20) | 20.51 s
[Task 25/25] Current/Best: 7.54/ 9.25 GFLOPS | Progress: (16/20) | 31.47 s
[Task 25/25] Current/Best: 7.71/ 9.25 GFLOPS | Progress: (20/20) | 42.45 s
+
[Task 24/25] Current/Best: 9.64/ 9.92 GFLOPS | Progress: (16/20) | 42.77 s
[Task 24/25] Current/Best: 0.57/ 9.92 GFLOPS | Progress: (20/20) | 48.06 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 8.70 GFLOPS | Progress: (4/20) | 13.78 s Done.
+
[Task 25/25] Current/Best: 2.98/ 8.70 GFLOPS | Progress: (8/20) | 24.75 s
[Task 25/25] Current/Best: 1.55/ 8.70 GFLOPS | Progress: (12/20) | 35.72 s
[Task 25/25] Current/Best: 1.55/ 8.70 GFLOPS | Progress: (16/20) | 46.43 s
[Task 25/25] Current/Best: 3.59/ 8.70 GFLOPS | Progress: (20/20) | 52.86 s
@@ -665,7 +665,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -723,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 420.10544814999776, 'median': 419.11991549999357, 'std': 3.924647276829995}
- unoptimized: {'mean': 516.5989671299997, 'median': 516.4876506499979, 'std': 1.4108379840399878}
+ optimized: {'mean': 434.47758615999646, 'median': 434.093213150004, 'std': 1.7515361448761324}
+ unoptimized: {'mean': 515.5682691700019, 'median': 515.9838409999963, 'std': 1.7782090558300219}
@@ -747,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 13 minutes 7.395 seconds)
+ **Total running time of the script:** ( 12 minutes 41.015 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 253d15ad28..935b77ca32 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
- 1.298e-07 secs/op
+ 1.255e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 258e537587..fbd9ab33eb 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x24299f90)), stage(b, placeholder(b, 0x2583b830)), 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, 0x111b85a0)), stage(b, placeholder(b, 0x5f6f470)), 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 291f2924ed..1c8e844200 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:37.274** total execution time for **tutorial** files:
+**16:31.629** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 13:07.395 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:41.015 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:28.627 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:32.606 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.691 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.617 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.337 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:37.269 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:20.916 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.678 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.239 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.412 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.877 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.857 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.190 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 6752326ecf..bfe0d55902 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,8 +285,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000007
+ Numpy running time: 0.000007
+ naive: 0.000008
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000009
+ parallel: 0.000008
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000026
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.59015999847179e-06 1.0
- naive 6.706499999999999e-06 0.8835782119679021
- parallel 9.463599999999999e-06 1.2468248366181225
- vector 2.45834e-05 3.2388513555642624
+ numpy 7.4787199991988015e-06 1.0
+ naive 7.5044e-06 1.003433742780041
+ parallel 8.226799999999999e-06 1.100027812363792
+ vector 2.6062200000000003e-05 3.4848476748416917
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019188
+ Numpy running time: 0.019077
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.348043
+ none: 3.447589
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.314236
+ blocking: 0.297712
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.354639
+ vectorization: 0.340880
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.120555
+ loop permutation: 0.116791
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108701
+ array packing: 0.108593
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111046
+ block caching: 0.110738
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146355
+ parallelization: 0.146589
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3480426914999994 1.0
- blocking 0.3142360954 0.09385665726359513
- vectorization 0.3546392053 0.10592433788265511
- loop permutation 0.1205546086 0.036007488466638635
- array packing 0.10870069020000002 0.032466936719764354
- block caching 0.11104589169999998 0.033167406133118596
- parallelization 0.1463547486 0.04371352521028629
+ none 3.4475891644 1.0
+ blocking 0.2977117138 0.08635359365732667
+ vectorization 0.3408795012 0.09887474549460269
+ loop permutation 0.1167912378 0.03387620514822152
+ array packing 0.1085934579 0.031498375450689474
+ block caching 0.1107381693 0.032120465641175745
+ parallelization 0.1465888387 0.04251923060139665
@@ -1596,7 +1596,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.691 seconds)
+ **Total running time of the script:** ( 1 minutes 1.617 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 25e1ae82f4..76357a9fc8 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-56d0e3b7affce768ae8c7b9d17743d3e8332308d
+fc2a9e50afd03adba9839b94ef6d10145be5fc37
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index fdf17b6958..72345262bd 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.698 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.335 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 1915e1a602..47a285657f 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -511,7 +511,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 972ms/step
+1/1 [==============================] - 1s 956ms/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 c7b4371d27..64765627bc 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip35c63c99-f7f4-4606-8467-222552f3b069 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.zip251b0ea1-bcf0-4833-9cbe-c6bf4f384760 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 287c4040be..d3c5c071fd 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,12 +454,12 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 56.1MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 60.2MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 64.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 64.8MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 69.7MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 68.0MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 49.1MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 56.3MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 54.6MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.3MB/s]
+ 90%|######### | 37.5M/41.5M [00:00<00:00, 54.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 56.2MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 291706dae5..127df2e704 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,10 +437,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 72.1MB/s]
- 50%|####9 | 22.2M/44.7M [00:00<00:00, 114MB/s]
- 75%|#######4 | 33.4M/44.7M [00:00<00:00, 104MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 112MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 55.9MB/s]
+ 36%|###5 | 16.0M/44.7M [00:00<00:00, 64.8MB/s]
+ 58%|#####8 | 26.1M/44.7M [00:00<00:00, 70.1MB/s]
+ 87%|########6 | 38.8M/44.7M [00:00<00:00, 90.9MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 85.6MB/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 10710d99e2..2ed343e21f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -654,7 +654,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.871 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.848 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 ab23e2b61f..25f8ec6566 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:46.308</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:42.385</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:25.871</p></td>
+<td><p>01:23.848</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:20.698</p></td>
+<td><p>01:20.335</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>00:58.193</p></td>
+<td><p>00:56.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:38.013</p></td>
+<td><p>00:37.760</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:32.542</p></td>
+<td><p>00:32.660</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:31.642</p></td>
+<td><p>00:31.302</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:27.765</p></td>
+<td><p>00:27.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:26.519</p></td>
+<td><p>00:26.274</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:22.252</p></td>
+<td><p>00:22.945</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>00:02.813</p></td>
+<td><p>00:02.764</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 3095d144c8..3a2cf5ea3d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -799,7 +799,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2750.3303 2749.6866 2752.7384 2748.2985 1.6465
+ 2677.7677 2677.2289 2681.0580 2676.1151 1.5808
</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_adreno_tvmc.html b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
index 8bd6d541a9..1dbd0e2b35 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
@@ -443,24 +443,25 @@ to run this tutorial with a real device over rpc.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
8192/102967424 [..............................] - ETA: 0s
- 8118272/102967424 [=>............................] - ETA: 0s
- 13099008/102967424 [==>...........................] - ETA: 0s
+ 8380416/102967424 [=>............................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
- 23412736/102967424 [=====>........................] - ETA: 0s
- 28278784/102967424 [=======>......................] - ETA: 0s
- 36749312/102967424 [=========>....................] - ETA: 0s
- 41713664/102967424 [===========>..................] - ETA: 0s
- 46718976/102967424 [============>.................] - ETA: 0s
+ 25157632/102967424 [======>.......................] - ETA: 0s
+ 28663808/102967424 [=======>......................] - ETA: 0s
+ 33546240/102967424 [========>.....................] - ETA: 0s
+ 41934848/102967424 [===========>..................] - ETA: 0s
+ 48578560/102967424 [=============>................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
- 55574528/102967424 [===============>..............] - ETA: 0s
- 56623104/102967424 [===============>..............] - ETA: 0s
- 66600960/102967424 [==================>...........] - ETA: 0s
- 68362240/102967424 [==================>...........] - ETA: 0s
+ 55771136/102967424 [===============>..............] - ETA: 0s
+ 58712064/102967424 [================>.............] - ETA: 0s
+ 67100672/102967424 [==================>...........] - ETA: 0s
+ 69296128/102967424 [===================>..........] - ETA: 0s
+ 72540160/102967424 [====================>.........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
- 84795392/102967424 [=======================>......] - ETA: 0s
+ 82124800/102967424 [======================>.......] - ETA: 0s
+ 83877888/102967424 [=======================>......] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
- 98607104/102967424 [===========================>..] - ETA: 0s
-102916096/102967424 [============================>.] - ETA: 0s
+100630528/102967424 [============================>.] - ETA: 0s
+102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
</pre></div>
</div>
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 651b2f6fde..2d92e912fd 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1432 16.0046 17.1164 15.9001 0.3423
+ 15.7724 15.7627 15.8659 15.6972 0.0532
</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 10e22d484c..2ff86f7e17 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,29 +459,31 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 5%|4 | 7.99M/170M [00:00<00:02, 71.9MB/s]
- 10%|9 | 16.9M/170M [00:00<00:01, 83.8MB/s]
- 15%|#4 | 25.0M/170M [00:00<00:02, 72.0MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 58.1MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 62.0MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:02, 61.4MB/s]
- 33%|###2 | 56.0M/170M [00:00<00:01, 66.8MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 60.3MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 65.4MB/s]
- 46%|####6 | 78.5M/170M [00:01<00:01, 64.4MB/s]
- 51%|##### | 86.3M/170M [00:01<00:01, 62.5MB/s]
- 54%|#####4 | 92.4M/170M [00:01<00:01, 62.6MB/s]
- 58%|#####7 | 98.5M/170M [00:01<00:01, 56.1MB/s]
- 61%|######1 | 104M/170M [00:01<00:01, 56.1MB/s]
- 66%|######5 | 112M/170M [00:01<00:00, 62.3MB/s]
- 71%|####### | 120M/170M [00:01<00:00, 66.0MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 68.4MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 71.1MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 74.7MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 66.6MB/s]
- 94%|#########4| 160M/170M [00:02<00:00, 59.6MB/s]
- 99%|#########8| 168M/170M [00:02<00:00, 65.5MB/s]
-100%|##########| 170M/170M [00:02<00:00, 65.0MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 65.6MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 55.2MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 53.1MB/s]
+ 18%|#7 | 30.3M/170M [00:00<00:03, 45.8MB/s]
+ 20%|## | 34.8M/170M [00:00<00:03, 45.3MB/s]
+ 27%|##6 | 45.2M/170M [00:00<00:02, 61.7MB/s]
+ 30%|### | 51.5M/170M [00:00<00:02, 57.0MB/s]
+ 34%|###3 | 57.3M/170M [00:01<00:02, 57.7MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:02, 54.9MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 54.6MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 61.3MB/s]
+ 51%|##### | 86.3M/170M [00:01<00:01, 59.1MB/s]
+ 54%|#####4 | 92.4M/170M [00:01<00:01, 60.4MB/s]
+ 58%|#####7 | 98.3M/170M [00:01<00:01, 60.6MB/s]
+ 61%|######1 | 104M/170M [00:02<00:01, 47.2MB/s]
+ 66%|######5 | 112M/170M [00:02<00:01, 54.0MB/s]
+ 71%|####### | 120M/170M [00:02<00:00, 57.5MB/s]
+ 74%|#######4 | 126M/170M [00:02<00:00, 56.6MB/s]
+ 79%|#######9 | 134M/170M [00:02<00:00, 59.5MB/s]
+ 83%|########2 | 140M/170M [00:02<00:00, 57.7MB/s]
+ 86%|########5 | 146M/170M [00:02<00:00, 57.8MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 46.1MB/s]
+ 95%|#########4| 161M/170M [00:03<00:00, 56.0MB/s]
+ 98%|#########8| 167M/170M [00:03<00:00, 49.7MB/s]
+100%|##########| 170M/170M [00:03<00:00, 54.8MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -579,7 +581,7 @@ 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 42.801 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 36.832 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 b229ba5e0a..a8667a01c2 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,9 +500,8 @@ 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]
