You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/02 03:35:10 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@b723d22b36ac72512c539f190de7136f2d9ad51f)
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 d492f72f1 deploying docs (apache/tvm@b723d22b36ac72512c539f190de7136f2d9ad51f)
d492f72f1 is described below
commit d492f72f199b2ffbc3d56a0e50e18bc5358ad08f
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Aug 2 03:35:05 2022 +0000
deploying docs (apache/tvm@b723d22b36ac72512c539f190de7136f2d9ad51f)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../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 | 507 ++++-----------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 87 +++-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 40 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 18 +-
docs/how_to/compile_models/from_pytorch.html | 5 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 30 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 24 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../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 | 42 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
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 | 507 ++++-----------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 87 +++-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++---
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +++++------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 20 +-
docs/tutorial/tensor_expr_get_started.html | 40 +-
121 files changed, 1092 insertions(+), 1688 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 0d90ae6db..a9a52af4c 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.752 seconds)
+ **Total running time of the script:** ( 1 minutes 0.684 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 2d99674cf..cfefbd2f2 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa1c023ab-551e-45cd-9ae8-a4ef5cac86e5 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1b5c2de6-7b24-4467-8775-0be4f73b0df5 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 380a8f6a6..b773a7f38 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 19.8MB/s]
20%|#9 | 8.23M/41.5M [00:00<00:02, 16.3MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:01, 25.6MB/s]
41%|#### | 17.0M/41.5M [00:00<00:01, 24.4MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.8MB/s]
62%|######1 | 25.7M/41.5M [00:01<00:00, 30.3MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 34.4MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 41.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 32.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:01, 31.3MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 39.7MB/s]
45%|####4 | 18.5M/41.5M [00:00<00:00, 37.3MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 34.0MB/s]
62%|######1 | 25.6M/41.5M [00:00<00:00, 29.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
87%|########6 | 36.0M/41.5M [00:01<00:00, 34.1MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 32.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index cb60cdee3..259d257a3 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 247MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
83%|########2 | 37.0M/44.7M [00:00<00:00, 205MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 202MB/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 c49863f3d..dd3114e47 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.210 seconds)
+ **Total running time of the script:** ( 1 minutes 1.164 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 382204d7a..3a1dc8847 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:02.302** total execution time for **how_to_compile_models** files:
+**04:53.303** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:04.752 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.164 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:00.684 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.135 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:38.285 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.715 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:27.903 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.501 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.791 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:24.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.904 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.671 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:20.952 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.606 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.892 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.570 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.293 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.159 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 40e5c5f4b..ba291fd90 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6513 15.6438 15.7711 15.5562 0.0638
+ 14.5041 14.5029 14.6329 14.3705 0.0666
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 f4e66054b..224994215 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.70M/170M [00:00<00:04, 38.7MB/s]
5%|4 | 7.65M/170M [00:00<00:04, 40.3MB/s]
18%|#8 | 31.0M/170M [00:00<00:01, 133MB/s]
30%|##9 | 50.9M/170M [00:00<00:00, 163MB/s]
45%|####5 | 76.7M/170M [00:00<00:00, 202MB/s]
60%|#####9 | 102M/170M [00:00<00:00, 222MB/s]
75%|#######4 | 127M/170M [00:00<00:00, 237MB/s]
90%|######### | 153M/170M [00:00<00:00, 247MB/s]
100%|##########| 170M/170M [00:00<00:00, 205MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.74M/170M [00:00<00:04, 39.2MB/s]
4%|4 | 7.48M/170M [00:00<00:04, 35.9MB/s]
16%|#5 | 26.4M/170M [00:00<00:01, 106MB/s]
22%|##1 | 37.3M/170M [00:00<00:01, 109MB/s]
34%|###3 | 57.4M/170M [00:00<00:00, 145MB/s]
43%|####3 | 73.5M/170M [00:00<00:00, 153MB/s]
52%|#####2 | 88.8M/170M [00:00<00:00, 155MB/s]
61%|######1 | 104M/170M [00:00<00:00, 142MB/s]
69%|######9 | 117M/170M [00:00<00:00, 126MB/s]
78%|#######7 | 132M/170M [00:01<00:00, 134MB/s]
88%|########8 | 149M/170M [00:01<00:00, 147MB/s]
98%|#########8| 167M/170M [00:01<00:00, 156MB/s]
100%|##########| 170M/170M [00:01<00:00, 136MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 55.491 seconds)
+ **Total running time of the script:** ( 2 minutes 47.460 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 9d825b0fe..67d6c9a67 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 174MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 147MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.5382 90.3460 101.3143 90.1115 1.1773
+ 87.8245 87.7726 92.1256 87.5640 0.4514
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.437 seconds)
+ **Total running time of the script:** ( 1 minutes 5.897 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 e922cd918..25bb82edd 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 123.3640 122.9528 129.9980 121.8549 1.4583
+ 114.9413 114.7248 118.6789 113.8433 0.8352
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 2.203 seconds)
+ **Total running time of the script:** ( 1 minutes 55.264 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 cf20060f1..5c5713fa9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.840 seconds)
+ **Total running time of the script:** ( 1 minutes 23.698 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 26127387d..546ed4ba1 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
0%| | 173/132723 [00:00<01:17, 1719.72KB/s]
3%|3 | 4192/132723 [00:00<00:05, 24292.65KB/s]
9%|8 | 11406/132723 [00:00<00:02, 46107.71KB/s]
15%|#4 | 19782/132723 [00:00<00:01, 60951.23KB/s]
21%|##1 | 28161/132723 [00:00<00:01, 69177.81KB/s]
26%|##6 | 35083/132723 [00:00<00:01, 52134.43KB/s]
33%|###2 | 43533/132723 [00:00<00:01, 60797.63KB/s]
38%|###7 | 50177/132723 [00:01<00:02, 31922.43KB/s]
44%|####4 | 58530/132723 [00:01<00:01, 40607.41KB/s]
49%|####8 | 64581/132723 [00:01<00:02, 28131.92KB/s]
52%|#####2 | 69232/132723 [00:01<00:02, 26103.06KB/s]
58%|#####7 | 76351/132723 [00:02<00:01, 29690.10KB/s]
62%|######1 | 81905/132723 [00:02<00:01, 32848.33KB/s]
66%|######6 | 88133/132723 [00:02<00:01, 38289.53KB/s]
70%|####### | 92911/132723 [00:02<00:01, 38346.86KB/s]
73%|#######3 | 97
410/132723 [00:02<00:01, 31566.70KB/s]
76%|#######6 | 101176/132723 [00:02<00:01, 31168.23KB/s]
82%|########2 | 109116/132723 [00:03<00:00, 34044.67KB/s]
86%|########6 | 114680/132723 [00:03<00:00, 36889.83KB/s]
91%|######### | 120571/132723 [00:03<00:00, 41642.95KB/s]
95%|#########4| 125661/132723 [00:03<00:00, 43820.90KB/s]
99%|#########8| 131063/132723 [00:03<00:00, 42377.91KB/s]
100%|##########| 132723/132723 [00:03<00:00, 37849.28KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5299/132723 [00:00<00:02, 52491.33KB/s]
10%|# | 13373/132723 [00:00<00:01, 69039.63KB/s]
15%|#5 | 20284/132723 [00:00<00:02, 54949.51KB/s]
21%|##1 | 28354/132723 [00:00<00:01, 63732.50KB/s]
28%|##7 | 36547/132723 [00:00<00:01, 69693.09KB/s]
34%|###3 | 44597/132723 [00:00<00:01, 73136.89KB/s]
40%|###9 | 52721/132723 [00:00<00:01, 75668.96KB/s]
46%|####5 | 60873/132723 [00:00<00:00, 77472.21KB/s]
52%|#####1 | 68722/132723 [00:01<00:01, 60706.51KB/s]
58%|#####7 | 76908/132723 [00:01<00:00, 66089.16KB/s]
64%|######4 | 85098/132723 [00:01<00:00, 70302.53KB/s]
70%|####### | 93275/132723 [00:01<00:00, 73464.70KB/s]
76%|#######6 | 101444/132723 [00:01<00:00, 75788.53KB/s]
83%|########2 | 109626/132723 [00:01<00:00, 77522.39KB/s]
89%|########8 | 117561/132723 [00:01<00:00, 68235.01KB/s]
95%|########
#4| 125572/132723 [00:01<00:00, 71400.46KB/s]
100%|##########| 132723/132723 [00:01<00:00, 70214.20KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.729 seconds)
+ **Total running time of the script:** ( 2 minutes 26.485 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 a99e05df2..67edb3c95 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:26.999** total execution time for **how_to_deploy_models** files:
+**10:50.841** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:55.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:47.460 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:33.729 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:26.485 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:02.203 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:55.264 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:30.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:23.698 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.437 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.897 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.207 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:27.926 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.736 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.306 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.350 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.799 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 36a2ec578..357e7ff63 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7a247940-8d69-4667-a7d8-7670577ca64e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip233fa0a3-a80f-48ca-adf9-ca3b97ddec76 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -590,7 +590,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
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 995bea231..798c7a98b 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
=================
-**00:40.964** total execution time for **how_to_extend_tvm** files:
+**00:40.588** 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``) | 00:37.823 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.480 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.205 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.174 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.927 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index be65a575e..90980a62d 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6516us [6516us] (45.68%; 45.68%)
- FoldScaleAxis: 7749us [5us] (54.32%; 54.32%)
- FoldConstant: 7744us [1585us] (54.28%; 99.93%)
- InferType: 6159us [6159us] (43.18%; 79.54%)
+ InferType: 6555us [6555us] (46.03%; 46.03%)
+ FoldScaleAxis: 7687us [5us] (53.97%; 53.97%)
+ FoldConstant: 7681us [1553us] (53.94%; 99.93%)
+ InferType: 6128us [6128us] (43.03%; 79.78%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6158us [6158us] (44.67%; 44.67%)
- FoldScaleAxis: 7626us [5us] (55.33%; 55.33%)
- FoldConstant: 7621us [1552us] (55.29%; 99.94%)
- InferType: 6069us [6069us] (44.03%; 79.64%)
+ InferType: 6144us [6144us] (44.70%; 44.70%)
+ FoldScaleAxis: 7601us [5us] (55.30%; 55.30%)
+ FoldConstant: 7597us [1568us] (55.27%; 99.94%)
+ InferType: 6029us [6029us] (43.86%; 79.36%)
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 0405b018f..01bb1621e 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.189487 ms
+ Convolution: 54.103791 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 3f9d076f5..cfa4071f8 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.389695 ms
+ conv2d with tensor core: 10.382363 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 c19ef0def..a13ef12c8 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018346
- Baseline: 3.254176
+ Numpy running time: 0.015112
+ Baseline: 3.385716
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.309036
+ Opt1: 0.296929
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.334143
+ Opt2: 0.320584
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117955
+ Opt3: 0.111998
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112680
+ Opt4: 0.108299
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111372
+ Opt5: 0.099070
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144780
+ Opt6: 0.129248
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 4d0ec9dce..8c9a46ce1 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.042** total execution time for **how_to_optimize_operators** files:
+**00:32.861** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.854 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:30.458 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.215 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.320 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.082 | 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 229006399..719885c98 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:23.739** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:02.638** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:26.576 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:18.069 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.744 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.746 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.666 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:45.497 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.161 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.622 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.965 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.542 | 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 b2de54a89..f83073a6e 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
@@ -240,228 +240,48 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*784)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(threadIdx.x_2*48)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 3)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 5)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 6)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 7)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 8)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 9)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 9)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 10)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 10)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 11)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 11)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 12)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 13)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 14)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 15)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 16)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 17)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 18)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 18)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 19)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 19)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 20)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 20)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 21)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 22)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 23)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 24)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 25)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 26)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 27)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 27)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 28)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 28)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 29)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 29)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 30)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 31)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 32)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 33)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 34)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 35)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 36)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 36)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 37)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 37)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 38)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 38)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 39)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 40)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 41)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 42)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 43)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 44)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 45)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 45)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 46)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 46)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 47)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 47)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 256) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((((rc.outer.outer*98) + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv((threadIdx.x_1 + 17), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 18)*4608)) + (rc.outer.outer*18)) + floormod(threadIdx.x_2, 18))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 46), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 18)*4608)) + (rc.outer.outer*18)) + (floordiv(floormod((threadIdx.x_2 + 8), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 92)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 196)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 4)]), 0f32)
}
}
}
@@ -516,7 +336,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.291 ms
+ Execution time of this operator: 0.378 ms
@@ -564,36 +384,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- 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_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_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=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+ 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=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
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_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_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_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)
@@ -611,16 +431,16 @@ 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=48)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=98)
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=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -638,212 +458,45 @@ 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) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[162];
+ __shared__ float kernel_shared[144];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 256; ++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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- 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 * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ 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 * 98) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) * 48)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 9)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 10)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 11)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 13)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 14)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 16)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 17)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 18)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 18)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 19)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 19)];