- 1%| | 120k/13.6M [00:00<00:13, 1.05MB/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 45.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 58.1MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 98.5MB/s]
</pre></div>
</div>
</div>
@@ -593,7 +592,7 @@ 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)
- 90.3799 90.2302 96.6319 90.0786 0.6925
+ 90.3195 90.1863 92.1042 90.0481 0.3192
</pre></div>
</div>
<div class="admonition note">
@@ -632,7 +631,7 @@ 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 18.539 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.287 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 2e83b31ccb..64c5c1f245 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.5675 120.5660 123.1183 119.6611 0.5511
+ 120.5631 120.5275 121.4506 119.9558 0.2801
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.964 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.193 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 0bc38fb346..f79b2b6b11 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.635 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.153 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 4e7ca9204a..d19d66afc1 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,24 +468,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5413/132723 [00:00<00:02, 54122.70KB/s]
- 10%|# | 13505/132723 [00:00<00:01, 69881.84KB/s]
- 16%|#5 | 21141/132723 [00:00<00:01, 72835.10KB/s]
- 22%|##1 | 28828/132723 [00:00<00:01, 74426.13KB/s]
- 27%|##7 | 36461/132723 [00:00<00:01, 75108.98KB/s]
- 33%|###3 | 44048/132723 [00:00<00:01, 75365.35KB/s]
- 39%|###9 | 51991/132723 [00:00<00:01, 76691.90KB/s]
- 45%|####5 | 60016/132723 [00:00<00:00, 77821.86KB/s]
- 51%|#####1 | 68036/132723 [00:00<00:00, 78560.36KB/s]
- 57%|#####7 | 76079/132723 [00:01<00:00, 79134.79KB/s]
- 63%|######3 | 84017/132723 [00:01<00:00, 79203.32KB/s]
- 69%|######9 | 92056/132723 [00:01<00:00, 79563.03KB/s]
- 75%|#######5 | 100119/132723 [00:01<00:00, 79879.33KB/s]
- 82%|########1 | 108219/132723 [00:01<00:00, 80216.65KB/s]
- 88%|########7 | 116295/132723 [00:01<00:00, 80375.93KB/s]
- 94%|#########3| 124333/132723 [00:01<00:00, 77405.07KB/s]
-100%|#########9| 132583/132723 [00:01<00:00, 78888.64KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77294.67KB/s]
+ 5%|4 | 6402/132723 [00:00<00:01, 64016.55KB/s]
+ 11%|#1 | 15224/132723 [00:00<00:01, 78250.42KB/s]
+ 18%|#8 | 23971/132723 [00:00<00:01, 82457.74KB/s]
+ 25%|##4 | 32858/132723 [00:00<00:01, 84985.89KB/s]
+ 31%|###1 | 41741/132723 [00:00<00:01, 86368.13KB/s]
+ 38%|###8 | 50608/132723 [00:00<00:00, 87145.52KB/s]
+ 45%|####4 | 59385/132723 [00:00<00:00, 87344.79KB/s]
+ 51%|#####1 | 68237/132723 [00:00<00:00, 87707.53KB/s]
+ 58%|#####8 | 77118/132723 [00:00<00:00, 88050.77KB/s]
+ 65%|######4 | 85970/132723 [00:01<00:00, 88192.72KB/s]
+ 71%|#######1 | 94790/132723 [00:01<00:00, 87865.08KB/s]
+ 78%|#######8 | 103649/132723 [00:01<00:00, 88082.88KB/s]
+ 85%|########4 | 112508/132723 [00:01<00:00, 88234.33KB/s]
+ 91%|#########1| 121401/132723 [00:01<00:00, 88441.02KB/s]
+ 98%|#########8| 130299/132723 [00:01<00:00, 88600.18KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 86686.14KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -524,7 +522,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 50.751 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 47.037 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 69e44ec542..5924132821 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:33.494</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>16:12.688</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,43 +354,43 @@
</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>03:50.751</p></td>
+<td><p>03:47.037</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>03:42.801</p></td>
+<td><p>03:36.832</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>02:35.964</p></td>
+<td><p>02:31.193</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>01:33.635</p></td>
+<td><p>01:32.153</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>01:18.539</p></td>
+<td><p>01:17.287</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>00:57.872</p></td>
+<td><p>00:56.956</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_adreno_tvmc.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-tvmc-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™ with tvmc Interface</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno_tvmc.py</span></code>)</p></td>
-<td><p>00:52.226</p></td>
+<td><p>00:51.751</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:43.825</p></td>
+<td><p>00:42.992</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:29.374</p></td>
+<td><p>00:28.544</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:28.502</p></td>
+<td><p>00:27.937</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index d5d0428cc9..656857201c 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf49bae85-3e3b-4cb2-b55b-d91a2410f97c 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.zip789d493e-d870-4c98-81f0-67341f07999a 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 72969c3ea5..d7880b6941 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:56.061</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:54.635</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:52.156</p></td>
+<td><p>00:50.763</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>00:02.795</p></td>
+<td><p>00:02.773</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>00:01.102</p></td>
+<td><p>00:01.093</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 d31e0f4a14..d7915c9641 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 22291us [22291us] (48.83%; 48.83%)
-FoldScaleAxis: 23356us [8us] (51.17%; 51.17%)
- FoldConstant: 23348us [1691us] (51.15%; 99.97%)
- InferType: 21657us [21657us] (47.44%; 92.76%)
+InferType: 22487us [22487us] (48.96%; 48.96%)
+FoldScaleAxis: 23444us [7us] (51.04%; 51.04%)
+ FoldConstant: 23437us [1679us] (51.03%; 99.97%)
+ InferType: 21758us [21758us] (47.37%; 92.83%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 21746us [21746us] (48.17%; 48.17%)
-FoldScaleAxis: 23394us [7us] (51.83%; 51.83%)
- FoldConstant: 23388us [1831us] (51.81%; 99.97%)
- InferType: 21557us [21557us] (47.75%; 92.17%)
+InferType: 22690us [22690us] (49.18%; 49.18%)
+FoldScaleAxis: 23445us [6us] (50.82%; 50.82%)
+ FoldConstant: 23439us [1722us] (50.81%; 99.98%)
+ InferType: 21718us [21718us] (47.07%; 92.65%)
</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 cd89d06ffa..91db91eeb3 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.260864 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.075454 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 bf4f15dbc5..935c277701 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.345917 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.809395 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 a8f83f6fb6..f743a64b56 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019561
-Baseline: 3.353592
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019272
+Baseline: 3.350613
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.331504
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296082
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.357202
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.345343
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.130327
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120812
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110347
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110296
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111157
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111122
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147754
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146888
</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 24ea631297..0baaecf007 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.795</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.875</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:33.094</p></td>
+<td><p>00:32.334</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>00:01.594</p></td>
+<td><p>00:01.495</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>00:01.107</p></td>
+<td><p>00:01.046</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 dafcd9860c..92afc08bba 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:09.171</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:57.816</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:13.892</p></td>
+<td><p>06:07.791</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>01:44.714</p></td>
+<td><p>01:42.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:08.258</p></td>
+<td><p>01:07.344</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>00:33.961</p></td>
+<td><p>00:32.704</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:14.546</p></td>
+<td><p>00:14.264</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:13.801</p></td>
+<td><p>00:13.699</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 f6602207aa..16cfdf30a7 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
@@ -494,6 +494,9 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</pre></div>
+</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -510,11 +513,11 @@ class Module:
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True})
- blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ blockIdx_x = T.launch_thread("blockIdx.x", 56)
conv2d_nchw = T.allocate([7], "float32", "local")
- pad_temp_shared = T.allocate([648], "float32", "shared")
- kernel_shared = T.allocate([1152], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ pad_temp_shared = T.allocate([168], "float32", "shared")
+ kernel_shared = T.allocate([1536], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 64)
conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
@@ -523,64 +526,80 @@ class Module:
conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- for rc_outer_outer in range(64):
+ for rc_outer_outer, rx_outer_outer in T.grid(64, 3):
cse_var_2: T.int32 = rc_outer_outer * 392
cse_var_1: T.int32 = rc_outer_outer * 72
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((648,), data=pad_temp_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((168,), data=pad_temp_shared, scope="shared")
data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(9 <= (threadIdx_x_1 + 12) % 81 and (threadIdx_x_1 + 12) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 81 * 49 + (threadIdx_x_1 + 12) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- if T.likely(threadIdx_x_1 < 88):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 21 // 7 + blockIdx_x % 7 and threadIdx_x_1 % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + threadIdx_x_1 % 21 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ pad_temp_shared_1[threadIdx_x_1 + 64] = T.if_then_else(1 <= (threadIdx_x_1 + 1) % 21 // 7 + blockIdx_x % 7 and (threadIdx_x_1 + 1) % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + (threadIdx_x_1 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 + 1) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 64) // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + (threadIdx_x_1 + 1) % 21 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 64):
+ if T.likely(threadIdx_x_1 < 40):
+ pad_temp_shared_1[threadIdx_x_1 + 128] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 21 // 7 + blockIdx_x % 7 and (threadIdx_x_1 + 2) % 21 // 7 + blockIdx_x % 7 < 8 and 1 <= rx_outer_outer + (threadIdx_x_1 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 128) // 21 * 49 + blockIdx_x % 7 * 7 + rx_outer_outer + (threadIdx_x_1 + 2) % 21 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((1152,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((1536,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 336) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 16) % 24 * 3 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 56) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 672) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 24 * 3 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 896) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72 + 64512]
- with T.launch_thread(threadIdx_x_2, 112):
- if T.likely(threadIdx_x_2 < 32):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1120) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- for ry_outer_inner, rx_outer_inner, yy_outer_inner in T.grid(3, 3, 7):
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 9]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 18]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 27]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 36]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 45]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 54]
- conv2d_nchw_1[yy_outer_inner] = conv2d_nchw_1[yy_outer_inner] + pad_temp_shared_1[yy_outer_inner * 9 + ry_outer_inner * 9 + rx_outer_inner + threadIdx_x % 7 + 567] * kernel_shared_1[threadIdx_x // 7 * 72 + ry_outer_inner * 3 + rx_outer_inner + 63]
- for i2_inner in range(7):
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2:threadIdx_x_2 * 2 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 128:threadIdx_x_2 * 2 + 128 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 128) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 128) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 256:threadIdx_x_2 * 2 + 256 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 256) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 256) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 384:threadIdx_x_2 * 2 + 384 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 73728:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 73728 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 512:threadIdx_x_2 * 2 + 512 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 512) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 512) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 640:threadIdx_x_2 * 2 + 640 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 640) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 640) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 768:threadIdx_x_2 * 2 + 768 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 147456:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 147456 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 896:threadIdx_x_2 * 2 + 896 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 896) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 896) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1024:threadIdx_x_2 * 2 + 1024 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1024) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1024) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1152:threadIdx_x_2 * 2 + 1152 + 2] = kernel_1[blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 221184:blockIdx_x // 7 * 294912 + threadIdx_x_2 // 12 * 4608 + cse_var_1 + threadIdx_x_2 % 12 * 6 + rx_outer_outer + 221184 + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1280:threadIdx_x_2 * 2 + 1280 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1280) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1280) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 8) % 24 * 3 + rx_outer_outer + 6:3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 * 2 + 1408:threadIdx_x_2 * 2 + 1408 + 2] = kernel_1[blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1408) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer:blockIdx_x // 7 * 294912 + (threadIdx_x_2 * 2 + 1408) // 24 * 4608 + cse_var_1 + (threadIdx_x_2 * 2 + 16) % 24 * 3 + rx_outer_outer + 6:3]
+ for rc_outer_inner, ry_outer_inner in T.grid(2, 3):
+ cse_var_3: T.int32 = rc_outer_inner * 84 + ry_outer_inner * 7
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 21] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 42] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[cse_var_3 + 63] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 1] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 22] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 43] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[cse_var_3 + 64] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 2] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 23] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 44] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[cse_var_3 + 65] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 3] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 24] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 45] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[cse_var_3 + 66] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 4] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 25] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 46] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[cse_var_3 + 67] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 5] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 26] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 47] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[cse_var_3 + 68] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 6] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 27] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 48] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[cse_var_3 + 69] * kernel_shared_1[threadIdx_x * 24 + rc_outer_inner * 12 + ry_outer_inner + 9]
+ for i3_inner in range(7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
+ compute_1[blockIdx_x // 7 * 3136 + threadIdx_x * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i3_inner] + bias_1[blockIdx_x // 7 * 64 + threadIdx_x], T.float32(0))
</pre></div>
</div>
</div>
@@ -614,7 +633,7 @@ 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: 0.330 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.367 ms
</pre></div>
</div>
</div>
@@ -645,34 +664,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -690,16 +709,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=2)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -717,10 +736,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __shared__ float pad_temp_shared[168];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -729,46 +748,74 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 88) {
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- }
- __syncthreads();
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int yy_outer_inner = 0; yy_outer_inner < 7; ++yy_outer_inner) {
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
- conv2d_nchw[yy_outer_inner] = (conv2d_nchw[yy_outer_inner] + (pad_temp_shared[(((((yy_outer_inner * 9) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 72) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 21) / 7) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 21)) - 8)] : 0.0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 1) % 21) / 7) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 1) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) + 1) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer) + [...]
+ if (((int)threadIdx.x) < 40) {
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 2) % 21) / 7) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 2) % 21) / 7) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) + 2) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 21) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + rx_outer_outer [...]
+ }
+ int2 v_ = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + (((int)threadIdx.x) * 2)) = make_float2(kernel[v_.x],kernel[v_.y]);
+ int2 v__1 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 128)) = make_float2(kernel[v__1.x],kernel[v__1.y]);
+ int2 v__2 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 256)) = make_float2(kernel[v__2.x],kernel[v__2.y]);
+ int2 v__3 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 73728))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 73728))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 384)) = make_float2(kernel[v__3.x],kernel[v__3.y]);
+ int2 v__4 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 512)) = make_float2(kernel[v__4.x],kernel[v__4.y]);
+ int2 v__5 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 640)) = make_float2(kernel[v__5.x],kernel[v__5.y]);
+ int2 v__6 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 147456))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 147456))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 768)) = make_float2(kernel[v__6.x],kernel[v__6.y]);
+ int2 v__7 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 896)) = make_float2(kernel[v__7.x],kernel[v__7.y]);
+ int2 v__8 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1024)) = make_float2(kernel[v__8.x],kernel[v__8.y]);
+ int2 v__9 = make_int2(((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 221184))+(3*0), ((((((((((int)blockIdx.x) / 7) * 294912) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + rx_outer_outer) + 221184))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1152)) = make_float2(kernel[v__9.x],kernel[v__9.y]);
+ int2 v__10 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1280)) = make_float2(kernel[v__10.x],kernel[v__10.y]);
+ int2 v__11 = make_int2((((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*0), (((((((((int)blockIdx.x) / 7) * 294912) + ((((((int)threadIdx.x) * 2) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + rx_outer_outer))+(3*1));
+ *(float2*)(kernel_shared + ((((int)threadIdx.x) * 2) + 1408)) = make_float2(kernel[v__11.x],kernel[v__11.y]);
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 84) + (ry_outer_inner * 7))] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 22)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 43)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 23)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 44)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 3)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 24)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 66)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 4)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 25)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 67)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 5)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 26)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 68)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 6)] * kernel_shared[(((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 48)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 84) + (ry_outer_inner * 7)) + 69)] * kernel_shared[((((((int)threadIdx.x) * 24) + (rc_outer_inner * 12)) + ry_outer_inner) + 9)]));
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[(((((int)blockIdx.x) / 7) * 64) + ((int)threadIdx.x))]), 0.000000e+00f);
}
}
</pre></div>
@@ -803,7 +850,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 13.892 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 7.791 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 5e6775fa8e..860467d7a5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9269 7.9243 7.9336 7.9228 0.0048
+ 7.9078 7.9097 7.9148 7.8990 0.0066
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.258 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.344 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 943d33e3f8..18fa556e1c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.2379 755.4227 756.2502 751.0409 2.2858
+ 747.6164 747.7624 748.2666 746.8201 0.5995
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 44.714 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.015 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 869999378e..abd6c3847a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,23 +637,23 @@ 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((512,), data=compute_1)
+ for i0_outer_i1_outer_fused in T.parallel(32):
+ compute_1 = T.allocate([2048], "float32", "global")
+ compute_2 = T.Buffer((2048,), data=compute_1)
for i_outer_inner, nb_j_inner in T.grid(4, 2):
- for i_inner_init, j_init in T.grid(4, 16):
- compute_2[i_outer_inner * 128 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 4, 16):
+ for i_inner_init, j_init in T.grid(16, 16):
+ compute_2[i_outer_inner * 512 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 16, 16):
cse_var_1 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
- cse_var_2: T.int32 = i_outer_inner * 128 + i_inner * 32 + nb_j_inner * 16 + j
+ cse_var_2: T.int32 = i_outer_inner * 512 + i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 4096 + i_outer_inner * 1024 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(16):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 16384 + i_outer_inner * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
@@ -690,7 +690,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.485 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.499 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 d954abf3ba..c8a7b2af08 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.251</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.693</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.217</p></td>
+<td><p>00:44.659</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index fd38600863..7f1796291a 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -573,7 +573,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 317.62/317.62 result: MeasureResult(costs=(0.0007288700240384615,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.4993369579315186, timestamp=1679290499.8290403) [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7457151
+No: 2 GFLOPS: 0.00/317.62 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
@@ -695,8 +696,9 @@ 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, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6151453
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1263842
+No: 3 GFLOPS: 267.09/317.62 result: MeasureResult(costs=(0.0008667391459854014,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.049680709838867, timestamp=1679290502.3445191) [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,595226
+No: 4 GFLOPS: 0.00/317.62 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
@@ -818,8 +820,9 @@ 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, 128, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7020886
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10292832
+No: 5 GFLOPS: 1.98/317.62 result: MeasureResult(costs=(0.11678472125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7827577590942383, timestamp=1679290506.7678058) [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1554282
+No: 6 GFLOPS: 0.00/317.62 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
@@ -941,8 +944,8 @@ 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, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9179262
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6291829
+No: 7 GFLOPS: 0.00/317.62 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
@@ -1064,8 +1067,8 @@ 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, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7465413
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3651692
+No: 8 GFLOPS: 0.00/317.62 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
@@ -1187,8 +1190,8 @@ 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, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9473543
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4274178
+No: 9 GFLOPS: 0.00/317.62 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
@@ -1310,8 +1313,9 @@ 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, 2, 128, 1]), ('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', 1500), ('unroll_explicit', 1)],None,10122910
-No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4170455
+No: 10 GFLOPS: 37.78/317.62 result: MeasureResult(costs=(0.00612788452,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.192796945571899, timestamp=1679290515.6579175) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3220460
+No: 11 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1433,8 +1437,8 @@ 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, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3934519
-No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3354089
+No: 12 GFLOPS: 0.00/317.62 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
@@ -1556,9 +1560,9 @@ 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, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3034895
-No: 9 GFLOPS: 2.57/2.57 result: MeasureResult(costs=(0.090049858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.986830472946167, timestamp=1679262911.0680068) [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6584057
-No: 10 GFLOPS: 0.00/2.57 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5701868
+No: 13 GFLOPS: 6.20/317.62 result: MeasureResult(costs=(0.03733391175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5725536346435547, timestamp=1679290518.4227517) [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2393461
+No: 14 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1680,8 +1684,8 @@ 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, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3831935
-No: 11 GFLOPS: 0.00/2.57 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5965141
+No: 15 GFLOPS: 0.00/317.62 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
@@ -1803,28 +1807,8 @@ 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, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4962951