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 20)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 20)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 21)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 22)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 23)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 24)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 25)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 26)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 27)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 27)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 28)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 28)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 29)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 29)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 30)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 31)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 32)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 33)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 34)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 35)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 36)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 36)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 37)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 37)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 38)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 38)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 39)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 40)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 41)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 42)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 43)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 44)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 45)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 45)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 46)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 46)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 47)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 47)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+ if (((int)threadIdx.x) < 46) {
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 8) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__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) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 92)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
}
}
@@ -905,7 +558,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 26.576 seconds)
+ **Total running time of the script:** ( 3 minutes 18.069 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 de73122e2..07fa799ea 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8226 9.8169 9.8471 9.8037 0.0181
+ 10.2282 10.2427 10.2551 10.1867 0.0298
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 ed15250c7..0b454dde8 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)
- 759.7369 759.4551 760.3356 759.4199 0.4236
+ 761.4448 760.9117 763.4758 759.9470 1.4891
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.744 seconds)
+ **Total running time of the script:** ( 1 minutes 22.746 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 b692c5fe3..77987bc8a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,30 +397,79 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ }
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i1.outer*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
}
}
}
@@ -476,7 +525,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.458 ms
+ Execution time of this operator: 1.769 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 26aa19560..53eea77cc 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:45.852** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.677** 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``) | 00:45.816 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.645 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 67334dc49..768208644 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 174.07/174.07 result: MeasureResult(costs=(0.0013299487,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.033461809158325, timestamp=1659405351.8943799) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/174.07 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 171.33/171.33 result: MeasureResult(costs=(0.0013511669666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7861168384552002, timestamp=1659405152.7112277) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/171.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 259.66/259.66 result: MeasureResult(costs=(0.0008915628287292817,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4280335903167725, timestamp=1659405352.8098996) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.12/260.12 result: MeasureResult(costs=(0.0008899863038674034,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7162280082702637, timestamp=1659405153.6147745) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.33/259.66 result: MeasureResult(costs=(0.043465329250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8033015727996826, timestamp=1659405357.3562324) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/259.66 result: MeasureResult(costs=(0.069396362,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.549243927001953, timestamp=1659405358.593015) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.27/260.12 result: MeasureResult(costs=(0.04391039975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8151097297668457, timestamp=1659405158.115084) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/260.12 result: MeasureResult(costs=(0.0693521585,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.477893352508545, timestamp=1659405159.3490715) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 27.15/259.66 result: MeasureResult(costs=(0.008527278562499999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3000788688659668, timestamp=1659405369.6813524) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.98/260.12 result: MeasureResult(costs=(0.008275105857142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2979891300201416, timestamp=1659405170.3886118) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001293
+ Time cost of this operator: 0.001236
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 8e9e45b83..5896d3353 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.722 (1, 2, 10, 10, 3) 2 1 [310.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.974 (1, 6, 10, 10) 1 1 [3.066]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.303 (1, 1, 10, 10, 3) 1 1 [0.954]
- Total_time - 314.62 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.726 (1, 2, 10, 10, 3) 2 1 [311.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.043 0.966 (1, 6, 10, 10) 1 1 [3.043]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
+ Total_time - 315.013 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 152.6 98.245 (1, 6, 10, 10, 1) 2 1 [152.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.141 (1, 6, 10, 10) 1 1 [1.772]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.615 (1, 1, 10, 10, 3) 1 1 [0.955]
- Total_time - 155.327 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 194.8 98.673 (1, 6, 10, 10, 1) 2 1 [194.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 0.899 (1, 6, 10, 10) 1 1 [1.774]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.429 (1, 3, 10, 10, 1) 1 1 [0.847]
+ Total_time - 197.42 - - - - -
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 d620c9d2f..b16ae0ef7 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp6fhsojt6/images/random'
+ '/tmp/tmpqayvj1ab/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp6fhsojt6/images/target contains 8144 images
- /tmp/tmp6fhsojt6/images/random contains 5000 images
+ /tmp/tmpqayvj1ab/images/target contains 8144 images
+ /tmp/tmpqayvj1ab/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2041 - accuracy: 0.9263 - val_loss: 0.1161 - val_accuracy: 0.9607
+ 328/328 - 55s - loss: 0.2031 - accuracy: 0.9294 - val_loss: 0.1536 - val_accuracy: 0.9615
Epoch 2/3
- 328/328 - 53s - loss: 0.0947 - accuracy: 0.9650 - val_loss: 0.1161 - val_accuracy: 0.9626
+ 328/328 - 52s - loss: 0.0957 - accuracy: 0.9643 - val_loss: 0.1222 - val_accuracy: 0.9600
Epoch 3/3
- 328/328 - 52s - loss: 0.0614 - accuracy: 0.9767 - val_loss: 0.1058 - val_accuracy: 0.9675
+ 328/328 - 52s - loss: 0.0662 - accuracy: 0.9751 - val_loss: 0.1172 - val_accuracy: 0.9634
- <keras.callbacks.History object at 0x7fe6e4b2a250>
+ <keras.callbacks.History object at 0x7efcd43d57d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 7.677 seconds)
+ **Total running time of the script:** ( 4 minutes 51.692 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 11467c7dc..0b95f4d0c 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:01.334** total execution time for **how_to_work_with_microtvm** files:
+**05:44.321** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:07.677 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:51.692 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.385 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.960 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.964 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.401 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.266 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index cb52de071..d41870d34 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
=================
-**00:41.969** total execution time for **how_to_work_with_relay** files:
+**00:41.381** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:29.994 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.086 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.741 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.639 | 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 c90eec37a..37c84a390 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fe653dd3b00>
+ <function my_cuda_math_rule at 0x7efca8696200>
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 6e5f9c9dd..64080e180 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
=================
-**00:04.025** total execution time for **how_to_work_with_schedules** files:
+**00:04.187** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.881 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.955 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.929 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.993 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.527 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.506 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.097 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.026 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 3e54da1e3..14565e3ad 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp59144gv6/input0.cc'\nsource_filename = \"/tmp/tmp59144gv6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpzr_84a68/input0.cc'\nsource_filename = \"/tmp/tmpzr_84a68/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 66e4e02bb..eb353f105 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
=================
-**00:22.035** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.744** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.029 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.738 | 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 bdf2ad699..ba522fbf3 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 24.03s!
+ resnet18_v1 inference graph built in 22.39s!
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 c45139446..907f50a92 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.68s!
+ yolov3-tiny inference graph built in 15.71s!
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 21622e1c6..8d92aeaf0 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
=================
-**01:33.204** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.434** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.139 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.717 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.065 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.717 | 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 854f07127..0ea0e1606 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
=================
-**00:03.247** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.338** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.850 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.919 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.397 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.419 | 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 7bfa00a26..a80a70491 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
=================
-**00:00.724** total execution time for **topic_vta_tutorials** files:
+**00:00.749** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.391 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.397 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.333 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.351 | 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 ce54b94b9..813c62dc1 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -328,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.769 ms
+ Execution time of this operator: 91.663 ms
@@ -428,7 +428,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-
+ .T
@@ -446,7 +446,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.848 seconds)
+ **Total running time of the script:** ( 1 minutes 3.276 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 eb89048db..dd4255573 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.74/10.74 result: MeasureResult(costs=(0.024988932600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.536369800567627, timestamp=1659404130.1911142) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.95/10.74 result: MeasureResult(costs=(0.0910197508,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.597144365310669, timestamp=1659404131.8109076) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.022756179199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5696594715118408, timestamp=1659404132.867696) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.86/11.80 result: MeasureResult(costs=(0.14425883960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.439789295196533, timestamp=1659404135.879735) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.50/11.80 result: MeasureResult(costs=(0.07677793000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.364466905593872, timestamp=1659404137.900425) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.63/11.80 result: MeasureResult(costs=(0.1643082828,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.802633285522461, timestamp=1659404140.7467308) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.80/11.80 result: MeasureResult(costs=(0.336575252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.500689506530762, timestamp=1659404146.2929685) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 9.97/11.80 result: MeasureResult(costs=(0.026915956599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5758566856384277, timestamp=1659404146.8866026) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.49/11.80 result: MeasureResult(costs=(0.1796936574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.995450496673584, timestamp=1659404150.0023122) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.47/11.80 result: MeasureResult(costs=(0.1085235084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8646361827850342, timestamp=1659404151.9039223) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.29/9.29 result: MeasureResult(costs=(0.028902017600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5932786464691162, timestamp=1659403980.7007995) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.96/9.29 result: MeasureResult(costs=(0.0906982436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5954678058624268, timestamp=1659403982.3122838) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 12.02/12.02 result: MeasureResult(costs=(0.0223243618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5456256866455078, timestamp=1659403983.3486478) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.81/12.02 result: MeasureResult(costs=(0.1480357606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.480104684829712, timestamp=1659403986.3976388) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.77/12.02 result: MeasureResult(costs=(0.0712325436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2739124298095703, timestamp=1659403987.7990823) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.85/12.02 result: MeasureResult(costs=(0.14545264400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4494028091430664, timestamp=1659403990.8073525) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/12.02 result: MeasureResult(costs=(0.3069756668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.031695604324341, timestamp=1659403995.8841174) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.84/12.02 result: MeasureResult(costs=(0.0247634874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5399374961853027, timestamp=1659403996.4438865) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.92/12.02 result: MeasureResult(costs=(0.13962370699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3315341472625732, timestamp=1659403998.8941357) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.81/12.02 result: MeasureResult(costs=(0.0953702032,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6319117546081543, timestamp=1659404000.5854797) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 2888590a4..23ab40ffe 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 485.76568479999986, 'median': 485.4440337500023, 'std': 1.1913165428408141}
+ {'mean': 492.3574661800012, 'median': 492.12807169997177, 'std': 0.9719009953902206}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (4/20) | 6.27 s
[Task 1/25] Current/Best: 6.23/ 17.77 GFLOPS | Progress: (8/20) | 9.24 s
[Task 1/25] Current/Best: 11.71/ 23.11 GFLOPS | Progress: (12/20) | 11.67 s
[Task 1/25] Current/Best: 17.14/ 23.11 GFLOPS | Progress: (16/20) | 13.33 s
[Task 1/25] Current/Best: 11.67/ 24.28 GFLOPS | Progress: (20/20) | 15.07 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.26/ 12.94 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 14.31/ 18.79 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.34 s
[Task 2/25] Current/Best: 12.36/ 21.26 GFLOPS | Progress: (16/20) | 7.58 s
[Task 2/25] Current/Best: 20.17/ 21.26 GFLOPS | Progress: (20/20) | 9.19 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.65/ 10.70 GFLOPS | Progress: (4/20) | 5.79 s
[Task 3/25] Current/Best: 15.86/ 17.18 GFLOPS | Progress: (8/20) | 7.70 s
[Task 3/25] Current/Best: 15.08/ 17.18 GFLOPS | Progress: (12/20) | 9.39 s
[Task 3/25] Current/Best: 7.29/ 24.03 GFLOPS | Progress: (16/20) | 11.27 s
[Task 3/25] Current/Best: 12.75/ 24.03 GFLOPS | Progress: (20/20) | 15.79 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.72/ 20.71 GFLOPS | Progress: (4/20) | 2.36 s
[Task 4/25] Current/Best: 6.93/ 20.71 GFLOPS | Progress: (8/20) | 7.03 s
[Task 4/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (12/20) | 11.98 s
[Task 4/25] Current/Best: 17.33/ 22.71 GFLOPS | Progress: (16/20) | 14.37 s
[Task 4/25] Current/Best: 13.62/ 22.71 GFLOPS | Progress: (20/20) | 16.46 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.95/ 10.59 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.95/ 12.95 GFLOPS | Progress: (8/20) | 4.56 s
[Task 5/25] Current/Best: 11.62/ 17.97 GFLOPS | Progress: (12/20) | 7.70 s
[Task 5/25] Current/Best: 11.96/ 22.80 GFLOPS | Progress: (16/20) | 9.10 s
[Task 5/25] Current/Best: 11.99/ 22.80 GFLOPS | Progress: (20/20) | 11.01 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.67 GFLOPS | Progress: (4/20) | 4.11 s
[Task 6/25] Current/Best: 18.88/ 20.67 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 13.36/ 20.67 GFLOPS | Progress: (12/20) | 7.80 s
[Task 6/25] Current/Best: 20.06/ 20.67 GFLOPS | Progress: (16/20) | 10.03 s
[Task 6/25] Current/Best: 3.75/ 20.67 GFLOPS | Progress: (20/20) | 12.54 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.24/ 12.95 GFLOPS | Progress: (4/20) | 3.62 s
[Task 7/25] Current/Best: 20.33/ 21.13 GFLOPS | Progress: (8/20) | 5.12 s
[Task 7/25] Current/Best: 16.10/ 21.13 GFLOPS | Progress: (12/20) | 7.04 s
[Task 7/25] Current/Best: 12.26/ 21.13 GFLOPS | Progress: (16/20) | 9.06 s
[Task 7/25] Current/Best: 6.43/ 21.70 GFLOPS | Progress: (20/20) | 11.52 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.45/ 14.38 GFLOPS | Progress: (4/20) | 2.88 s
[Task 8/25] Current/Best: 9.74/ 14.38 GFLOPS | Progress: (8/20) | 8.01 s
[Task 8/25] Current/Best: 13.20/ 14.38 GFLOPS | Progress: (12/20) | 14.56 s
[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 16.67 s
[Task 8/25] Current/Best: 20.17/ 20.17 GFLOPS | Progress: (20/20) | 23.83 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.30/ 15.89 GFLOPS | Progress: (4/20) | 11.96 s
[Task 9/25] Current/Best: 23.44/ 23.44 GFLOPS | Progress: (8/20) | 13.71 s
[Task 9/25] Current/Best: 8.24/ 23.44 GFLOPS | Progress: (12/20) | 16.26 s
[Task 9/25] Current/Best: 17.93/ 23.44 GFLOPS | Progress: (16/20) | 19.12 s
[Task 9/25] Current/Best: 9.22/ 23.44 GFLOPS | Progress: (20/20) | 27.68 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.57 s
[Task 10/25] Current/Best: 15.55/ 18.21 GFLOPS | Progress: (8/20) | 4.19 s
[Task 10/25] Current/Best: 13.14/ 18.95 GFLOPS | Progress: (12/20) | 5.73 s
[Task 10/25] Current/Best: 19.14/ 20.43 GFLOPS | Progress: (16/20) | 6.84 s
[Task 10/25] Current/Best: 9.04/ 20.43 GFLOPS | Progress: (20/20
) | 8.37 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.96/ 18.09 GFLOPS | Progress: (4/20) | 3.41 s
[Task 11/25] Current/Best: 16.93/ 18.09 GFLOPS | Progress: (8/20) | 6.23 s
[Task 11/25] Current/Best: 18.00/ 18.09 GFLOPS | Progress: (12/20) | 8.33 s
[Task 11/25] Current/Best: 13.47/ 21.15 GFLOPS | Progress: (16/20) | 11.32 s
[Task 11/25] Current/Best: 19.40/ 21.61 GFLOPS | Progress: (20/20) | 13.43 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.79/ 18.09 GFLOPS | Progress: (4/20) | 5.78 s
[Task 12/25] Current/Best: 5.31/ 18.09 GFLOPS | Progress: (8/20) | 9.76 s
[Task 12/25] Current/Best: 18.83/ 18.91 GFLOPS | Progress: (12/20) | 11.72 s
[Task 12/25] Current/Best: 15.15/ 18.91 GFLOPS | Progress: (16/20) | 14.69 s
[Task 12/25] Current/Best: 15.18/ 19.05 GFLOPS | Progress: (20/20) | 16.60 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.84/ 17.24 GFLOPS | Progress: (4/20) | 3.76 s
[Task 13/25] Current/Best: 16.11/ 21.01 GFLOPS | Progress: (8/20) | 6.38 s
[Task 13/25] Current/Best: 19.52/ 21.11 GFLOPS | Progress: (12/20) | 9.38 s
[Task 13/25] Current/Best: 12.21/ 21.11 GFLOPS | Progress: (16/20) | 12.86 s
[Task 13/25] Current/Best: 18.56/ 21.11 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.55/ 13.55 GFLOPS | Progress: (4/20) | 3.39 s
[Task 14/25] Current/Best: 6.06/ 13.55 GFLOPS | Progress: (8/20) | 5.56 s
[Task 14/25] Current/Best: 21.14/ 21.14 GFLOPS | Progress: (12/20) | 8.26 s
[Task 14/25] Current/Best: 16.88/ 21.14 GFLOPS | Progress: (16/20) | 9.91 s Done.