-No: 12 GFLOPS: 107.28/107.28 result: MeasureResult(costs=(0.0021579820212765956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6963624954223633, timestamp=1679262911.930655) [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8906424
-No: 13 GFLOPS: 0.00/107.28 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, 8, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7958127
-No: 14 GFLOPS: 231.27/231.27 result: MeasureResult(costs=(0.0010010168496732024,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.923830509185791, timestamp=1679262923.2302449) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8790474
-No: 15 GFLOPS: 0.00/231.27 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, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6214415
+No: 16 GFLOPS: 0.00/317.62 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
@@ -1946,10 +1930,8 @@ 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, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6840537
-No: 16 GFLOPS: 238.78/238.78 result: MeasureResult(costs=(0.0009695047530120482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8221814632415771, timestamp=1679262924.362877) [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3718091
-No: 17 GFLOPS: 40.20/238.78 result: MeasureResult(costs=(0.005758930863636364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.500558853149414, timestamp=1679262930.0089822) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9122960
-No: 18 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5156099
+No: 17 GFLOPS: 0.00/317.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2071,8 +2053,8 @@ 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, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4510176
-No: 19 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2877909
+No: 18 GFLOPS: 0.00/317.62 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
@@ -2194,8 +2176,8 @@ 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, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1401158
-No: 20 GFLOPS: 0.00/238.78 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9512448
+No: 19 GFLOPS: 0.00/317.62 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
@@ -2317,7 +2299,8 @@ 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, 64, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2215056
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5087984
+No: 20 GFLOPS: 4.28/317.62 result: MeasureResult(costs=(0.054125968749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.200007438659668, timestamp=1679290520.8900924) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5552142
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2356,9 +2339,9 @@ 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, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3718091
+[('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7457151
Finish loading 20 records
-Time cost of this operator: 0.001346
+Time cost of this operator: 0.001105
</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 c31c274093..82cb01d9d8 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -649,10 +649,10 @@ 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 315.1 98.736 (1, 2, 10, 10, 3) 2 1 [315.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.966 (1, 6, 10, 10) 1 1 [3.082]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.298 (1, 1, 10, 10, 3) 1 1 [0.953]
-Total_time - 319.134 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.7 98.735 (1, 2, 10, 10, 3) 2 1 [315.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.964 (1, 6, 10, 10) 1 1 [3.082]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.301 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 319.745 - - - - -
</pre></div>
</div>
</div>
@@ -704,13 +704,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 140.0 98.17 (1, 6, 10, 10, 1) 2 1 [140.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.767 1.239 (1, 6, 10, 10) 1 1 [1.767]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.591 (1, 3, 10, 10, 1) 1 1 [0.843]
-Total_time - 142.61 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.354 (1, 6, 10, 10, 1) 2 1 [100.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.713 (1, 6, 10, 10) 1 1 [1.765]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.933 (1, 1, 10, 10, 3) 1 1 [0.961]
+Total_time - 103.026 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.968 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.200 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 54c30e6597..f22cb497c8 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -460,7 +460,8 @@ 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, 97.9MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 17.8MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 27.6MB/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.
@@ -586,7 +587,7 @@ 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 21.006 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.810 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 296c04807d..5879269e43 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ 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/tmp_bmuqz83/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp9u61sxi2/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp_bmuqz83/images/target contains 8144 images
-/tmp/tmp_bmuqz83/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp9u61sxi2/images/target contains 8144 images
+/tmp/tmp9u61sxi2/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 48s - loss: 0.2120 - accuracy: 0.9281 - val_loss: 0.1464 - val_accuracy: 0.9471 - 48s/epoch - 146ms/step
+328/328 - 47s - loss: 0.2170 - accuracy: 0.9257 - val_loss: 0.1426 - val_accuracy: 0.9486 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0950 - accuracy: 0.9642 - val_loss: 0.1288 - val_accuracy: 0.9566 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.1015 - accuracy: 0.9630 - val_loss: 0.0951 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0648 - accuracy: 0.9767 - val_loss: 0.1331 - val_accuracy: 0.9551 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0763 - accuracy: 0.9722 - val_loss: 0.0741 - val_accuracy: 0.9721 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f08bcb16a90>
+<keras.callbacks.History object at 0x7fc372b69ed0>
</pre></div>
</div>
</div>
@@ -972,7 +972,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 30.158 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 25.470 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 d8898b1fad..02f7414ad4 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:40.424</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:30.895</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:30.158</p></td>
+<td><p>04:25.470</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:22.968</p></td>
+<td><p>01:21.200</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:21.006</p></td>
+<td><p>01:18.810</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.601</p></td>
+<td><p>00:10.225</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_custom_ide.html#sphx-glr-how-to-work-with-microtvm-micro-custom-ide-py"><span class="std std-ref">9. Bring microTVM to your own development environment</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_custom_ide.py</span></code>)</p></td>
-<td><p>00:08.073</p></td>
+<td><p>00:07.926</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.617</p></td>
+<td><p>00:07.264</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
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 3006e45568..c7ba01dce9 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.236</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:46.529</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</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>00:35.123</p></td>
+<td><p>00:34.475</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>00:10.482</p></td>
+<td><p>00:10.301</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>00:01.624</p></td>
+<td><p>00:01.747</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>
-<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/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index ee150389be..3589b16182 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -540,7 +540,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f0772068440>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc227366680>
</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 c17b6a6583..62f5af4377 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.626</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.534</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,19 +354,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.977</p></td>
+<td><p>00:05.932</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>00:01.219</p></td>
+<td><p>00:01.179</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>00:00.598</p></td>
+<td><p>00:00.591</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>00:00.571</p></td>
+<td><p>00:00.574</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>
@@ -374,7 +374,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:00.062</p></td>
+<td><p>00:00.060</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>
@@ -382,7 +382,7 @@
<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>00:00.028</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 8b33ca40af..b38cf2e776 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1905,7 +1905,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 7f93c23a2c..c2acf43eda 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/56d0e3b7a/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index c20cf1ab2e..4910861521 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/56d0e3b7a/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 d942bb41dc..cd7f285cb4 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/56d0e3b7a/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L357">runtime.ts:357</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L376">runtime.ts:376</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L367">runtime.ts:367</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 62b20adbe3..5c28123654 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/56d0e3b7a/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L299">runtime.ts:299</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L320">runtime.ts:320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L327">runtime.ts:327</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 8c50bc5a92..24121114bd 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/56d0e3b7a/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 250ff50ecd..2ee39fca0c 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/56d0e3b7a/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L50">runtime.ts:50</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L48">runtime.ts:48</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L77">runtime.ts:77</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L67">runtime.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L85">runtime.ts:85</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L96">runtime.ts:96</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L73">runtime.ts:73</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index edf44bba0d..777bd2cc26 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L957">runtime.ts:957</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 966427d462..fa8050cf76 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/56d0e3b7a/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 0139466d43..a663d8afe2 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L641">runtime.ts:641</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L687">runtime.ts:687</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 16984c74e5..c2907e4ce4 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/56d0e3b7a/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L401">runtime.ts:401</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L394">runtime.ts:394</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L553">runtime.ts:553</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 5c1923e3be..7051bc3fb4 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 17f7657573..7d99ac7854 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/56d0e3b7a/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 32ffcda822..7ac2d6d8cb 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index a1cb6fac89..9028f90fa8 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/56d0e3b7a/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index 6490f9e2ab..3246ef1200 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 69480f0f0c..db4741d73a 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 6b15f6729b..d3edf4534b 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/56d0e3b7a/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 0cbe516a1f..5950bddf5c 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/56d0e3b7a/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 3bf4730fef..3bfc6bf66a 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/56d0e3b7a/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 29ab4eae21..02d8ea2f1e 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/56d0e3b7a/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index a8735cb53a..74b9d0faed 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/56d0e3b7a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 7ceec457c0..c87d618bd9 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/56d0e3b7a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index e1adb940e2..0cfc5164e1 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 7f8039e429..185d79388f 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/56d0e3b7a/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 b499f7c249..75e0090cd4 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/56d0e3b7a/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 ad69d59fe3..1e8861f7d7 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/56d0e3b7a/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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/56d0e3b7a/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc2a9e50a/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 9d2298c7de..465d62c033 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 7f47b094a1..8edc7892b6 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.349</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:31.261</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,11 +354,11 @@
</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>00:31.343</p></td>
+<td><p>00:31.254</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>00:00.007</p></td>
+<td><p>00:00.006</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 cc316ce186..16f45a4454 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 34.65s!
+resnet18_v1 inference graph built in 33.52s!
</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 9352db3139..46ace458f3 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 23.41s!
+yolov3-tiny inference graph built in 22.96s!
</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 8611acd9a0..283540a768 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:41.930</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:40.089</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:51.549</p></td>
+<td><p>00:50.380</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:50.382</p></td>
+<td><p>00:49.709</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 efd253000d..def86a265c 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.234</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.171</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.760</p></td>
+<td><p>00:02.716</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.474</p></td>
+<td><p>00:00.455</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 87e0a7278d..a053e48648 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.818</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.766</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.424</p></td>
+<td><p>00:00.396</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>00:00.394</p></td>
+<td><p>00:00.370</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 d36eb08d95..ae2a77edc3 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -574,7 +574,7 @@ 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: 92.922 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 96.210 ms
</pre></div>
</div>
</div>
@@ -646,7 +646,7 @@ 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 28.627 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.606 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 115e06e5e8..e8c4d73d87 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 2.56/2.56 result: MeasureResult(costs=(0.10481578059999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9299747943878174, timestamp=1679261250.4601374) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 2 GFLOPS: 11.17/11.17 result: MeasureResult(costs=(0.0240278978,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6562690734863281, timestamp=1679261251.103908) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
-No: 3 GFLOPS: 11.02/11.17 result: MeasureResult(costs=(0.0243674976,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.657681941986084, timestamp=1679261253.0391736) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
-No: 4 GFLOPS: 10.52/11.17 result: MeasureResult(costs=(0.025511033,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6848843097686768, timestamp=1679261253.710547) [('tile_y', [-1, 8]), ('tile_x', [-1, 64])],None,63
-No: 5 GFLOPS: 3.21/11.17 result: MeasureResult(costs=(0.0836588114,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5874269008636475, timestamp=1679261255.6157768) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
-No: 6 GFLOPS: 8.51/11.17 result: MeasureResult(costs=(0.0315388392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9475069046020508, timestamp=1679261257.6437771) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
-No: 7 GFLOPS: 11.55/11.55 result: MeasureResult(costs=(0.0232429748,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6359972953796387, timestamp=1679261259.5818357) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
-No: 8 GFLOPS: 9.64/11.55 result: MeasureResult(costs=(0.027853055199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8461730480194092, timestamp=1679261260.2910635) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
-No: 9 GFLOPS: 10.38/11.55 result: MeasureResult(costs=(0.025871637800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6416771411895752, timestamp=1679261261.0467536) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 10 GFLOPS: 3.05/11.55 result: MeasureResult(costs=(0.0880257072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6226708889007568, timestamp=1679261262.7169578) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
+No: 1 GFLOPS: 0.87/0.87 result: MeasureResult(costs=(0.3093766536,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.16783332824707, timestamp=1679288853.1301324) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 2 GFLOPS: 3.90/3.90 result: MeasureResult(costs=(0.0688476878,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3839094638824463, timestamp=1679288854.4881644) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+No: 3 GFLOPS: 11.32/11.32 result: MeasureResult(costs=(0.023705878000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.625053882598877, timestamp=1679288856.401491) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
+No: 4 GFLOPS: 1.84/11.32 result: MeasureResult(costs=(0.1458902282,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5751214027404785, timestamp=1679288860.2716515) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 5 GFLOPS: 9.11/11.32 result: MeasureResult(costs=(0.029479459800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8053863048553467, timestamp=1679288861.429877) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
+No: 6 GFLOPS: 8.92/11.32 result: MeasureResult(costs=(0.0300845576,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0568006038665771, timestamp=1679288862.1740427) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+No: 7 GFLOPS: 1.54/11.32 result: MeasureResult(costs=(0.1746959444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.057299852371216, timestamp=1679288866.5027487) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+No: 8 GFLOPS: 1.97/11.32 result: MeasureResult(costs=(0.1361779494,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4306042194366455, timestamp=1679288868.9372778) [('tile_y', [-1, 16]), ('tile_x', [-1, 2])],None,14
+No: 9 GFLOPS: 8.65/11.32 result: MeasureResult(costs=(0.031021369800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7098093032836914, timestamp=1679288869.7760813) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 10 GFLOPS: 0.50/11.32 result: MeasureResult(costs=(0.5377059849999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.824166774749756, timestamp=1679288878.6373215) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
</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 dce90cc3b4..add43da97d 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 516.5989671299997, 'median': 516.4876506499979, 'std': 1.4108379840399878}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 515.5682691700019, 'median': 515.9838409999963, 'std': 1.7782090558300219}
</pre></div>
</div>
</div>
@@ -715,179 +715,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 5.68/ 9.00 GFLOPS | Progress: (4/20) | 13.03 s
-[Task 1/25] Current/Best: 16.01/ 22.35 GFLOPS | Progress: (8/20) | 16.96 s
-[Task 1/25] Current/Best: 17.51/ 22.35 GFLOPS | Progress: (12/20) | 19.59 s
-[Task 1/25] Current/Best: 11.31/ 22.35 GFLOPS | Progress: (16/20) | 22.45 s
-[Task 1/25] Current/Best: 21.91/ 22.35 GFLOPS | Progress: (20/20) | 25.14 s Done.
+[Task 1/25] Current/Best: 12.79/ 13.48 GFLOPS | Progress: (4/20) | 11.07 s
+[Task 1/25] Current/Best: 11.89/ 16.38 GFLOPS | Progress: (8/20) | 14.75 s
+[Task 1/25] Current/Best: 16.75/ 16.75 GFLOPS | Progress: (12/20) | 17.03 s
+[Task 1/25] Current/Best: 8.84/ 16.75 GFLOPS | Progress: (16/20) | 20.34 s
+[Task 1/25] Current/Best: 5.26/ 17.81 GFLOPS | Progress: (20/20) | 23.33 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 9.47/ 15.10 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 2/25] Current/Best: 12.16/ 15.26 GFLOPS | Progress: (8/20) | 6.34 s
-[Task 2/25] Current/Best: 16.45/ 16.93 GFLOPS | Progress: (12/20) | 9.50 s
-[Task 2/25] Current/Best: 15.18/ 19.09 GFLOPS | Progress: (16/20) | 11.00 s
-[Task 2/25] Current/Best: 21.76/ 21.76 GFLOPS | Progress: (20/20) | 12.36 s Done.
+[Task 2/25] Current/Best: 6.29/ 17.68 GFLOPS | Progress: (4/20) | 4.45 s
+[Task 2/25] Current/Best: 4.20/ 17.68 GFLOPS | Progress: (8/20) | 6.47 s
+[Task 2/25] Current/Best: 14.07/ 17.68 GFLOPS | Progress: (12/20) | 7.89 s
+[Task 2/25] Current/Best: 16.67/ 17.68 GFLOPS | Progress: (16/20) | 9.35 s
+[Task 2/25] Current/Best: 14.01/ 17.68 GFLOPS | Progress: (20/20) | 11.51 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 15.35/ 24.19 GFLOPS | Progress: (4/20) | 5.49 s
-[Task 3/25] Current/Best: 15.25/ 24.19 GFLOPS | Progress: (8/20) | 7.93 s
-[Task 3/25] Current/Best: 9.27/ 24.19 GFLOPS | Progress: (12/20) | 10.20 s
-[Task 3/25] Current/Best: 6.58/ 24.19 GFLOPS | Progress: (16/20) | 12.50 s
-[Task 3/25] Current/Best: 6.08/ 24.19 GFLOPS | Progress: (20/20) | 15.15 s Done.