-
[Task 14/25] Current/Best: 17.11/ 21.14 GFLOPS | Progress: (20/20) | 11.66 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.63 GFLOPS | Progress: (4/20) | 2.75 s
[Task 15/25] Current/Best: 14.42/ 18.06 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 10.38/ 22.26 GFLOPS | Progress: (12/20) | 6.37 s
[Task 15/25] Current/Best: 20.40/ 22.26 GFLOPS | Progress: (16/20) | 9.59 s
[Task 15/25] Current/Best: 9.71/ 22.26 GFLOPS | Progress: (20/20) | 10.61 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (4/20) | 2.95 s
[Task 16/25] Current/Best: 3.04/ 20.44 GFLOPS | Progress: (8/20) | 4.57 s
[Task 16/25] Current/Best: 19.47/ 20.44 GFLOPS | Progress: (12/20) | 5.77 s
[Task 16/25] Current/Best: 18.04/ 20.44 GFLOPS | Progress: (16/20) |
7.16 s
[Task 16/25] Current/Best: 10.01/ 22.27 GFLOPS | Progress: (20/20) | 9.32 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.49/ 17.03 GFLOPS | Progress: (4/20) | 4.86 s
[Task 17/25] Current/Best: 14.44/ 23.18 GFLOPS | Progress: (8/20) | 7.65 s
[Task 17/25] Current/Best: 16.77/ 23.18 GFLOPS | Progress: (12/20) | 9.70 s
[Task 17/25] Current/Best: 16.49/ 23.18 GFLOPS | Progress: (16/20) | 11.92 s
[Task 17/25] Current/Best: 10.02/ 23.18 GFLOPS | Progress: (20/20) | 14.09 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.23/ 17.96 GFLOPS | Progress: (4/20) | 3.83 s
[Task 18/25] Current/Best: 10.61/ 19.86 GFLOPS | Progress: (8/20) | 7.57 s
[Task 18/25] Current/Best: 18.59/ 19.86 GFLOPS | Progress: (12/20) | 9.51 s
[Task 18/25] Current/Best: 10.02/ 19.86 GFLOPS | Progress: (16/20) | 13.45 s
[Task 18/25] Current/Best: 19.97/ 19.97 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.09/ 20.06 GFLOPS | Progress: (4/20) | 6.23 s
[Task 19/25] Current/Best: 2.61/ 20.06 GFLOPS | Progress: (8/20) | 9.53 s
[Task 19/25] Current/Best: 17.61/ 20.79 GFLOPS | Progress: (12/20) | 12.49 s
[Task 19/25] Current/Best: 15.50/ 20.79 GFLOPS | Progress: (16/20) | 15.49 s
[Task 19/25] Current/Best: 2.69/ 22.89 GFLOPS | Progress: (20/20) | 18.25 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.00/ 15.16 GFLOPS | Progress: (4/20) | 3.36 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 6.84 s
[Task 1/25] Current/Best: 6.17/ 17.55 GFLOPS | Progress: (8/20) | 9.34 s
[Task 1/25] Current/Best: 11.56/ 22.78 GFLOPS | Progress: (12/20) | 11.83 s
[Task 1/25] Current/Best: 16.79/ 22.82 GFLOPS | Progress: (16/20) | 13.51 s
[Task 1/25] Current/Best: 11.58/ 23.90 GFLOPS | Progress: (20/20) | 15.25 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.32/ 12.99 GFLOPS | Progress: (4/20) | 3.76 s
[Task 2/25] Current/Best: 14.25/ 17.28 GFLOPS | Progress: (8/20) | 5.05 s
[Task 2/25] Current/Best: 20.83/ 20.83 GFLOPS | Progress: (12/20) | 6.40 s
[Task 2/25] Current/Best: 12.32/ 20.83 GFLOPS | Progress: (16/20) | 7.65 s
[Task 2/25] Current/Best: 19.15/ 20.83 GFLOPS | Progress: (20/20) | 9.28 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.87 s
[Task 3/25] Current/Best: 15.60/ 16.87 GFLOPS | Progress: (8/20) | 7.81 s
[Task 3/25] Current/Best: 14.91/ 16.87 GFLOPS | Progress: (12/20) | 9.52 s
[Task 3/25] Current/Best: 7.20/ 23.82 GFLOPS | Progress: (16/20) | 11.43 s
[Task 3/25] Current/Best: 12.68/ 23.82 GFLOPS | Progress: (20/20) | 15.98 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.57/ 20.45 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.85/ 20.45 GFLOPS | Progress: (8/20) | 7.11 s
[Task 4/25] Current/Best: 22.45/ 22.45 GFLOPS | Progress: (12/20) | 12.13 s
[Task 4/25] Current/Best: 16.76/ 22.45 GFLOPS | Progress: (16/20) | 14.53 s
[Task 4/25] Current/Best: 13.40/ 22.45 GFLOPS | Progress: (20/20) | 16.63 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.64/ 10.29 GFLOPS | Progress: (4/20) | 2.59 s
[Task 5/25] Current/Best: 11.74/ 12.69 GFLOPS | Progress: (8/20) | 4.69 s
[Task 5/25] Current/Best: 11.76/ 17.42 GFLOPS | Progress: (12/20) | 7.91 s
[Task 5/25] Current/Best: 11.87/ 22.53 GFLOPS | Progress: (16/20) | 9.32 s
[Task 5/25] Current/Best: 12.07/ 22.53 GFLOPS | Progress: (20/20) | 11.19 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.23/ 20.68 GFLOPS | Progress: (4/20) | 4.12 s
[Task 6/25] Current/Best: 18.98/ 20.68 GFLOPS | Progress: (8/20) | 5.89 s
[Task 6/25] Current/Best: 13.28/ 20.68 GFLOPS | Progress: (12/20) | 7.83 s
[Task 6/25] Current/Best: 20.03/ 20.68 GFLOPS | Progress: (16/20) | 10.08 s
[Task 6/25] Current/Best: 3.71/ 20.68 GFLOPS | Progress: (20/20) | 12.58 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.92 GFLOPS | Progress: (4/20) | 3.58 s
[Task 7/25] Current/Best: 20.35/ 21.08 GFLOPS | Progress: (8/20) | 5.07 s
[Task 7/25] Current/Best: 16.17/ 21.08 GFLOPS | Progress: (12/20) | 6.96 s
[Task 7/25] Current/Best: 12.29/ 21.08 GFLOPS | Progress: (16/20) | 8.99 s
[Task 7/25] Current/Best: 6.32/ 21.75 GFLOPS | Progress: (20/20) | 11.43 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.93/ 14.15 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.64/ 14.15 GFLOPS | Progress: (8/20) | 8.07 s
[Task 8/25] Current/Best: 12.68/ 14.15 GFLOPS | Progress: (12/20) | 14.57 s
[Task 8/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (16/20) | 16.65 s
[Task 8/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (20/20) | 23.80 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.29/ 14.29 GFLOPS | Progress: (4/20) | 11.96 s
[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.68 s
[Task 9/25] Current/Best: 8.25/ 23.46 GFLOPS | Progress: (12/20) | 16.19 s
[Task 9/25] Current/Best: 18.00/ 23.46 GFLOPS | Progress: (16/20) | 19.07 s
[Task 9/25] Current/Best: 9.26/ 23.46 GFLOPS | Progress: (20/20) | 27.74 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (4/20) | 2.57 s
[Task 10/25] Current/Best: 15.52/ 18.19 GFLOPS | Progress: (8/20) | 4.20 s
[Task 10/25] Current/Best: 12.57/ 18.78 GFLOPS | Progress: (12/20) | 5.76 s
[Task 10/25] Current/Best: 19.13/ 20.16 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.85/ 20.16 GFLOPS | Progress: (20/20
) | 8.41 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.33/ 18.17 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 15.53/ 18.17 GFLOPS | Progress: (8/20) | 6.17 s
[Task 11/25] Current/Best: 18.09/ 18.17 GFLOPS | Progress: (12/20) | 8.25 s
[Task 11/25] Current/Best: 13.44/ 21.18 GFLOPS | Progress: (16/20) | 11.19 s
[Task 11/25] Current/Best: 19.49/ 21.59 GFLOPS | Progress: (20/20) | 13.29 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 18.02 GFLOPS | Progress: (4/20) | 5.77 s
[Task 12/25] Current/Best: 5.26/ 18.02 GFLOPS | Progress: (8/20) | 9.72 s
[Task 12/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (12/20) | 11.69 s
[Task 12/25] Current/Best: 15.40/ 18.84 GFLOPS | Progress: (16/20) | 14.62 s
[Task 12/25] Current/Best: 15.14/ 18.84 GFLOPS | Progress: (20/20) | 16.55 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.68/ 17.35 GFLOPS | Progress: (4/20) | 3.77 s
[Task 13/25] Current/Best: 16.10/ 21.19 GFLOPS | Progress: (8/20) | 6.36 s
[Task 13/25] Current/Best: 19.53/ 21.74 GFLOPS | Progress: (12/20) | 9.40 s
[Task 13/25] Current/Best: 12.30/ 21.74 GFLOPS | Progress: (16/20) | 12.78 s
[Task 13/25] Current/Best: 18.51/ 21.74 GFLOPS | Progress: (20/20) | 15.12 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.65/ 13.65 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.03/ 13.65 GFLOPS | Progress: (8/20) | 5.59 s
[Task 14/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (12/20) | 8.30 s
[Task 14/25] Current/Best: 17.19/ 19.96 GFLOPS | Progress: (16/20) | 9.96 s Done.