+[Task 3/25] Current/Best: 14.85/ 14.90 GFLOPS | Progress: (4/20) | 5.20 s
+[Task 3/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (8/20) | 7.90 s
+[Task 3/25] Current/Best: 17.91/ 18.44 GFLOPS | Progress: (12/20) | 10.74 s
+[Task 3/25] Current/Best: 5.59/ 18.44 GFLOPS | Progress: (16/20) | 13.76 s
+[Task 3/25] Current/Best: 12.39/ 18.44 GFLOPS | Progress: (20/20) | 15.92 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 11.20/ 17.73 GFLOPS | Progress: (4/20) | 7.68 s
-[Task 4/25] Current/Best: 7.96/ 18.20 GFLOPS | Progress: (8/20) | 14.59 s
-[Task 4/25] Current/Best: 12.83/ 18.20 GFLOPS | Progress: (12/20) | 16.64 s
-[Task 4/25] Current/Best: 9.66/ 18.20 GFLOPS | Progress: (16/20) | 22.69 s
-[Task 4/25] Current/Best: 10.44/ 18.20 GFLOPS | Progress: (20/20) | 24.91 s Done.
+[Task 4/25] Current/Best: 5.76/ 19.89 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 4/25] Current/Best: 15.55/ 19.89 GFLOPS | Progress: (8/20) | 7.57 s
+[Task 4/25] Current/Best: 19.31/ 19.89 GFLOPS | Progress: (12/20) | 9.87 s
+[Task 4/25] Current/Best: 9.22/ 19.89 GFLOPS | Progress: (16/20) | 12.84 s
+[Task 4/25] Current/Best: 12.00/ 19.89 GFLOPS | Progress: (20/20) | 15.61 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 3.39/ 15.16 GFLOPS | Progress: (4/20) | 5.56 s
-[Task 5/25] Current/Best: 5.26/ 16.04 GFLOPS | Progress: (8/20) | 8.39 s
-[Task 5/25] Current/Best: 11.62/ 16.04 GFLOPS | Progress: (12/20) | 10.47 s
-[Task 5/25] Current/Best: 16.34/ 21.01 GFLOPS | Progress: (16/20) | 12.36 s
-[Task 5/25] Current/Best: 9.45/ 21.01 GFLOPS | Progress: (20/20) | 14.85 s Done.
+[Task 5/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 5.16 s
+[Task 5/25] Current/Best: 4.95/ 17.34 GFLOPS | Progress: (8/20) | 7.80 s
+[Task 5/25] Current/Best: 3.41/ 17.34 GFLOPS | Progress: (12/20) | 10.66 s
+[Task 5/25] Current/Best: 11.03/ 17.34 GFLOPS | Progress: (16/20) | 13.57 s
+[Task 5/25] Current/Best: 5.93/ 17.41 GFLOPS | Progress: (20/20) | 15.40 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 4.70/ 15.10 GFLOPS | Progress: (4/20) | 10.34 s
-[Task 6/25] Current/Best: 5.24/ 15.85 GFLOPS | Progress: (8/20) | 13.36 s
-[Task 6/25] Current/Best: 5.54/ 15.85 GFLOPS | Progress: (12/20) | 17.75 s
-[Task 6/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (16/20) | 20.32 s
-[Task 6/25] Current/Best: 9.18/ 17.85 GFLOPS | Progress: (20/20) | 22.94 s Done.
+[Task 6/25] Current/Best: 17.32/ 17.91 GFLOPS | Progress: (4/20) | 5.53 s
+[Task 6/25] Current/Best: 10.07/ 18.24 GFLOPS | Progress: (8/20) | 8.46 s
+[Task 6/25] Current/Best: 16.03/ 18.81 GFLOPS | Progress: (12/20) | 11.98 s
+[Task 6/25] Current/Best: 12.80/ 18.81 GFLOPS | Progress: (16/20) | 14.87 s
+[Task 6/25] Current/Best: 13.45/ 18.81 GFLOPS | Progress: (20/20) | 18.24 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.22/ 17.07 GFLOPS | Progress: (4/20) | 5.11 s
-[Task 7/25] Current/Best: 17.46/ 17.46 GFLOPS | Progress: (8/20) | 7.75 s
-[Task 7/25] Current/Best: 11.95/ 20.42 GFLOPS | Progress: (12/20) | 10.35 s
-[Task 7/25] Current/Best: 19.99/ 20.42 GFLOPS | Progress: (16/20) | 12.47 s
-[Task 7/25] Current/Best: 7.85/ 20.42 GFLOPS | Progress: (20/20) | 14.76 s Done.
+[Task 7/25] Current/Best: 13.19/ 21.40 GFLOPS | Progress: (4/20) | 6.57 s
+[Task 7/25] Current/Best: 17.81/ 21.40 GFLOPS | Progress: (8/20) | 8.64 s
+[Task 7/25] Current/Best: 16.32/ 21.40 GFLOPS | Progress: (12/20) | 10.55 s
+[Task 7/25] Current/Best: 13.38/ 21.40 GFLOPS | Progress: (16/20) | 13.35 s
+[Task 7/25] Current/Best: 5.87/ 21.40 GFLOPS | Progress: (20/20) | 16.30 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 5.72/ 13.96 GFLOPS | Progress: (4/20) | 6.49 s
-[Task 8/25] Current/Best: 16.06/ 16.06 GFLOPS | Progress: (8/20) | 10.05 s
-[Task 8/25] Current/Best: 10.63/ 16.06 GFLOPS | Progress: (12/20) | 14.28 s
-[Task 8/25] Current/Best: 12.35/ 22.53 GFLOPS | Progress: (16/20) | 16.93 s
-[Task 8/25] Current/Best: 10.89/ 22.53 GFLOPS | Progress: (20/20) | 22.22 s Done.
-
+[Task 8/25] Current/Best: 12.79/ 13.54 GFLOPS | Progress: (4/20) | 5.46 s
+[Task 8/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (8/20) | 7.83 s
+[Task 8/25] Current/Best: 10.51/ 18.84 GFLOPS | Progress: (12/20) | 14.01 s
+[Task 8/25] Current/Best: 11.93/ 18.84 GFLOPS | Progress: (16/20) | 17.01 s
+[Task 8/25] Current/Best: 7.69/ 18.84 GFLOPS | Progress: (20/20) | 28.60 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (4/20) | 5.85 s
-[Task 9/25] Current/Best: 14.18/ 22.51 GFLOPS | Progress: (8/20) | 16.91 s
-[Task 9/25] Current/Best: 11.40/ 22.51 GFLOPS | Progress: (12/20) | 21.54 s
-[Task 9/25] Current/Best: 10.78/ 22.51 GFLOPS | Progress: (16/20) | 27.11 s
-[Task 9/25] Current/Best: 13.60/ 22.87 GFLOPS | Progress: (20/20) | 31.33 s
-[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 13.14/ 14.19 GFLOPS | Progress: (4/20) | 7.33 s Done.
+[Task 9/25] Current/Best: 16.23/ 17.22 GFLOPS | Progress: (4/20) | 5.94 s
+[Task 9/25] Current/Best: 12.60/ 17.22 GFLOPS | Progress: (8/20) | 17.10 s Done.
-[Task 10/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (8/20) | 11.76 s
-[Task 10/25] Current/Best: 20.66/ 21.16 GFLOPS | Progress: (12/20) | 13.23 s
-[Task 10/25] Current/Best: 20.35/ 21.16 GFLOPS | Progress: (16/20) | 15.59 s
-[Task 10/25] Current/Best: 8.13/ 21.16 GFLOPS | Progress: (20/20) | 19.33 s Done.
+[Task 9/25] Current/Best: 17.44/ 17.44 GFLOPS | Progress: (12/20) | 20.26 s
+[Task 9/25] Current/Best: 10.89/ 17.44 GFLOPS | Progress: (16/20) | 25.63 s
+[Task 9/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (20/20) | 27.64 s Done.
+
+[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 10/25] Current/Best: 8.89/ 10.50 GFLOPS | Progress: (4/20) | 7.21 s
+[Task 10/25] Current/Best: 13.58/ 14.33 GFLOPS | Progress: (8/20) | 10.39 s
+[Task 10/25] Current/Best: 16.59/ 16.59 GFLOPS | Progress: (12/20) | 12.22 s
+[Task 10/25] Current/Best: 10.68/ 18.30 GFLOPS | Progress: (16/20) | 15.98 s
+[Task 10/25] Current/Best: 2.96/ 18.30 GFLOPS | Progress: (20/20) | 19.64 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 22.95/ 22.95 GFLOPS | Progress: (4/20) | 5.69 s
-[Task 11/25] Current/Best: 9.44/ 22.95 GFLOPS | Progress: (8/20) | 9.77 s
-[Task 11/25] Current/Best: 19.28/ 22.95 GFLOPS | Progress: (12/20) | 12.35 s
-[Task 11/25] Current/Best: 12.90/ 22.95 GFLOPS | Progress: (16/20) | 15.29 s
-[Task 11/25] Current/Best: 15.75/ 22.95 GFLOPS | Progress: (20/20) | 18.06 s Done.
+[Task 11/25] Current/Best: 9.40/ 17.65 GFLOPS | Progress: (4/20) | 5.50 s
+[Task 11/25] Current/Best: 6.29/ 21.62 GFLOPS | Progress: (8/20) | 8.07 s
+[Task 11/25] Current/Best: 16.32/ 21.62 GFLOPS | Progress: (12/20) | 10.90 s
+[Task 11/25] Current/Best: 19.83/ 21.62 GFLOPS | Progress: (16/20) | 14.96 s
+[Task 11/25] Current/Best: 13.74/ 21.62 GFLOPS | Progress: (20/20) | 17.54 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 16.25/ 16.78 GFLOPS | Progress: (4/20) | 5.71 s
-[Task 12/25] Current/Best: 8.05/ 16.78 GFLOPS | Progress: (8/20) | 8.73 s
-[Task 12/25] Current/Best: 18.69/ 18.69 GFLOPS | Progress: (12/20) | 12.43 s
-[Task 12/25] Current/Best: 13.50/ 18.69 GFLOPS | Progress: (16/20) | 15.23 s
-[Task 12/25] Current/Best: 5.10/ 18.69 GFLOPS | Progress: (20/20) | 18.00 s Done.