+
[Task 14/25] Current/Best: 17.18/ 19.96 GFLOPS | Progress: (20/20) | 11.76 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.12/ 17.70 GFLOPS | Progress: (4/20) | 2.72 s
[Task 15/25] Current/Best: 14.41/ 18.02 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.40/ 22.40 GFLOPS | Progress: (12/20) | 6.33 s
[Task 15/25] Current/Best: 20.41/ 22.40 GFLOPS | Progress: (16/20) | 9.46 s
[Task 15/25] Current/Best: 9.70/ 22.40 GFLOPS | Progress: (20/20) | 10.48 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (4/20) | 2.99 s
[Task 16/25] Current/Best: 3.01/ 20.63 GFLOPS | Progress: (8/20) | 4.60 s
[Task 16/25] Current/Best: 19.12/ 20.63 GFLOPS | Progress: (12/20) | 5.81 s
[Task 16/25] Current/Best: 17.73/ 20.63 GFLOPS | Progress: (16/20) |
7.19 s
[Task 16/25] Current/Best: 10.00/ 22.15 GFLOPS | Progress: (20/20) | 9.34 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.82/ 18.78 GFLOPS | Progress: (4/20) | 4.81 s
[Task 17/25] Current/Best: 14.42/ 23.34 GFLOPS | Progress: (8/20) | 7.69 s
[Task 17/25] Current/Best: 17.00/ 23.34 GFLOPS | Progress: (12/20) | 9.76 s
[Task 17/25] Current/Best: 16.52/ 23.34 GFLOPS | Progress: (16/20) | 12.00 s
[Task 17/25] Current/Best: 10.06/ 23.34 GFLOPS | Progress: (20/20) | 14.15 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.11/ 17.24 GFLOPS | Progress: (4/20) | 3.81 s
[Task 18/25] Current/Best: 10.60/ 19.11 GFLOPS | Progress: (8/20) | 7.48 s
[Task 18/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (12/20) | 9.41 s
[Task 18/25] Current/Best: 10.08/ 19.37 GFLOPS | Progress: (16/20) | 13.30 s
[Task 18/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 14.81 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.24/ 20.42 GFLOPS | Progress: (4/20) | 5.98 s
[Task 19/25] Current/Best: 2.61/ 20.42 GFLOPS | Progress: (8/20) | 9.35 s
[Task 19/25] Current/Best: 20.00/ 21.79 GFLOPS | Progress: (12/20) | 12.35 s
[Task 19/25] Current/Best: 14.14/ 21.79 GFLOPS | Progress: (16/20) | 15.41 s
[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 18.23 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.97/ 15.26 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-
[Task 20/25] Current/Best: 10.39/ 15.16 GFLOPS | Progress: (8/20) | 6.78 s
[Task 20/25] Current/Best: 2.32/ 16.72 GFLOPS | Progress: (12/20) | 10.79 s
[Task 20/25] Current/Best: 11.81/ 16.72 GFLOPS | Progress: (16/20) | 14.77 s
[Task 20/25] Current/Best: 13.52/ 21.70 GFLOPS | Progress: (20/20) | 16.90 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.78 GFLOPS | Progress: (4/20) | 3.32 s
[Task 21/25] Current/Best: 14.48/ 17.78 GFLOPS | Progress: (8/20) | 4.99 s
[Task 21/25] Current/Best: 1.61/ 17.78 GFLOPS | Progress: (12/20) | 7.19 s
[Task 21/25] Current/Best: 16.24/ 17.78 GFLOPS | Progress: (16/20) | 10.76 s
[Task 21/25] Current/Best: 4.47/ 17.78 GFLOPS | Progress: (20/20) | 18.17 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.93 GFLOPS | Progress: (4/20
) | 2.72 s
[Task 22/25] Current/Best: 9.01/ 21.85 GFLOPS | Progress: (8/20) | 4.74 s
[Task 22/25] Current/Best: 20.04/ 21.85 GFLOPS | Progress: (12/20) | 7.12 s
[Task 22/25] Current/Best: 15.28/ 21.85 GFLOPS | Progress: (16/20) | 9.24 s
[Task 22/25] Current/Best: 15.07/ 21.85 GFLOPS | Progress: (20/20) | 10.98 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.42/ 20.29 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 15.91/ 20.29 GFLOPS | Progress: (8/20) | 6.63 s
[Task 23/25] Current/Best: 20.71/ 21.42 GFLOPS | Progress: (12/20) | 8.51 s
[Task 23/25] Current/Best: 6.10/ 21.42 GFLOPS | Progress: (16/20) | 15.65 s
[Task 23/25] Current/Best: 7.72/ 21.42 GFLOPS | Progress: (20/20) | 19.89 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.45/ 8.45 GFLOPS | Progress: (4/20) | 11.83 s
[Task 24/25] Current/Best: 1.99/ 8.45 GFLOPS | Progress: (8/20) | 22.84 s
[Task 24/25] Current/Best: 4.46/ 8.45 GFLOPS | Progress: (12/20) | 34.38 s Done.
-
[Task 24/25] Current/Best: 7.24/ 8.93 GFLOPS | Progress: (16/20) | 40.10 s
[Task 24/25] Current/Best: 3.32/ 8.93 GFLOPS | Progress: (20/20) | 46.06 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.90 GFLOPS | Progress: (4/20) | 11.62 s
[Task 25/25] Current/Best: 5.74/ 7.82 GFLOPS | Progress: (8/20) | 22.92 s
[Task 25/25] Current/Best: 5.99/ 7.82 GFLOPS | Progress: (12/20) | 34.40 s
[Task 25/25] Current/Best: 5.83/ 9.34 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.93/ 9.34 GFLOPS | Progress: (20/20) | 46.83 s
+
[Task 20/25] Current/Best: 9.69/ 15.26 GFLOPS | Progress: (8/20) | 6.71 s
[Task 20/25] Current/Best: 2.31/ 16.53 GFLOPS | Progress: (12/20) | 10.58 s
[Task 20/25] Current/Best: 12.22/ 16.53 GFLOPS | Progress: (16/20) | 14.49 s
[Task 20/25] Current/Best: 12.09/ 22.22 GFLOPS | Progress: (20/20) | 16.62 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.72 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.66/ 17.72 GFLOPS | Progress: (8/20) | 4.91 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.04 s
[Task 21/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (16/20) | 10.56 s
[Task 21/25] Current/Best: 4.46/ 18.08 GFLOPS | Progress: (20/20) | 17.81 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.71/ 16.97 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.63/ 21.94 GFLOPS | Progress: (8/20) | 4.70 s
[Task 22/25] Current/Best: 19.97/ 21.94 GFLOPS | Progress: (12/20) | 7.10 s
[Task 22/25] Current/Best: 15.38/ 21.94 GFLOPS | Progress: (16/20) | 9.21 s
[Task 22/25] Current/Best: 13.86/ 21.94 GFLOPS | Progress: (20/20) | 10.94 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.64/ 20.93 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 14.27/ 20.93 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 21.05/ 21.89 GFLOPS | Progress: (12/20) | 8.36 s
[Task 23/25] Current/Best: 6.47/ 21.89 GFLOPS | Progress: (16/20) | 15.30 s
[Task 23/25] Current/Best: 7.94/ 21.89 GFLOPS | Progress: (20/20) | 19.48 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.09/ 8.09 GFLOPS | Progress: (4/20) | 11.79 s
[Task 24/25] Current/Best: 3.65/ 8.09 GFLOPS | Progress: (8/20) | 23.02 s
[Task 24/25] Current/Best: 4.58/ 8.09 GFLOPS | Progress: (12/20) | 33.72 s Done.
+
[Task 24/25] Current/Best: 6.17/ 8.95 GFLOPS | Progress: (16/20) | 39.32 s
[Task 24/25] Current/Best: 3.43/ 8.95 GFLOPS | Progress: (20/20) | 45.23 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.57/ 2.79 GFLOPS | Progress: (4/20) | 11.57 s
[Task 25/25] Current/Best: 5.91/ 8.24 GFLOPS | Progress: (8/20) | 22.80 s
[Task 25/25] Current/Best: 6.02/ 8.24 GFLOPS | Progress: (12/20) | 34.08 s
[Task 25/25] Current/Best: 5.84/ 8.52 GFLOPS | Progress: (16/20) | 35.94 s
[Task 25/25] Current/Best: 2.89/ 9.36 GFLOPS | Progress: (20/20) | 46.58 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 407.0159230499962, 'median': 407.0427203999998, 'std': 0.7926061920392635}
- unoptimized: {'mean': 485.76568479999986, 'median': 485.4440337500023, 'std': 1.1913165428408141}
+ optimized: {'mean': 390.9319189100097, 'median': 390.9034845500628, 'std': 0.823910532986542}
+ unoptimized: {'mean': 492.3574661800012, 'median': 492.12807169997177, 'std': 0.9719009953902206}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 26.603 seconds)
+ **Total running time of the script:** ( 10 minutes 21.075 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 50631a0f8..a606717f9 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.265e-07 secs/op
+ 1.243e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index a1c8d2af3..800ad7f1d 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x4bcc5d0)), stage(b, placeholder(b, 0xb3ef0d0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
+ [stage(a, placeholder(a, 0xbbdefa0)), stage(b, placeholder(b, 0x27437b20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index a3c2fea93..a893b8e98 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:24.712** total execution time for **tutorial** files:
+**13:17.097** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:26.603 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:21.075 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:01.848 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:03.276 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.403 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.549 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.464 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:29.207 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.256 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.372 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.271 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.777 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.702 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.680 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.158 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.153 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 90c3af628..c7baf2912 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000025
+ vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.794269999976677e-06 1.0
- naive 5.8309e-06 0.7481008484460313
- parallel 6.055100000000001e-06 0.7768655691961043
- vector 2.46354e-05 3.1607065190291994
+ numpy 8.091600002444465e-06 1.0
+ naive 5.9406e-06 0.734168767389064
+ parallel 5.9968e-06 0.7411142417060127
+ vector 2.44763e-05 3.024902366973866
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017944
+ Numpy running time: 0.015050
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.185733
+ none: 3.307579
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.326560
+ blocking: 0.293194
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.345907
+ vectorization: 0.321184
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.122926
+ loop permutation: 0.115425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.110293
+ array packing: 0.109169
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111173
+ block caching: 0.099342
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.145357
+ parallelization: 0.129176
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.1857328411999997 1.0
- blocking 0.32655993159999996 0.10250700478606097
- vectorization 0.3459066478 0.10857992965590427
- loop permutation 0.12292583400000001 0.03858635991387664
- array packing 0.11029261100000001 0.034620797316593274
- block caching 0.1111726304 0.0348970349811642
- parallelization 0.14535693879999997 0.04562747287536108
+ none 3.3075787489 1.0
+ blocking 0.2931938092 0.08864303209636575
+ vectorization 0.3211839272 0.09710545132351452
+ loop permutation 0.115424887 0.034897094147308454
+ array packing 0.1091687748 0.03300564645250131
+ block caching 0.0993415468 0.030034522030061406
+ parallelization 0.12917559539999998 0.0390544277873837
diff --git a/docs/commit_hash b/docs/commit_hash
index c2e8ae5c5..4bf2b9d14 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-bca0385862d93918fde877ed512c834fc32d80d5
+b723d22b36ac72512c539f190de7136f2d9ad51f
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8451759ca..e42267d81 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.752 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.684 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index efa1bf133..17735e41a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa1c023ab-551e-45cd-9ae8-a4ef5cac86e5 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.zip1b5c2de6-7b24-4467-8775-0be4f73b0df5 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 ba8157154..de2d4a26a 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,15 +432,15 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:01, 19.8MB/s]
- 20%|#9 | 8.23M/41.5M [00:00<00:02, 16.3MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:01, 25.6MB/s]
- 41%|#### | 17.0M/41.5M [00:00<00:01, 24.4MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 31.8MB/s]
- 62%|######1 | 25.7M/41.5M [00:01<00:00, 30.3MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 34.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 41.5MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 32.2MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:01, 31.3MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 39.7MB/s]
+ 45%|####4 | 18.5M/41.5M [00:00<00:00, 37.3MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 34.0MB/s]
+ 62%|######1 | 25.6M/41.5M [00:00<00:00, 29.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
+ 87%|########6 | 36.0M/41.5M [00:01<00:00, 34.1MB/s]
+ 96%|#########6| 40.0M/41.5M [00:01<00:00, 32.5MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 4717593ef..b4e6677f5 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,8 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 247MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:00, 128MB/s]
+ 83%|########2 | 37.0M/44.7M [00:00<00:00, 205MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 202MB/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 a2763a838..500629aac 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.210 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.164 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 f3b0e2d17..6627dd21c 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.302</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:53.303</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:04.752</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:01.164</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:02.210</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:00.684</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:39.135</p></td>
+<td><p>00:38.285</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:27.715</p></td>
+<td><p>00:27.903</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>00:24.501</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:24.791</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:24.353</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:23.904</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>00:22.671</p></td>
+<td><p>00:20.952</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.606</p></td>
+<td><p>00:18.892</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>00:15.067</p></td>
+<td><p>00:14.570</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>00:02.293</p></td>
+<td><p>00:02.159</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index eeb398df5..065d126ab 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6513 15.6438 15.7711 15.5562 0.0638
+ 14.5041 14.5029 14.6329 14.3705 0.0666
</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 92abad744..0c169fcfe 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,15 +436,19 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|2 | 3.70M/170M [00:00<00:04, 38.7MB/s]
- 5%|4 | 7.65M/170M [00:00<00:04, 40.3MB/s]
- 18%|#8 | 31.0M/170M [00:00<00:01, 133MB/s]
- 30%|##9 | 50.9M/170M [00:00<00:00, 163MB/s]
- 45%|####5 | 76.7M/170M [00:00<00:00, 202MB/s]
- 60%|#####9 | 102M/170M [00:00<00:00, 222MB/s]
- 75%|#######4 | 127M/170M [00:00<00:00, 237MB/s]
- 90%|######### | 153M/170M [00:00<00:00, 247MB/s]
-100%|##########| 170M/170M [00:00<00:00, 205MB/s]
+ 2%|2 | 3.74M/170M [00:00<00:04, 39.2MB/s]
+ 4%|4 | 7.48M/170M [00:00<00:04, 35.9MB/s]
+ 16%|#5 | 26.4M/170M [00:00<00:01, 106MB/s]
+ 22%|##1 | 37.3M/170M [00:00<00:01, 109MB/s]
+ 34%|###3 | 57.4M/170M [00:00<00:00, 145MB/s]
+ 43%|####3 | 73.5M/170M [00:00<00:00, 153MB/s]
+ 52%|#####2 | 88.8M/170M [00:00<00:00, 155MB/s]
+ 61%|######1 | 104M/170M [00:00<00:00, 142MB/s]
+ 69%|######9 | 117M/170M [00:00<00:00, 126MB/s]
+ 78%|#######7 | 132M/170M [00:01<00:00, 134MB/s]
+ 88%|########8 | 149M/170M [00:01<00:00, 147MB/s]
+ 98%|#########8| 167M/170M [00:01<00:00, 156MB/s]
+100%|##########| 170M/170M [00:01<00:00, 136MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -539,7 +543,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 55.491 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 47.460 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 f01d0b744..083031a41 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 174MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 147MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +569,7 @@ 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)
- 90.5382 90.3460 101.3143 90.1115 1.1773
+ 87.8245 87.7726 92.1256 87.5640 0.4514
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.437 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.897 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 847fa2217..e72ab1600 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 123.3640 122.9528 129.9980 121.8549 1.4583
+ 114.9413 114.7248 118.6789 113.8433 0.8352
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 2.203 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 55.264 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 f9203e814..26789297a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.840 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.698 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 12e7bdfc6..1a662134e 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,29 +441,23 @@ 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]
- 0%| | 173/132723 [00:00<01:17, 1719.72KB/s]
- 3%|3 | 4192/132723 [00:00<00:05, 24292.65KB/s]
- 9%|8 | 11406/132723 [00:00<00:02, 46107.71KB/s]
- 15%|#4 | 19782/132723 [00:00<00:01, 60951.23KB/s]
- 21%|##1 | 28161/132723 [00:00<00:01, 69177.81KB/s]
- 26%|##6 | 35083/132723 [00:00<00:01, 52134.43KB/s]
- 33%|###2 | 43533/132723 [00:00<00:01, 60797.63KB/s]
- 38%|###7 | 50177/132723 [00:01<00:02, 31922.43KB/s]
- 44%|####4 | 58530/132723 [00:01<00:01, 40607.41KB/s]
- 49%|####8 | 64581/132723 [00:01<00:02, 28131.92KB/s]
- 52%|#####2 | 69232/132723 [00:01<00:02, 26103.06KB/s]
- 58%|#####7 | 76351/132723 [00:02<00:01, 29690.10KB/s]
- 62%|######1 | 81905/132723 [00:02<00:01, 32848.33KB/s]
- 66%|######6 | 88133/132723 [00:02<00:01, 38289.53KB/s]
- 70%|####### | 92911/132723 [00:02<00:01, 38346.86KB/s]
- 73%|#######3 | 97410/132723 [00:02<00:01, 31566.70KB/s]
- 76%|#######6 | 101176/132723 [00:02<00:01, 31168.23KB/s]
- 82%|########2 | 109116/132723 [00:03<00:00, 34044.67KB/s]
- 86%|########6 | 114680/132723 [00:03<00:00, 36889.83KB/s]
- 91%|######### | 120571/132723 [00:03<00:00, 41642.95KB/s]
- 95%|#########4| 125661/132723 [00:03<00:00, 43820.90KB/s]
- 99%|#########8| 131063/132723 [00:03<00:00, 42377.91KB/s]
-100%|##########| 132723/132723 [00:03<00:00, 37849.28KB/s]
+ 4%|3 | 5299/132723 [00:00<00:02, 52491.33KB/s]
+ 10%|# | 13373/132723 [00:00<00:01, 69039.63KB/s]
+ 15%|#5 | 20284/132723 [00:00<00:02, 54949.51KB/s]
+ 21%|##1 | 28354/132723 [00:00<00:01, 63732.50KB/s]
+ 28%|##7 | 36547/132723 [00:00<00:01, 69693.09KB/s]
+ 34%|###3 | 44597/132723 [00:00<00:01, 73136.89KB/s]
+ 40%|###9 | 52721/132723 [00:00<00:01, 75668.96KB/s]
+ 46%|####5 | 60873/132723 [00:00<00:00, 77472.21KB/s]
+ 52%|#####1 | 68722/132723 [00:01<00:01, 60706.51KB/s]
+ 58%|#####7 | 76908/132723 [00:01<00:00, 66089.16KB/s]
+ 64%|######4 | 85098/132723 [00:01<00:00, 70302.53KB/s]
+ 70%|####### | 93275/132723 [00:01<00:00, 73464.70KB/s]
+ 76%|#######6 | 101444/132723 [00:01<00:00, 75788.53KB/s]
+ 83%|########2 | 109626/132723 [00:01<00:00, 77522.39KB/s]
+ 89%|########8 | 117561/132723 [00:01<00:00, 68235.01KB/s]
+ 95%|#########4| 125572/132723 [00:01<00:00, 71400.46KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 70214.20KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -506,7 +500,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.729 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.485 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 0a91b60a5..2eaf60824 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:26.999</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:50.841</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:55.491</p></td>
+<td><p>02:47.460</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:33.729</p></td>
+<td><p>02:26.485</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>02:02.203</p></td>
+<td><p>01:55.264</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>01:30.840</p></td>
+<td><p>01:23.698</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.437</p></td>
+<td><p>01:05.897</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>00:29.207</p></td>
+<td><p>00:27.926</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>00:22.736</p></td>
+<td><p>00:22.306</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>00:22.350</p></td>
+<td><p>00:21.799</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>
-<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/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 60717e50f..abf60950b 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7a247940-8d69-4667-a7d8-7670577ca64e 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.zip233fa0a3-a80f-48ca-adf9-ca3b97ddec76 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>
@@ -676,7 +676,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 5603e7230..e59706d3c 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.964</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.588</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="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>00:37.823</p></td>
+<td><p>00:37.480</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>00:02.205</p></td>
+<td><p>00:02.174</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>
@@ -348,7 +348,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index e9e4be525..e7b84a1d6 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6516us [6516us] (45.68%; 45.68%)
-FoldScaleAxis: 7749us [5us] (54.32%; 54.32%)
- FoldConstant: 7744us [1585us] (54.28%; 99.93%)
- InferType: 6159us [6159us] (43.18%; 79.54%)
+InferType: 6555us [6555us] (46.03%; 46.03%)
+FoldScaleAxis: 7687us [5us] (53.97%; 53.97%)
+ FoldConstant: 7681us [1553us] (53.94%; 99.93%)
+ InferType: 6128us [6128us] (43.03%; 79.78%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6158us [6158us] (44.67%; 44.67%)
-FoldScaleAxis: 7626us [5us] (55.33%; 55.33%)
- FoldConstant: 7621us [1552us] (55.29%; 99.94%)
- InferType: 6069us [6069us] (44.03%; 79.64%)
+InferType: 6144us [6144us] (44.70%; 44.70%)
+FoldScaleAxis: 7601us [5us] (55.30%; 55.30%)
+ FoldConstant: 7597us [1568us] (55.27%; 99.94%)
+ InferType: 6029us [6029us] (43.86%; 79.36%)
</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 5b4aca73f..f7c72c3b3 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.189487 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.103791 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 17e637239..87da5f092 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.389695 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.382363 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 00a52ef73..eb7147139 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018346
-Baseline: 3.254176
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.015112
+Baseline: 3.385716
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.309036
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296929
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334143
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.320584
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117955
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.111998
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112680
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108299
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111372
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.099070
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144780
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.129248
</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 e7797ab92..90b30b4bd 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.042</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:32.861</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.854</p></td>
+<td><p>00:30.458</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>00:01.215</p></td>
+<td><p>00:01.320</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:00.973</p></td>
+<td><p>00:01.082</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 7b2c5b5ba..386631036 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:23.739</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:02.638</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:26.576</p></td>
+<td><p>03:18.069</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>01:23.744</p></td>
+<td><p>01:22.746</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:46.666</p></td>
+<td><p>00:45.497</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>00:28.745</p></td>
+<td><p>00:19.161</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.043</p></td>
+<td><p>00:08.622</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.965</p></td>
+<td><p>00:08.542</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 d474cf52b..e1d887a8f 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
@@ -491,228 +491,48 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [162]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*784)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1120), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1 + 1232), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(threadIdx.x_2*48)] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 3)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 4)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 5)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 1), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 6)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 7)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 8)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 2), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 9)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 9)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 10)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 10)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 11)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 11)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 12)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 13)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 14)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 4), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 15)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 16)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 17)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 5), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 18)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 18)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 19)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 19)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 20)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 20)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 21)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 22)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 23)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 7), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 24)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 25)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 26)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 8), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 27)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 27)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 28)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 28)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 29)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 29)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 30)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 31)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 32)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 10), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 33)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 34)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 35)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 11), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 36)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 36)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 37)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 37)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 38)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 38)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 39)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 40)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 41)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 13), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 42)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 43)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 44)] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floordiv(((floormod(threadIdx.x_2, 3)*16) + 14), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 45)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 45)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 46)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 46)]
- }
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*48) + 47)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 3)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 3)*48)) + 47)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- for (ry.outer.inner: int32, 0, 3) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 8) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((((rc.outer.inner*648) + (rc.inner*81)) + (ry.outer.inner*9)) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*288) + (rc.outer.inner*72)) + (rc.inner*9)) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 256) {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [162], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((rc.outer.outer*98) + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 64), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else((((threadIdx.x_1 < 55) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[(((((rc.outer.outer*98) + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv((threadIdx.x_1 + 17), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [144], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 18)*4608)) + (rc.outer.outer*18)) + floormod(threadIdx.x_2, 18))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 46), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 18)*4608)) + (rc.outer.outer*18)) + (floordiv(floormod((threadIdx.x_2 + 8), 18), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (rc.outer.inner: int32, 0, 2) {
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*81) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*36) + (rc.outer.inner*9)) + (ry.outer.inner*3)) + 92)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 196)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 4)]), 0f32)
}
}
}
@@ -749,7 +569,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.291 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.378 ms
</pre></div>
</div>
</div>
@@ -778,36 +598,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-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_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_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=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+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=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
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_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_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_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)
@@ -825,16 +645,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=48)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=98)
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=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -852,212 +672,45 @@ 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) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[4];
+ __shared__ float pad_temp_shared[162];
+ __shared__ float kernel_shared[144];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 256; ++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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- 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 * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ 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 * 98) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) * 48)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 1) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 2) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 9)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 10)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 11)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 13)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 14)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 4) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 16)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 17)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 5) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 18)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 18)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 19)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 19)];
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 98) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 20)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 20)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 21)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 22)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 23)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 7) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 24)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 25)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 26)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 27)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 27)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 28)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 28)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 29)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 29)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 30)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 31)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 32)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 10) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 33)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 34)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 35)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 11) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 36)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 36)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 37)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 37)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 38)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 38)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 39)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 40)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 41)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 13) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 42)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 43)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 44)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 3) * 16) + 14) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 45)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 45)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 46)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 46)];
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((((int)threadIdx.x) * 48) + 47)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 3) * 48)) + 47)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+ if (((int)threadIdx.x) < 46) {
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((((int)threadIdx.x) + 8) % 18) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__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) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 8; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((((rc_outer_inner * 648) + (rc_inner * 81)) + (ry_outer_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 288) + (rc_outer_inner * 72)) + (rc_inner * 9)) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
- }
- }
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 36) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 92)]));
}
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 196)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 4)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1094,7 +747,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 26.576 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 18.069 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 8ff2df96a..b12ab6979 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8226 9.8169 9.8471 9.8037 0.0181
+ 10.2282 10.2427 10.2551 10.1867 0.0298
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 88b0c51da..c85ca3f80 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.7369 759.4551 760.3356 759.4199 0.4236
+ 761.4448 760.9117 763.4758 759.9470 1.4891
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.744 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.746 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 73687c706..28214a2a1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,30 +625,79 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ }
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = (((i0.inner*512) + (i1.outer*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
}
}
}
@@ -686,7 +735,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.458 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.769 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 25d025cd6..94c8a216f 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.852</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.677</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:45.816</p></td>
+<td><p>00:45.645</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.016</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index ff180ff1b..507681877 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 174.07/174.07 result: MeasureResult(costs=(0.0013299487,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.033461809158325, timestamp=1659405351.8943799) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/174.07 result: Traceback (most recent call last):