+[Task 12/25] Current/Best: 3.14/ 14.25 GFLOPS | Progress: (4/20) | 6.45 s
+[Task 12/25] Current/Best: 5.06/ 14.25 GFLOPS | Progress: (8/20) | 8.79 s
+[Task 12/25] Current/Best: 11.92/ 15.45 GFLOPS | Progress: (12/20) | 11.78 s
+[Task 12/25] Current/Best: 18.37/ 18.37 GFLOPS | Progress: (16/20) | 14.31 s
+[Task 12/25] Current/Best: 14.35/ 18.37 GFLOPS | Progress: (20/20) | 17.06 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 3.10/ 11.57 GFLOPS | Progress: (4/20) | 7.17 s
-[Task 13/25] Current/Best: 8.86/ 22.73 GFLOPS | Progress: (8/20) | 12.41 s
-[Task 13/25] Current/Best: 13.12/ 22.73 GFLOPS | Progress: (12/20) | 14.54 s
-[Task 13/25] Current/Best: 14.13/ 22.73 GFLOPS | Progress: (16/20) | 16.87 s
-[Task 13/25] Current/Best: 13.92/ 22.73 GFLOPS | Progress: (20/20) | 20.02 s Done.
+[Task 13/25] Current/Best: 18.18/ 18.55 GFLOPS | Progress: (4/20) | 5.28 s
+[Task 13/25] Current/Best: 9.74/ 21.97 GFLOPS | Progress: (8/20) | 8.47 s
+[Task 13/25] Current/Best: 11.90/ 21.97 GFLOPS | Progress: (12/20) | 11.04 s
+[Task 13/25] Current/Best: 17.77/ 21.97 GFLOPS | Progress: (16/20) | 15.09 s
+[Task 13/25] Current/Best: 8.53/ 22.23 GFLOPS | Progress: (20/20) | 18.67 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 9.28/ 18.72 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 14/25] Current/Best: 9.37/ 18.72 GFLOPS | Progress: (8/20) | 7.59 s
-[Task 14/25] Current/Best: 3.00/ 18.72 GFLOPS | Progress: (12/20) | 10.68 s
-[Task 14/25] Current/Best: 8.16/ 18.72 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 14/25] Current/Best: 2.87/ 18.92 GFLOPS | Progress: (20/20) | 18.42 s
+[Task 14/25] Current/Best: 11.59/ 12.28 GFLOPS | Progress: (4/20) | 6.47 s
+[Task 14/25] Current/Best: 11.81/ 16.78 GFLOPS | Progress: (8/20) | 10.73 s
+[Task 14/25] Current/Best: 11.69/ 18.46 GFLOPS | Progress: (12/20) | 13.89 s
+[Task 14/25] Current/Best: 15.84/ 18.46 GFLOPS | Progress: (16/20) | 19.38 s
+[Task 14/25] Current/Best: 11.21/ 18.46 GFLOPS | Progress: (20/20) | 21.50 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 17.91/ 17.91 GFLOPS | Progress: (4/20) | 4.41 s
-[Task 15/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (8/20) | 7.35 s
-[Task 15/25] Current/Best: 14.29/ 19.30 GFLOPS | Progress: (12/20) | 12.17 s
-[Task 15/25] Current/Best: 17.03/ 19.30 GFLOPS | Progress: (16/20) | 15.13 s
-[Task 15/25] Current/Best: 11.65/ 19.30 GFLOPS | Progress: (20/20) | 19.02 s
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 11.16/ 18.04 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 16/25] Current/Best: 15.03/ 18.04 GFLOPS | Progress: (8/20) | 8.63 s Done.
+[Task 15/25] Current/Best: 13.02/ 15.03 GFLOPS | Progress: (4/20) | 5.56 s
+[Task 15/25] Current/Best: 12.21/ 15.03 GFLOPS | Progress: (8/20) | 8.77 s
+[Task 15/25] Current/Best: 13.91/ 18.66 GFLOPS | Progress: (12/20) | 11.98 s
+[Task 15/25] Current/Best: 20.85/ 20.85 GFLOPS | Progress: (16/20) | 13.62 s
+[Task 15/25] Current/Best: 15.67/ 20.85 GFLOPS | Progress: (20/20) | 16.75 s
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-[Task 16/25] Current/Best: 17.21/ 18.04 GFLOPS | Progress: (12/20) | 11.60 s
-[Task 16/25] Current/Best: 7.13/ 20.06 GFLOPS | Progress: (16/20) | 13.29 s
-[Task 16/25] Current/Best: 7.05/ 20.06 GFLOPS | Progress: (20/20) | 16.91 s Done.
+[Task 16/25] Current/Best: 15.32/ 15.32 GFLOPS | Progress: (4/20) | 4.88 s
+[Task 16/25] Current/Best: 12.55/ 16.88 GFLOPS | Progress: (8/20) | 8.08 s
+[Task 16/25] Current/Best: 3.05/ 16.88 GFLOPS | Progress: (12/20) | 10.74 s
+[Task 16/25] Current/Best: 10.57/ 16.88 GFLOPS | Progress: (16/20) | 13.38 s
+[Task 16/25] Current/Best: 16.23/ 16.88 GFLOPS | Progress: (20/20) | 15.37 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 16.41/ 16.47 GFLOPS | Progress: (4/20) | 5.21 s
-[Task 17/25] Current/Best: 15.32/ 16.47 GFLOPS | Progress: (8/20) | 8.09 s
-[Task 17/25] Current/Best: 10.85/ 21.72 GFLOPS | Progress: (12/20) | 11.29 s
-[Task 17/25] Current/Best: 6.16/ 21.72 GFLOPS | Progress: (16/20) | 14.04 s
-[Task 17/25] Current/Best: 21.27/ 23.22 GFLOPS | Progress: (20/20) | 17.14 s Done.
+[Task 17/25] Current/Best: 13.08/ 13.08 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 17/25] Current/Best: 15.33/ 17.22 GFLOPS | Progress: (8/20) | 9.81 s
+[Task 17/25] Current/Best: 12.43/ 20.17 GFLOPS | Progress: (12/20) | 12.33 s
+[Task 17/25] Current/Best: 18.84/ 20.17 GFLOPS | Progress: (16/20) | 15.68 s
+[Task 17/25] Current/Best: 10.07/ 20.17 GFLOPS | Progress: (20/20) | 19.22 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 10.30/ 18.61 GFLOPS | Progress: (4/20) | 6.04 s
-[Task 18/25] Current/Best: 16.30/ 18.61 GFLOPS | Progress: (8/20) | 9.80 s
-[Task 18/25] Current/Best: 6.56/ 18.61 GFLOPS | Progress: (12/20) | 11.98 s
-[Task 18/25] Current/Best: 9.59/ 18.61 GFLOPS | Progress: (16/20) | 14.48 s
-[Task 18/25] Current/Best: 6.43/ 18.61 GFLOPS | Progress: (20/20) | 19.83 s Done.
+[Task 18/25] Current/Best: 19.81/ 20.53 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 18/25] Current/Best: 18.20/ 20.53 GFLOPS | Progress: (8/20) | 9.18 s
+[Task 18/25] Current/Best: 16.80/ 20.53 GFLOPS | Progress: (12/20) | 12.41 s
+[Task 18/25] Current/Best: 12.22/ 20.53 GFLOPS | Progress: (16/20) | 14.59 s
+[Task 18/25] Current/Best: 11.41/ 20.99 GFLOPS | Progress: (20/20) | 18.09 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 17.95/ 17.95 GFLOPS | Progress: (4/20) | 6.07 s
-[Task 19/25] Current/Best: 7.24/ 20.87 GFLOPS | Progress: (8/20) | 10.10 s
-[Task 19/25] Current/Best: 16.93/ 20.87 GFLOPS | Progress: (12/20) | 14.02 s
-[Task 19/25] Current/Best: 12.36/ 20.87 GFLOPS | Progress: (16/20) | 17.67 s
-[Task 19/25] Current/Best: 7.88/ 20.87 GFLOPS | Progress: (20/20) | 21.60 s Done.
+[Task 19/25] Current/Best: 22.18/ 22.18 GFLOPS | Progress: (4/20) | 6.99 s
+[Task 19/25] Current/Best: 18.73/ 22.18 GFLOPS | Progress: (8/20) | 9.85 s
+[Task 19/25] Current/Best: 16.99/ 22.18 GFLOPS | Progress: (12/20) | 12.98 s
+[Task 19/25] Current/Best: 6.13/ 22.18 GFLOPS | Progress: (16/20) | 16.60 s
+[Task 19/25] Current/Best: 20.73/ 22.18 GFLOPS | Progress: (20/20) | 19.06 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 4.59/ 11.61 GFLOPS | Progress: (4/20) | 6.02 s
-[Task 20/25] Current/Best: 9.84/ 18.23 GFLOPS | Progress: (8/20) | 8.29 s
-[Task 20/25] Current/Best: 2.52/ 18.23 GFLOPS | Progress: (12/20) | 12.67 s
-[Task 20/25] Current/Best: 12.00/ 18.87 GFLOPS | Progress: (16/20) | 17.00 s
-[Task 20/25] Current/Best: 17.37/ 18.87 GFLOPS | Progress: (20/20) | 19.55 s
+[Task 20/25] Current/Best: 4.93/ 14.75 GFLOPS | Progress: (4/20) | 6.28 s
+[Task 20/25] Current/Best: 9.94/ 14.75 GFLOPS | Progress: (8/20) | 10.00 s
+[Task 20/25] Current/Best: 4.51/ 20.46 GFLOPS | Progress: (12/20) | 12.36 s
+[Task 20/25] Current/Best: 16.35/ 20.46 GFLOPS | Progress: (16/20) | 14.33 s
+[Task 20/25] Current/Best: 2.43/ 20.46 GFLOPS | Progress: (20/20) | 18.57 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.70/ 17.82 GFLOPS | Progress: (4/20) | 5.11 s
-[Task 21/25] Current/Best: 12.94/ 17.82 GFLOPS | Progress: (8/20) | 11.86 s
-[Task 21/25] Current/Best: 16.54/ 17.82 GFLOPS | Progress: (12/20) | 14.79 s
-[Task 21/25] Current/Best: 14.33/ 18.48 GFLOPS | Progress: (16/20) | 17.26 s
-[Task 21/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (20/20) | 20.05 s
+[Task 21/25] Current/Best: 13.21/ 20.42 GFLOPS | Progress: (4/20) | 4.79 s
+[Task 21/25] Current/Best: 14.03/ 20.42 GFLOPS | Progress: (8/20) | 7.58 s
+[Task 21/25] Current/Best: 16.66/ 20.42 GFLOPS | Progress: (12/20) | 9.24 s
+[Task 21/25] Current/Best: 14.10/ 20.42 GFLOPS | Progress: (16/20) | 12.53 s
+[Task 21/25] Current/Best: 11.02/ 22.81 GFLOPS | Progress: (20/20) | 15.39 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (4/20) | 6.38 s
-[Task 22/25] Current/Best: 10.50/ 18.05 GFLOPS | Progress: (8/20) | 8.30 s
-[Task 22/25] Current/Best: 16.24/ 18.05 GFLOPS | Progress: (12/20) | 11.71 s
-[Task 22/25] Current/Best: 12.49/ 18.05 GFLOPS | Progress: (16/20) | 15.16 s
-[Task 22/25] Current/Best: 16.34/ 18.05 GFLOPS | Progress: (20/20) | 17.02 s Done.
+[Task 22/25] Current/Best: 6.15/ 11.66 GFLOPS | Progress: (4/20) | 4.95 s
+[Task 22/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (8/20) | 6.95 s
+[Task 22/25] Current/Best: 15.09/ 20.86 GFLOPS | Progress: (12/20) | 8.75 s
+[Task 22/25] Current/Best: 10.56/ 20.86 GFLOPS | Progress: (16/20) | 10.60 s
+[Task 22/25] Current/Best: 14.48/ 20.86 GFLOPS | Progress: (20/20) | 12.82 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 10.29/ 22.56 GFLOPS | Progress: (4/20) | 6.06 s
-[Task 23/25] Current/Best: 18.68/ 22.56 GFLOPS | Progress: (8/20) | 8.95 s
-[Task 23/25] Current/Best: 9.39/ 22.56 GFLOPS | Progress: (12/20) | 12.35 s
-[Task 23/25] Current/Best: 11.73/ 22.56 GFLOPS | Progress: (16/20) | 15.77 s
-[Task 23/25] Current/Best: 11.97/ 22.56 GFLOPS | Progress: (20/20) | 18.20 s Done.
+[Task 23/25] Current/Best: 12.06/ 12.06 GFLOPS | Progress: (4/20) | 12.15 s
+[Task 23/25] Current/Best: 16.85/ 18.27 GFLOPS | Progress: (8/20) | 14.79 s
+[Task 23/25] Current/Best: 17.75/ 22.36 GFLOPS | Progress: (12/20) | 17.72 s
+[Task 23/25] Current/Best: 21.49/ 22.81 GFLOPS | Progress: (16/20) | 21.61 s
+[Task 23/25] Current/Best: 2.69/ 22.81 GFLOPS | Progress: (20/20) | 24.95 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 9.79/ 9.79 GFLOPS | Progress: (4/20) | 13.46 s Done.
+[Task 24/25] Current/Best: 1.55/ 3.26 GFLOPS | Progress: (4/20) | 10.17 s
+[Task 24/25] Current/Best: 9.92/ 9.92 GFLOPS | Progress: (8/20) | 21.13 s
+[Task 24/25] Current/Best: 6.31/ 9.92 GFLOPS | Progress: (12/20) | 32.12 s Done.
Done.
-[Task 24/25] Current/Best: 7.31/ 9.79 GFLOPS | Progress: (8/20) | 25.72 s
-[Task 24/25] Current/Best: 3.07/ 9.79 GFLOPS | Progress: (12/20) | 38.42 s
-[Task 24/25] Current/Best: 0.00/ 9.79 GFLOPS | Progress: (16/20) | 50.48 s
-[Task 24/25] Current/Best: 4.38/ 9.79 GFLOPS | Progress: (20/20) | 63.46 s
+[Task 24/25] Current/Best: 9.64/ 9.92 GFLOPS | Progress: (16/20) | 42.77 s
+[Task 24/25] Current/Best: 0.57/ 9.92 GFLOPS | Progress: (20/20) | 48.06 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 7.51/ 8.15 GFLOPS | Progress: (4/20) | 6.35 s Done.
+[Task 25/25] Current/Best: 1.54/ 8.70 GFLOPS | Progress: (4/20) | 13.78 s Done.
-[Task 25/25] Current/Best: 3.51/ 8.15 GFLOPS | Progress: (8/20) | 11.40 s
-[Task 25/25] Current/Best: 4.56/ 9.25 GFLOPS | Progress: (12/20) | 20.51 s
-[Task 25/25] Current/Best: 7.54/ 9.25 GFLOPS | Progress: (16/20) | 31.47 s
-[Task 25/25] Current/Best: 7.71/ 9.25 GFLOPS | Progress: (20/20) | 42.45 s
+[Task 25/25] Current/Best: 2.98/ 8.70 GFLOPS | Progress: (8/20) | 24.75 s
+[Task 25/25] Current/Best: 1.55/ 8.70 GFLOPS | Progress: (12/20) | 35.72 s
+[Task 25/25] Current/Best: 1.55/ 8.70 GFLOPS | Progress: (16/20) | 46.43 s
+[Task 25/25] Current/Best: 3.59/ 8.70 GFLOPS | Progress: (20/20) | 52.86 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -948,7 +948,7 @@ 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=0.621103
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -986,8 +986,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 420.10544814999776, 'median': 419.11991549999357, 'std': 3.924647276829995}
-unoptimized: {'mean': 516.5989671299997, 'median': 516.4876506499979, 'std': 1.4108379840399878}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 434.47758615999646, 'median': 434.093213150004, 'std': 1.7515361448761324}
+unoptimized: {'mean': 515.5682691700019, 'median': 515.9838409999963, 'std': 1.7782090558300219}
</pre></div>
</div>
</div>
@@ -1001,7 +1001,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 13 minutes 7.395 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 41.015 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 0e05a430a2..e668de36cc 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.298e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.255e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 19d9834e34..49526198e6 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x24299f90)), stage(b, placeholder(b, 0x2583b830)), 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, 0x111b85a0)), stage(b, placeholder(b, 0x5f6f470)), 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 1fc40b00e4..fc97786960 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:37.274</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:31.629</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>13:07.395</p></td>
+<td><p>12:41.015</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>01:28.627</p></td>
+<td><p>01:32.606</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.691</p></td>
+<td><p>01:01.617</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:37.337</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
+<td><p>00:37.269</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>00:20.916</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
+<td><p>00:36.678</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>00:01.239</p></td>
+<td><p>00:01.412</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>00:00.877</p></td>
+<td><p>00:00.857</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>00:00.190</p></td>
+<td><p>00:00.176</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index e328946e01..160956ac2d 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -554,8 +554,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -610,7 +610,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
</pre></div>
</div>
</div>
@@ -649,7 +649,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000026
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.59015999847179e-06 1.0
- naive 6.706499999999999e-06 0.8835782119679021
-parallel 9.463599999999999e-06 1.2468248366181225
- vector 2.45834e-05 3.2388513555642624
+ numpy 7.4787199991988015e-06 1.0
+ naive 7.5044e-06 1.003433742780041
+parallel 8.226799999999999e-06 1.100027812363792
+ vector 2.6062200000000003e-05 3.4848476748416917
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019188
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019077
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.348043
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.447589
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.314236
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.297712
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.354639
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.340880
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.120555
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116791
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108701
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108593
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111046
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110738
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146355
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146589
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3480426914999994 1.0
- blocking 0.3142360954 0.09385665726359513
- vectorization 0.3546392053 0.10592433788265511
-loop permutation 0.1205546086 0.036007488466638635
- array packing 0.10870069020000002 0.032466936719764354
- block caching 0.11104589169999998 0.033167406133118596
- parallelization 0.1463547486 0.04371352521028629
+ none 3.4475891644 1.0
+ blocking 0.2977117138 0.08635359365732667
+ vectorization 0.3408795012 0.09887474549460269
+loop permutation 0.1167912378 0.03387620514822152
+ array packing 0.1085934579 0.031498375450689474
+ block caching 0.1107381693 0.032120465641175745
+ parallelization 0.1465888387 0.04251923060139665
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.691 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.617 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>