+No: 9 GFLOPS: 171.33/171.33 result: MeasureResult(costs=(0.0013511669666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7861168384552002, timestamp=1659405152.7112277) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/171.33 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 259.66/259.66 result: MeasureResult(costs=(0.0008915628287292817,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4280335903167725, timestamp=1659405352.8098996) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.12/260.12 result: MeasureResult(costs=(0.0008899863038674034,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7162280082702637, timestamp=1659405153.6147745) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.33/259.66 result: MeasureResult(costs=(0.043465329250000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8033015727996826, timestamp=1659405357.3562324) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/259.66 result: MeasureResult(costs=(0.069396362,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.549243927001953, timestamp=1659405358.593015) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.27/260.12 result: MeasureResult(costs=(0.04391039975,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8151097297668457, timestamp=1659405158.115084) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/260.12 result: MeasureResult(costs=(0.0693521585,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.477893352508545, timestamp=1659405159.3490715) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 27.15/259.66 result: MeasureResult(costs=(0.008527278562499999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3000788688659668, timestamp=1659405369.6813524) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.98/260.12 result: MeasureResult(costs=(0.008275105857142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2979891300201416, timestamp=1659405170.3886118) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/259.66 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.12 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001293
+Time cost of this operator: 0.001236
</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 c94b80f8e..f9fb3fa62 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.722 (1, 2, 10, 10, 3) 2 1 [310.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.974 (1, 6, 10, 10) 1 1 [3.066]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.303 (1, 1, 10, 10, 3) 1 1 [0.954]
-Total_time - 314.62 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.0 98.726 (1, 2, 10, 10, 3) 2 1 [311.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.043 0.966 (1, 6, 10, 10) 1 1 [3.043]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.308 (1, 1, 10, 10, 3) 1 1 [0.969]
+Total_time - 315.013 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 152.6 98.245 (1, 6, 10, 10, 1) 2 1 [152.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.141 (1, 6, 10, 10) 1 1 [1.772]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.615 (1, 1, 10, 10, 3) 1 1 [0.955]
-Total_time - 155.327 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 194.8 98.673 (1, 6, 10, 10, 1) 2 1 [194.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.774 0.899 (1, 6, 10, 10) 1 1 [1.774]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.429 (1, 3, 10, 10, 1) 1 1 [0.847]
+Total_time - 197.42 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 8a8d4cbb2..06ba5d7bb 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp6fhsojt6/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpqayvj1ab/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp6fhsojt6/images/target contains 8144 images
-/tmp/tmp6fhsojt6/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpqayvj1ab/images/target contains 8144 images
+/tmp/tmpqayvj1ab/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2041 - accuracy: 0.9263 - val_loss: 0.1161 - val_accuracy: 0.9607
+328/328 - 55s - loss: 0.2031 - accuracy: 0.9294 - val_loss: 0.1536 - val_accuracy: 0.9615
Epoch 2/3
-328/328 - 53s - loss: 0.0947 - accuracy: 0.9650 - val_loss: 0.1161 - val_accuracy: 0.9626
+328/328 - 52s - loss: 0.0957 - accuracy: 0.9643 - val_loss: 0.1222 - val_accuracy: 0.9600
Epoch 3/3
-328/328 - 52s - loss: 0.0614 - accuracy: 0.9767 - val_loss: 0.1058 - val_accuracy: 0.9675
+328/328 - 52s - loss: 0.0662 - accuracy: 0.9751 - val_loss: 0.1172 - val_accuracy: 0.9634
-<keras.callbacks.History object at 0x7fe6e4b2a250>
+<keras.callbacks.History object at 0x7efcd43d57d0>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 7.677 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 51.692 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 3d347a1d9..8994fb738 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:01.334</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:44.321</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:07.677</p></td>
+<td><p>04:51.692</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.385</p></td>
+<td><p>00:41.960</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.964</p></td>
+<td><p>00:07.401</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.306</p></td>
+<td><p>00:03.266</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 79bd6c335..e52cf2c02 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.969</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:41.381</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:30.391</p></td>
+<td><p>00:29.994</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>00:10.086</p></td>
+<td><p>00:09.741</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>00:01.485</p></td>
+<td><p>00:01.639</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index d712adf00..ed249737a 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fe653dd3b00>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7efca8696200>
</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 7545b80da..18aa5da1c 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.025</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.187</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.881</p></td>
+<td><p>00:01.955</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.929</p></td>
+<td><p>00:00.993</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>00:00.527</p></td>
+<td><p>00:00.539</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>00:00.506</p></td>
+<td><p>00:00.524</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.100</p></td>
+<td><p>00:00.097</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -360,7 +360,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.027</p></td>
+<td><p>00:00.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index f89472a8c..433d368a6 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp59144gv6/input0.cc'\nsource_filename = \"/tmp/tmp59144gv6/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpzr_84a68/input0.cc'\nsource_filename = \"/tmp/tmpzr_84a68/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7d4a20bf6..1adcc0880 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 4297d3656..409240953 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/bca038586/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index bf277dc70..5f834cf20 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/bca038586/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 4fb8d06d9..641eac6d3 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/bca038586/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index b6abdd9ea..b2e837603 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/bca038586/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index a9b747bb6..c4ed18c35 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/bca038586/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 5130f82fb..4a5f18b54 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/bca038586/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 1e8bd9420..469ce1263 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 1aca0a295..a50d3803e 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 14b971451..af8af13fe 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/bca038586/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 d8b95158c..d0e413e78 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 41b737097..124e2cae1 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/bca038586/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index cc783097f..8a9efd888 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index eee3f1a6e..55b78a638 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/bca038586/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 098b531bc..c19a7e008 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/bca038586/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index bbe70617f..601171bcf 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/bca038586/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 45b10893f..b5192bb36 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/bca038586/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 901d0092a..dd4756687 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/bca038586/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 604e493b7..4ff1118ea 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/bca038586/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 0be11450b..87a0826d3 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/bca038586/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 1fb3a0c4d..53ef165ad 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/bca038586/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index e3e39c2bb..eae0d0341 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 7babcb36b..aa2cd4b5a 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/bca038586/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 a6dd7ab20..c67186581 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/bca038586/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 f3a0fdcfb..980d5df1a 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/bca038586/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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/bca038586/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b723d22b3/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 7298f7a45..8a22f4081 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 a4c840d00..918302a2b 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:22.035</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.744</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -336,7 +336,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:22.029</p></td>
+<td><p>00:20.738</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 3d8441775..34feb74ea 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -571,7 +571,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 24.03s!
+resnet18_v1 inference graph built in 22.39s!
</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 44c7f5c15..0a30fe006 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -589,7 +589,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.68s!
+yolov3-tiny inference graph built in 15.71s!
</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 92884945c..ac69a6c88 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:33.204</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.434</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.139</p></td>
+<td><p>00:48.717</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:44.065</p></td>
+<td><p>00:42.717</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 e6784a75a..4a1b10528 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.247</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.338</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.850</p></td>
+<td><p>00:02.919</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>00:00.397</p></td>
+<td><p>00:00.419</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 746ccbf7d..00abbe529 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.724</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.749</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,11 +336,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.391</p></td>
+<td><p>00:00.397</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>00:00.333</p></td>
+<td><p>00:00.351</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 b259bfd42..538e20148 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -566,7 +566,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.769 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 91.663 ms
</pre></div>
</div>
</div>
@@ -630,6 +630,7 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
+.T
</pre></div>
</div>
</div>
@@ -640,7 +641,7 @@ 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 1.848 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.276 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 bd3fa34f9..1a939a22b 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -668,16 +668,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.74/10.74 result: MeasureResult(costs=(0.024988932600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.536369800567627, timestamp=1659404130.1911142) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.95/10.74 result: MeasureResult(costs=(0.0910197508,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.597144365310669, timestamp=1659404131.8109076) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.80/11.80 result: MeasureResult(costs=(0.022756179199999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5696594715118408, timestamp=1659404132.867696) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.86/11.80 result: MeasureResult(costs=(0.14425883960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.439789295196533, timestamp=1659404135.879735) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.50/11.80 result: MeasureResult(costs=(0.07677793000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.364466905593872, timestamp=1659404137.900425) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.63/11.80 result: MeasureResult(costs=(0.1643082828,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.802633285522461, timestamp=1659404140.7467308) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.80/11.80 result: MeasureResult(costs=(0.336575252,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.500689506530762, timestamp=1659404146.2929685) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 9.97/11.80 result: MeasureResult(costs=(0.026915956599999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5758566856384277, timestamp=1659404146.8866026) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.49/11.80 result: MeasureResult(costs=(0.1796936574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.995450496673584, timestamp=1659404150.0023122) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.47/11.80 result: MeasureResult(costs=(0.1085235084,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8646361827850342, timestamp=1659404151.9039223) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.29/9.29 result: MeasureResult(costs=(0.028902017600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5932786464691162, timestamp=1659403980.7007995) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.96/9.29 result: MeasureResult(costs=(0.0906982436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5954678058624268, timestamp=1659403982.3122838) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 12.02/12.02 result: MeasureResult(costs=(0.0223243618,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5456256866455078, timestamp=1659403983.3486478) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.81/12.02 result: MeasureResult(costs=(0.1480357606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.480104684829712, timestamp=1659403986.3976388) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.77/12.02 result: MeasureResult(costs=(0.0712325436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2739124298095703, timestamp=1659403987.7990823) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.85/12.02 result: MeasureResult(costs=(0.14545264400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4494028091430664, timestamp=1659403990.8073525) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/12.02 result: MeasureResult(costs=(0.3069756668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.031695604324341, timestamp=1659403995.8841174) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.84/12.02 result: MeasureResult(costs=(0.0247634874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5399374961853027, timestamp=1659403996.4438865) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.92/12.02 result: MeasureResult(costs=(0.13962370699999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3315341472625732, timestamp=1659403998.8941357) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.81/12.02 result: MeasureResult(costs=(0.0953702032,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6319117546081543, timestamp=1659404000.5854797) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 0f64b921c..352f4c44d 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -550,7 +550,7 @@ 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': 485.76568479999986, 'median': 485.4440337500023, 'std': 1.1913165428408141}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 492.3574661800012, 'median': 492.12807169997177, 'std': 0.9719009953902206}
</pre></div>
</div>
</div>
@@ -705,178 +705,178 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.77/ 17.77 GFLOPS | Progress: (4/20) | 6.27 s
-[Task 1/25] Current/Best: 6.23/ 17.77 GFLOPS | Progress: (8/20) | 9.24 s
-[Task 1/25] Current/Best: 11.71/ 23.11 GFLOPS | Progress: (12/20) | 11.67 s
-[Task 1/25] Current/Best: 17.14/ 23.11 GFLOPS | Progress: (16/20) | 13.33 s
-[Task 1/25] Current/Best: 11.67/ 24.28 GFLOPS | Progress: (20/20) | 15.07 s Done.
+[Task 1/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 6.84 s
+[Task 1/25] Current/Best: 6.17/ 17.55 GFLOPS | Progress: (8/20) | 9.34 s
+[Task 1/25] Current/Best: 11.56/ 22.78 GFLOPS | Progress: (12/20) | 11.83 s
+[Task 1/25] Current/Best: 16.79/ 22.82 GFLOPS | Progress: (16/20) | 13.51 s
+[Task 1/25] Current/Best: 11.58/ 23.90 GFLOPS | Progress: (20/20) | 15.25 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.26/ 12.94 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 2/25] Current/Best: 14.31/ 18.79 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.34 s
-[Task 2/25] Current/Best: 12.36/ 21.26 GFLOPS | Progress: (16/20) | 7.58 s
-[Task 2/25] Current/Best: 20.17/ 21.26 GFLOPS | Progress: (20/20) | 9.19 s Done.
+[Task 2/25] Current/Best: 12.32/ 12.99 GFLOPS | Progress: (4/20) | 3.76 s
+[Task 2/25] Current/Best: 14.25/ 17.28 GFLOPS | Progress: (8/20) | 5.05 s
+[Task 2/25] Current/Best: 20.83/ 20.83 GFLOPS | Progress: (12/20) | 6.40 s
+[Task 2/25] Current/Best: 12.32/ 20.83 GFLOPS | Progress: (16/20) | 7.65 s
+[Task 2/25] Current/Best: 19.15/ 20.83 GFLOPS | Progress: (20/20) | 9.28 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.65/ 10.70 GFLOPS | Progress: (4/20) | 5.79 s
-[Task 3/25] Current/Best: 15.86/ 17.18 GFLOPS | Progress: (8/20) | 7.70 s
-[Task 3/25] Current/Best: 15.08/ 17.18 GFLOPS | Progress: (12/20) | 9.39 s
-[Task 3/25] Current/Best: 7.29/ 24.03 GFLOPS | Progress: (16/20) | 11.27 s
-[Task 3/25] Current/Best: 12.75/ 24.03 GFLOPS | Progress: (20/20) | 15.79 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.58 GFLOPS | Progress: (4/20) | 5.87 s
+[Task 3/25] Current/Best: 15.60/ 16.87 GFLOPS | Progress: (8/20) | 7.81 s
+[Task 3/25] Current/Best: 14.91/ 16.87 GFLOPS | Progress: (12/20) | 9.52 s
+[Task 3/25] Current/Best: 7.20/ 23.82 GFLOPS | Progress: (16/20) | 11.43 s
+[Task 3/25] Current/Best: 12.68/ 23.82 GFLOPS | Progress: (20/20) | 15.98 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.72/ 20.71 GFLOPS | Progress: (4/20) | 2.36 s
-[Task 4/25] Current/Best: 6.93/ 20.71 GFLOPS | Progress: (8/20) | 7.03 s
-[Task 4/25] Current/Best: 22.71/ 22.71 GFLOPS | Progress: (12/20) | 11.98 s
-[Task 4/25] Current/Best: 17.33/ 22.71 GFLOPS | Progress: (16/20) | 14.37 s
-[Task 4/25] Current/Best: 13.62/ 22.71 GFLOPS | Progress: (20/20) | 16.46 s Done.
+[Task 4/25] Current/Best: 9.57/ 20.45 GFLOPS | Progress: (4/20) | 2.39 s
+[Task 4/25] Current/Best: 6.85/ 20.45 GFLOPS | Progress: (8/20) | 7.11 s
+[Task 4/25] Current/Best: 22.45/ 22.45 GFLOPS | Progress: (12/20) | 12.13 s
+[Task 4/25] Current/Best: 16.76/ 22.45 GFLOPS | Progress: (16/20) | 14.53 s
+[Task 4/25] Current/Best: 13.40/ 22.45 GFLOPS | Progress: (20/20) | 16.63 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.95/ 10.59 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 5/25] Current/Best: 11.95/ 12.95 GFLOPS | Progress: (8/20) | 4.56 s
-[Task 5/25] Current/Best: 11.62/ 17.97 GFLOPS | Progress: (12/20) | 7.70 s
-[Task 5/25] Current/Best: 11.96/ 22.80 GFLOPS | Progress: (16/20) | 9.10 s
-[Task 5/25] Current/Best: 11.99/ 22.80 GFLOPS | Progress: (20/20) | 11.01 s Done.
+[Task 5/25] Current/Best: 9.64/ 10.29 GFLOPS | Progress: (4/20) | 2.59 s
+[Task 5/25] Current/Best: 11.74/ 12.69 GFLOPS | Progress: (8/20) | 4.69 s
+[Task 5/25] Current/Best: 11.76/ 17.42 GFLOPS | Progress: (12/20) | 7.91 s
+[Task 5/25] Current/Best: 11.87/ 22.53 GFLOPS | Progress: (16/20) | 9.32 s
+[Task 5/25] Current/Best: 12.07/ 22.53 GFLOPS | Progress: (20/20) | 11.19 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.21/ 20.67 GFLOPS | Progress: (4/20) | 4.11 s
-[Task 6/25] Current/Best: 18.88/ 20.67 GFLOPS | Progress: (8/20) | 5.86 s
-[Task 6/25] Current/Best: 13.36/ 20.67 GFLOPS | Progress: (12/20) | 7.80 s
-[Task 6/25] Current/Best: 20.06/ 20.67 GFLOPS | Progress: (16/20) | 10.03 s
-[Task 6/25] Current/Best: 3.75/ 20.67 GFLOPS | Progress: (20/20) | 12.54 s Done.
+[Task 6/25] Current/Best: 12.23/ 20.68 GFLOPS | Progress: (4/20) | 4.12 s
+[Task 6/25] Current/Best: 18.98/ 20.68 GFLOPS | Progress: (8/20) | 5.89 s
+[Task 6/25] Current/Best: 13.28/ 20.68 GFLOPS | Progress: (12/20) | 7.83 s
+[Task 6/25] Current/Best: 20.03/ 20.68 GFLOPS | Progress: (16/20) | 10.08 s
+[Task 6/25] Current/Best: 3.71/ 20.68 GFLOPS | Progress: (20/20) | 12.58 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.24/ 12.95 GFLOPS | Progress: (4/20) | 3.62 s
-[Task 7/25] Current/Best: 20.33/ 21.13 GFLOPS | Progress: (8/20) | 5.12 s
-[Task 7/25] Current/Best: 16.10/ 21.13 GFLOPS | Progress: (12/20) | 7.04 s
-[Task 7/25] Current/Best: 12.26/ 21.13 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 7/25] Current/Best: 6.43/ 21.70 GFLOPS | Progress: (20/20) | 11.52 s Done.
+[Task 7/25] Current/Best: 11.17/ 12.92 GFLOPS | Progress: (4/20) | 3.58 s
+[Task 7/25] Current/Best: 20.35/ 21.08 GFLOPS | Progress: (8/20) | 5.07 s
+[Task 7/25] Current/Best: 16.17/ 21.08 GFLOPS | Progress: (12/20) | 6.96 s
+[Task 7/25] Current/Best: 12.29/ 21.08 GFLOPS | Progress: (16/20) | 8.99 s
+[Task 7/25] Current/Best: 6.32/ 21.75 GFLOPS | Progress: (20/20) | 11.43 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.45/ 14.38 GFLOPS | Progress: (4/20) | 2.88 s
-[Task 8/25] Current/Best: 9.74/ 14.38 GFLOPS | Progress: (8/20) | 8.01 s
-[Task 8/25] Current/Best: 13.20/ 14.38 GFLOPS | Progress: (12/20) | 14.56 s
-[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 16.67 s
-[Task 8/25] Current/Best: 20.17/ 20.17 GFLOPS | Progress: (20/20) | 23.83 s Done.
+[Task 8/25] Current/Best: 9.93/ 14.15 GFLOPS | Progress: (4/20) | 2.90 s
+[Task 8/25] Current/Best: 9.64/ 14.15 GFLOPS | Progress: (8/20) | 8.07 s
+[Task 8/25] Current/Best: 12.68/ 14.15 GFLOPS | Progress: (12/20) | 14.57 s
+[Task 8/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (16/20) | 16.65 s
+[Task 8/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (20/20) | 23.80 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.30/ 15.89 GFLOPS | Progress: (4/20) | 11.96 s
-[Task 9/25] Current/Best: 23.44/ 23.44 GFLOPS | Progress: (8/20) | 13.71 s
-[Task 9/25] Current/Best: 8.24/ 23.44 GFLOPS | Progress: (12/20) | 16.26 s
-[Task 9/25] Current/Best: 17.93/ 23.44 GFLOPS | Progress: (16/20) | 19.12 s
-[Task 9/25] Current/Best: 9.22/ 23.44 GFLOPS | Progress: (20/20) | 27.68 s
+[Task 9/25] Current/Best: 14.29/ 14.29 GFLOPS | Progress: (4/20) | 11.96 s
+[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.68 s
+[Task 9/25] Current/Best: 8.25/ 23.46 GFLOPS | Progress: (12/20) | 16.19 s
+[Task 9/25] Current/Best: 18.00/ 23.46 GFLOPS | Progress: (16/20) | 19.07 s
+[Task 9/25] Current/Best: 9.26/ 23.46 GFLOPS | Progress: (20/20) | 27.74 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.57 s
-[Task 10/25] Current/Best: 15.55/ 18.21 GFLOPS | Progress: (8/20) | 4.19 s
-[Task 10/25] Current/Best: 13.14/ 18.95 GFLOPS | Progress: (12/20) | 5.73 s
-[Task 10/25] Current/Best: 19.14/ 20.43 GFLOPS | Progress: (16/20) | 6.84 s
-[Task 10/25] Current/Best: 9.04/ 20.43 GFLOPS | Progress: (20/20) | 8.37 s Done.
+[Task 10/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 10/25] Current/Best: 15.52/ 18.19 GFLOPS | Progress: (8/20) | 4.20 s
+[Task 10/25] Current/Best: 12.57/ 18.78 GFLOPS | Progress: (12/20) | 5.76 s
+[Task 10/25] Current/Best: 19.13/ 20.16 GFLOPS | Progress: (16/20) | 6.86 s
+[Task 10/25] Current/Best: 8.85/ 20.16 GFLOPS | Progress: (20/20) | 8.41 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.96/ 18.09 GFLOPS | Progress: (4/20) | 3.41 s
-[Task 11/25] Current/Best: 16.93/ 18.09 GFLOPS | Progress: (8/20) | 6.23 s
-[Task 11/25] Current/Best: 18.00/ 18.09 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 11/25] Current/Best: 13.47/ 21.15 GFLOPS | Progress: (16/20) | 11.32 s
-[Task 11/25] Current/Best: 19.40/ 21.61 GFLOPS | Progress: (20/20) | 13.43 s Done.
+[Task 11/25] Current/Best: 12.33/ 18.17 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 11/25] Current/Best: 15.53/ 18.17 GFLOPS | Progress: (8/20) | 6.17 s
+[Task 11/25] Current/Best: 18.09/ 18.17 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 11/25] Current/Best: 13.44/ 21.18 GFLOPS | Progress: (16/20) | 11.19 s
+[Task 11/25] Current/Best: 19.49/ 21.59 GFLOPS | Progress: (20/20) | 13.29 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.79/ 18.09 GFLOPS | Progress: (4/20) | 5.78 s
-[Task 12/25] Current/Best: 5.31/ 18.09 GFLOPS | Progress: (8/20) | 9.76 s
-[Task 12/25] Current/Best: 18.83/ 18.91 GFLOPS | Progress: (12/20) | 11.72 s
-[Task 12/25] Current/Best: 15.15/ 18.91 GFLOPS | Progress: (16/20) | 14.69 s
-[Task 12/25] Current/Best: 15.18/ 19.05 GFLOPS | Progress: (20/20) | 16.60 s Done.
+[Task 12/25] Current/Best: 7.81/ 18.02 GFLOPS | Progress: (4/20) | 5.77 s
+[Task 12/25] Current/Best: 5.26/ 18.02 GFLOPS | Progress: (8/20) | 9.72 s
+[Task 12/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (12/20) | 11.69 s
+[Task 12/25] Current/Best: 15.40/ 18.84 GFLOPS | Progress: (16/20) | 14.62 s
+[Task 12/25] Current/Best: 15.14/ 18.84 GFLOPS | Progress: (20/20) | 16.55 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.84/ 17.24 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 13/25] Current/Best: 16.11/ 21.01 GFLOPS | Progress: (8/20) | 6.38 s
-[Task 13/25] Current/Best: 19.52/ 21.11 GFLOPS | Progress: (12/20) | 9.38 s
-[Task 13/25] Current/Best: 12.21/ 21.11 GFLOPS | Progress: (16/20) | 12.86 s
-[Task 13/25] Current/Best: 18.56/ 21.11 GFLOPS | Progress: (20/20) | 15.20 s Done.
+[Task 13/25] Current/Best: 8.68/ 17.35 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 13/25] Current/Best: 16.10/ 21.19 GFLOPS | Progress: (8/20) | 6.36 s
+[Task 13/25] Current/Best: 19.53/ 21.74 GFLOPS | Progress: (12/20) | 9.40 s
+[Task 13/25] Current/Best: 12.30/ 21.74 GFLOPS | Progress: (16/20) | 12.78 s
+[Task 13/25] Current/Best: 18.51/ 21.74 GFLOPS | Progress: (20/20) | 15.12 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.55/ 13.55 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 14/25] Current/Best: 6.06/ 13.55 GFLOPS | Progress: (8/20) | 5.56 s
-[Task 14/25] Current/Best: 21.14/ 21.14 GFLOPS | Progress: (12/20) | 8.26 s
-[Task 14/25] Current/Best: 16.88/ 21.14 GFLOPS | Progress: (16/20) | 9.91 s Done.
+[Task 14/25] Current/Best: 13.65/ 13.65 GFLOPS | Progress: (4/20) | 3.40 s
+[Task 14/25] Current/Best: 6.03/ 13.65 GFLOPS | Progress: (8/20) | 5.59 s
+[Task 14/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (12/20) | 8.30 s
+[Task 14/25] Current/Best: 17.19/ 19.96 GFLOPS | Progress: (16/20) | 9.96 s Done.
-[Task 14/25] Current/Best: 17.11/ 21.14 GFLOPS | Progress: (20/20) | 11.66 s
+[Task 14/25] Current/Best: 17.18/ 19.96 GFLOPS | Progress: (20/20) | 11.76 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.15/ 17.63 GFLOPS | Progress: (4/20) | 2.75 s
-[Task 15/25] Current/Best: 14.42/ 18.06 GFLOPS | Progress: (8/20) | 4.09 s
-[Task 15/25] Current/Best: 10.38/ 22.26 GFLOPS | Progress: (12/20) | 6.37 s
-[Task 15/25] Current/Best: 20.40/ 22.26 GFLOPS | Progress: (16/20) | 9.59 s
-[Task 15/25] Current/Best: 9.71/ 22.26 GFLOPS | Progress: (20/20) | 10.61 s
+[Task 15/25] Current/Best: 16.12/ 17.70 GFLOPS | Progress: (4/20) | 2.72 s
+[Task 15/25] Current/Best: 14.41/ 18.02 GFLOPS | Progress: (8/20) | 4.06 s
+[Task 15/25] Current/Best: 10.40/ 22.40 GFLOPS | Progress: (12/20) | 6.33 s
+[Task 15/25] Current/Best: 20.41/ 22.40 GFLOPS | Progress: (16/20) | 9.46 s
+[Task 15/25] Current/Best: 9.70/ 22.40 GFLOPS | Progress: (20/20) | 10.48 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (4/20) | 2.95 s
-[Task 16/25] Current/Best: 3.04/ 20.44 GFLOPS | Progress: (8/20) | 4.57 s
-[Task 16/25] Current/Best: 19.47/ 20.44 GFLOPS | Progress: (12/20) | 5.77 s
-[Task 16/25] Current/Best: 18.04/ 20.44 GFLOPS | Progress: (16/20) | 7.16 s
-[Task 16/25] Current/Best: 10.01/ 22.27 GFLOPS | Progress: (20/20) | 9.32 s Done.
+[Task 16/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (4/20) | 2.99 s
+[Task 16/25] Current/Best: 3.01/ 20.63 GFLOPS | Progress: (8/20) | 4.60 s
+[Task 16/25] Current/Best: 19.12/ 20.63 GFLOPS | Progress: (12/20) | 5.81 s
+[Task 16/25] Current/Best: 17.73/ 20.63 GFLOPS | Progress: (16/20) | 7.19 s
+[Task 16/25] Current/Best: 10.00/ 22.15 GFLOPS | Progress: (20/20) | 9.34 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.49/ 17.03 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 17/25] Current/Best: 14.44/ 23.18 GFLOPS | Progress: (8/20) | 7.65 s
-[Task 17/25] Current/Best: 16.77/ 23.18 GFLOPS | Progress: (12/20) | 9.70 s
-[Task 17/25] Current/Best: 16.49/ 23.18 GFLOPS | Progress: (16/20) | 11.92 s
-[Task 17/25] Current/Best: 10.02/ 23.18 GFLOPS | Progress: (20/20) | 14.09 s Done.
+[Task 17/25] Current/Best: 12.82/ 18.78 GFLOPS | Progress: (4/20) | 4.81 s
+[Task 17/25] Current/Best: 14.42/ 23.34 GFLOPS | Progress: (8/20) | 7.69 s
+[Task 17/25] Current/Best: 17.00/ 23.34 GFLOPS | Progress: (12/20) | 9.76 s
+[Task 17/25] Current/Best: 16.52/ 23.34 GFLOPS | Progress: (16/20) | 12.00 s
+[Task 17/25] Current/Best: 10.06/ 23.34 GFLOPS | Progress: (20/20) | 14.15 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.23/ 17.96 GFLOPS | Progress: (4/20) | 3.83 s
-[Task 18/25] Current/Best: 10.61/ 19.86 GFLOPS | Progress: (8/20) | 7.57 s
-[Task 18/25] Current/Best: 18.59/ 19.86 GFLOPS | Progress: (12/20) | 9.51 s
-[Task 18/25] Current/Best: 10.02/ 19.86 GFLOPS | Progress: (16/20) | 13.45 s
-[Task 18/25] Current/Best: 19.97/ 19.97 GFLOPS | Progress: (20/20) | 14.96 s Done.
+[Task 18/25] Current/Best: 11.11/ 17.24 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 18/25] Current/Best: 10.60/ 19.11 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 18/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (12/20) | 9.41 s
+[Task 18/25] Current/Best: 10.08/ 19.37 GFLOPS | Progress: (16/20) | 13.30 s
+[Task 18/25] Current/Best: 20.34/ 20.34 GFLOPS | Progress: (20/20) | 14.81 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.09/ 20.06 GFLOPS | Progress: (4/20) | 6.23 s
-[Task 19/25] Current/Best: 2.61/ 20.06 GFLOPS | Progress: (8/20) | 9.53 s
-[Task 19/25] Current/Best: 17.61/ 20.79 GFLOPS | Progress: (12/20) | 12.49 s
-[Task 19/25] Current/Best: 15.50/ 20.79 GFLOPS | Progress: (16/20) | 15.49 s
-[Task 19/25] Current/Best: 2.69/ 22.89 GFLOPS | Progress: (20/20) | 18.25 s Done.
+[Task 19/25] Current/Best: 7.24/ 20.42 GFLOPS | Progress: (4/20) | 5.98 s
+[Task 19/25] Current/Best: 2.61/ 20.42 GFLOPS | Progress: (8/20) | 9.35 s
+[Task 19/25] Current/Best: 20.00/ 21.79 GFLOPS | Progress: (12/20) | 12.35 s
+[Task 19/25] Current/Best: 14.14/ 21.79 GFLOPS | Progress: (16/20) | 15.41 s
+[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 18.23 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.00/ 15.16 GFLOPS | Progress: (4/20) | 3.36 s Done.
+[Task 20/25] Current/Best: 8.97/ 15.26 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-[Task 20/25] Current/Best: 10.39/ 15.16 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 20/25] Current/Best: 2.32/ 16.72 GFLOPS | Progress: (12/20) | 10.79 s
-[Task 20/25] Current/Best: 11.81/ 16.72 GFLOPS | Progress: (16/20) | 14.77 s
-[Task 20/25] Current/Best: 13.52/ 21.70 GFLOPS | Progress: (20/20) | 16.90 s
+[Task 20/25] Current/Best: 9.69/ 15.26 GFLOPS | Progress: (8/20) | 6.71 s
+[Task 20/25] Current/Best: 2.31/ 16.53 GFLOPS | Progress: (12/20) | 10.58 s
+[Task 20/25] Current/Best: 12.22/ 16.53 GFLOPS | Progress: (16/20) | 14.49 s
+[Task 20/25] Current/Best: 12.09/ 22.22 GFLOPS | Progress: (20/20) | 16.62 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.78 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 21/25] Current/Best: 14.48/ 17.78 GFLOPS | Progress: (8/20) | 4.99 s
-[Task 21/25] Current/Best: 1.61/ 17.78 GFLOPS | Progress: (12/20) | 7.19 s
-[Task 21/25] Current/Best: 16.24/ 17.78 GFLOPS | Progress: (16/20) | 10.76 s
-[Task 21/25] Current/Best: 4.47/ 17.78 GFLOPS | Progress: (20/20) | 18.17 s
+[Task 21/25] Current/Best: 6.42/ 17.72 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 21/25] Current/Best: 14.66/ 17.72 GFLOPS | Progress: (8/20) | 4.91 s
+[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 7.04 s
+[Task 21/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (16/20) | 10.56 s
+[Task 21/25] Current/Best: 4.46/ 18.08 GFLOPS | Progress: (20/20) | 17.81 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.93 GFLOPS | Progress: (4/20) | 2.72 s
-[Task 22/25] Current/Best: 9.01/ 21.85 GFLOPS | Progress: (8/20) | 4.74 s
-[Task 22/25] Current/Best: 20.04/ 21.85 GFLOPS | Progress: (12/20) | 7.12 s
-[Task 22/25] Current/Best: 15.28/ 21.85 GFLOPS | Progress: (16/20) | 9.24 s
-[Task 22/25] Current/Best: 15.07/ 21.85 GFLOPS | Progress: (20/20) | 10.98 s Done.
+[Task 22/25] Current/Best: 2.71/ 16.97 GFLOPS | Progress: (4/20) | 2.67 s
+[Task 22/25] Current/Best: 8.63/ 21.94 GFLOPS | Progress: (8/20) | 4.70 s
+[Task 22/25] Current/Best: 19.97/ 21.94 GFLOPS | Progress: (12/20) | 7.10 s
+[Task 22/25] Current/Best: 15.38/ 21.94 GFLOPS | Progress: (16/20) | 9.21 s
+[Task 22/25] Current/Best: 13.86/ 21.94 GFLOPS | Progress: (20/20) | 10.94 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.42/ 20.29 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 23/25] Current/Best: 15.91/ 20.29 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 23/25] Current/Best: 20.71/ 21.42 GFLOPS | Progress: (12/20) | 8.51 s
-[Task 23/25] Current/Best: 6.10/ 21.42 GFLOPS | Progress: (16/20) | 15.65 s
-[Task 23/25] Current/Best: 7.72/ 21.42 GFLOPS | Progress: (20/20) | 19.89 s Done.
+[Task 23/25] Current/Best: 17.64/ 20.93 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 23/25] Current/Best: 14.27/ 20.93 GFLOPS | Progress: (8/20) | 6.53 s
+[Task 23/25] Current/Best: 21.05/ 21.89 GFLOPS | Progress: (12/20) | 8.36 s
+[Task 23/25] Current/Best: 6.47/ 21.89 GFLOPS | Progress: (16/20) | 15.30 s
+[Task 23/25] Current/Best: 7.94/ 21.89 GFLOPS | Progress: (20/20) | 19.48 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.45/ 8.45 GFLOPS | Progress: (4/20) | 11.83 s
-[Task 24/25] Current/Best: 1.99/ 8.45 GFLOPS | Progress: (8/20) | 22.84 s
-[Task 24/25] Current/Best: 4.46/ 8.45 GFLOPS | Progress: (12/20) | 34.38 s Done.
+[Task 24/25] Current/Best: 8.09/ 8.09 GFLOPS | Progress: (4/20) | 11.79 s
+[Task 24/25] Current/Best: 3.65/ 8.09 GFLOPS | Progress: (8/20) | 23.02 s
+[Task 24/25] Current/Best: 4.58/ 8.09 GFLOPS | Progress: (12/20) | 33.72 s Done.
-[Task 24/25] Current/Best: 7.24/ 8.93 GFLOPS | Progress: (16/20) | 40.10 s
-[Task 24/25] Current/Best: 3.32/ 8.93 GFLOPS | Progress: (20/20) | 46.06 s Done.
+[Task 24/25] Current/Best: 6.17/ 8.95 GFLOPS | Progress: (16/20) | 39.32 s
+[Task 24/25] Current/Best: 3.43/ 8.95 GFLOPS | Progress: (20/20) | 45.23 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.55/ 2.90 GFLOPS | Progress: (4/20) | 11.62 s
-[Task 25/25] Current/Best: 5.74/ 7.82 GFLOPS | Progress: (8/20) | 22.92 s
-[Task 25/25] Current/Best: 5.99/ 7.82 GFLOPS | Progress: (12/20) | 34.40 s
-[Task 25/25] Current/Best: 5.83/ 9.34 GFLOPS | Progress: (16/20) | 36.16 s
-[Task 25/25] Current/Best: 2.93/ 9.34 GFLOPS | Progress: (20/20) | 46.83 s
+[Task 25/25] Current/Best: 1.57/ 2.79 GFLOPS | Progress: (4/20) | 11.57 s
+[Task 25/25] Current/Best: 5.91/ 8.24 GFLOPS | Progress: (8/20) | 22.80 s
+[Task 25/25] Current/Best: 6.02/ 8.24 GFLOPS | Progress: (12/20) | 34.08 s
+[Task 25/25] Current/Best: 5.84/ 8.52 GFLOPS | Progress: (16/20) | 35.94 s
+[Task 25/25] Current/Best: 2.89/ 9.36 GFLOPS | Progress: (20/20) | 46.58 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -980,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 407.0159230499962, 'median': 407.0427203999998, 'std': 0.7926061920392635}
-unoptimized: {'mean': 485.76568479999986, 'median': 485.4440337500023, 'std': 1.1913165428408141}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 390.9319189100097, 'median': 390.9034845500628, 'std': 0.823910532986542}
+unoptimized: {'mean': 492.3574661800012, 'median': 492.12807169997177, 'std': 0.9719009953902206}
</pre></div>
</div>
</div>
@@ -995,7 +995,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 26.603 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 21.075 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 1237e8b1f..ea9130569 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -526,7 +526,7 @@ 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>1.265e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.243e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index aa280d683..8cb50d1d7 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -483,7 +483,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x4bcc5d0)), stage(b, placeholder(b, 0xb3ef0d0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[it [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xbbdefa0)), stage(b, placeholder(b, 0x27437b20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 5cd8cefe0..6d7071646 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:24.712</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:17.097</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:26.603</p></td>
+<td><p>10:21.075</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>01:01.848</p></td>
+<td><p>01:03.276</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:58.403</p></td>
+<td><p>00:58.549</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:30.464</p></td>
+<td><p>00:29.207</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>00:25.256</p></td>
+<td><p>00:23.372</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>00:01.271</p></td>
+<td><p>00:00.777</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>00:00.702</p></td>
+<td><p>00:00.680</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>00:00.158</p></td>
+<td><p>00:00.153</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index b7239b8e4..c158ea839 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -634,7 +634,7 @@ factor to be the number of threads on your CPU.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vector: 0.000025
+vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -667,10 +667,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.794269999976677e-06 1.0
- naive 5.8309e-06 0.7481008484460313
-parallel 6.055100000000001e-06 0.7768655691961043
- vector 2.46354e-05 3.1607065190291994
+ numpy 8.091600002444465e-06 1.0
+ naive 5.9406e-06 0.734168767389064
+parallel 5.9968e-06 0.7411142417060127
+ vector 2.44763e-05 3.024902366973866
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -986,7 +986,7 @@ 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: 0.017944
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.015050
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1029,7 +1029,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.185733
+none: 3.307579
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1096,7 +1096,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.326560
+blocking: 0.293194
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.345907
+vectorization: 0.321184
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1214,7 +1214,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.122926
+loop permutation: 0.115425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1292,7 +1292,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.110293
+array packing: 0.109169
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1368,7 +1368,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.111173
+block caching: 0.099342
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1437,7 +1437,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.145357
+parallelization: 0.129176
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1499,13 +1499,13 @@ 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 3.1857328411999997 1.0
- blocking 0.32655993159999996 0.10250700478606097
- vectorization 0.3459066478 0.10857992965590427
-loop permutation 0.12292583400000001 0.03858635991387664
- array packing 0.11029261100000001 0.034620797316593274
- block caching 0.1111726304 0.0348970349811642
- parallelization 0.14535693879999997 0.04562747287536108
+ none 3.3075787489 1.0
+ blocking 0.2931938092 0.08864303209636575
+ vectorization 0.3211839272 0.09710545132351452
+loop permutation 0.115424887 0.034897094147308454
+ array packing 0.1091687748 0.03300564645250131
+ block caching 0.0993415468 0.030034522030061406
+ parallelization 0.12917559539999998 0.0390544277873837
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a