You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/11/28 13:25:15 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@fc59b6dbdf445c09f70d20c8156cc940f696fdcd)
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 9fa720e472 deploying docs (apache/tvm@fc59b6dbdf445c09f70d20c8156cc940f696fdcd)
9fa720e472 is described below
commit 9fa720e472975ba8f83937e7601c8db1cfb0c5e1
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Nov 28 13:25:09 2022 +0000
deploying docs (apache/tvm@fc59b6dbdf445c09f70d20c8156cc940f696fdcd)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 4 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 404 +++++++++++++--------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 187 +---------
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 207 ++++++++---
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 8 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 62 ++--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 ++-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 10 +-
docs/how_to/compile_models/from_pytorch.html | 13 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_adreno.html | 4 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 43 +--
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 24 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 404 +++++++++++++--------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 187 +---------
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 207 ++++++++---
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +++---
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 267 +++++++-------
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 28 +-
docs/tutorial/tensor_expr_get_started.html | 43 ++-
128 files changed, 1678 insertions(+), 1566 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 f075e73fca..a05e979313 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.984 seconds)
+ **Total running time of the script:** ( 1 minutes 9.613 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 067953a638..30629a6d70 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 897ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 1s/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 07e9a6638b..0055c09987 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.zip6aac35ae-2a9c-4a6c-86ad-de7b9bfe0368 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip97a78d84-9dd6-45c0-a1bb-ed12a2d188dd 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 26842286f6..7a286bc10b 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 52.1MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 60.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 53.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 61.5MB/s]
92%|#########2| 38.2M/41.5M [00:00<00:00, 60.5MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 56.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
28%|##8 | 11.8M/41.5M [00:00<00:00, 124MB/s]
57%|#####6 | 23.6M/41.5M [00:00<00:00, 109MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 105MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 106MB/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 109cb7cbc4..282f1f1da7 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 53.0MB/s]
27%|##7 | 12.1M/44.7M [00:00<00:00, 57.0MB/s]
39%|###9 | 17.5M/44.7M [00:00<00:00, 48.6MB/s]
58%|#####8 | 26.1M/44.7M [00:00<00:00, 55.5MB/s]
71%|####### | 31.7M/44.7M [00:00<00:00, 48.7MB/s]
86%|########5 | 38.3M/44.7M [00:00<00:00, 44.3MB/s]
98%|#########8| 43.8M/44.7M [00:00<00:00, 47.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 49.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
26%|##6 | 11.8M/44.7M [00:00<00:00, 123MB/s]
53%|#####2 | 23.5M/44.7M [00:00<00:00, 109MB/s]
76%|#######6 | 34.0M/44.7M [00:00<00:00, 105MB/s]
99%|#########8| 44.0M/44.7M [00:00<00:00, 103MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/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 afe8d4d99e..90fe5f95b5 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.010 seconds)
+ **Total running time of the script:** ( 1 minutes 13.118 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 3833418442..a41f86716b 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
=================
-**05:48.431** total execution time for **how_to_compile_models** files:
+**05:42.732** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:13.984 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:13.118 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.613 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.848 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.430 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.885 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.059 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.412 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.510 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.399 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.404 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.305 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.784 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.022 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.386 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index dab80df09a..ab46d3c398 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3339.1324 3338.3742 3343.3233 3336.8353 2.0746
+ 3344.6771 3343.5188 3359.0259 3336.9567 6.5112
@@ -732,7 +732,7 @@ well as provides information about the model's performance
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.800 seconds)
+ **Total running time of the script:** ( 1 minutes 1.226 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
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 9a55b5c9aa..0b6ea2411f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9765 15.9888 16.5506 15.4907 0.3792
+ 16.1232 15.9256 16.9046 15.7265 0.4393
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 aa175c27f9..244206a134 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:03, 52.3MB/s]
7%|6 | 11.3M/170M [00:00<00:04, 36.8MB/s]
9%|9 | 16.0M/170M [00:00<00:04, 36.1MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 43.8MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 50.6MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 58.1MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 61.0MB/s]
34%|###3 | 56.9M/170M [00:01<00:01, 69.7MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 61.4MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 65.4MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 68.6MB/s]
51%|#####1 | 86.7M/170M [00:01<00:01, 69.1MB/s]
55%|#####5 | 93.5M/170M [00:01<00:01, 57.3MB/s]
58%|#####8 | 99.4M/170M [00:01<00:01, 55.8MB/s]
62%|######1 | 105M/170M [00:01<00:01, 55.5MB/s]
67%|######7 | 114M/170M [00:02<00:00, 63.7MB/s]
71%|####### | 120M/170M [00:02<00:00, 63.8MB/s]
76%|#######5 | 129M/170M [00:02<00:00, 70.2MB/s]
80%|######## | 136M/170M [00:02<00:00, 72.5MB/s]
85%|########4 | 144M/170M [00:02<00:00, 74.2MB/s]
89%|########9 | 152M/170M [00:02<00:00, 65.8MB/s]
93%|#########3| 158M/170M [00:02<00:00, 65.1MB/s]
97%|#########6| 165M/170M [00:02<00:00, 61.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 60.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|8 | 14.6M/170M [00:00<00:01, 153MB/s]
17%|#7 | 29.2M/170M [00:00<00:01, 116MB/s]
24%|##4 | 40.8M/170M [00:00<00:01, 108MB/s]
30%|### | 51.3M/170M [00:00<00:01, 106MB/s]
36%|###6 | 61.6M/170M [00:00<00:01, 104MB/s]
42%|####2 | 71.6M/170M [00:00<00:01, 99.5MB/s]
48%|####7 | 81.2M/170M [00:00<00:00, 97.9MB/s]
53%|#####3 | 90.5M/170M [00:00<00:00, 87.2MB/s]
59%|#####8 | 100M/170M [00:01<00:00, 90.8MB/s]
64%|######4 | 109M/170M [00:01<00:00, 90.8MB/s]
69%|######9 | 118M/170M [00:01<00:00, 90.5MB/s]
75%|#######4 | 127M/170M [00:01<00:00, 92.4MB/s]
80%|######## | 136M/170M [00:01<00:00, 68.0MB/s]
87%|########6 | 147M/170M [00:01<00:00, 78.7MB/s]
92%|#########1| 156M/170M [00:01<00:00, 78.4MB/s]
96%|#########6| 164M/170M [00:01<00:00, 74.2MB/s]
100%|##########| 170M/170M [00:01<00:00, 90.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 18.004 seconds)
+ **Total running time of the script:** ( 3 minutes 16.418 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 cba9e4c2c1..8ead1316d3 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
90%|######### | 12.2M/13.6M [00:00<00:00, 128MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 124MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
86%|########6 | 11.7M/13.6M [00:00<00:00, 91.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 99.0MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2100 90.1585 91.5626 89.9461 0.2206
+ 90.2859 90.1851 92.7542 90.0537 0.3070
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.277 seconds)
+ **Total running time of the script:** ( 1 minutes 6.492 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 2089b35fee..5025d9b733 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.9358 118.8613 125.9193 117.8568 0.8452
+ 120.6198 120.6334 122.5440 119.6961 0.4538
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 21.857 seconds)
+ **Total running time of the script:** ( 2 minutes 23.458 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 89dd6f9f7b..e38e97859c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.186 seconds)
+ **Total running time of the script:** ( 1 minutes 15.534 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 ae082de465..c25da7652f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6121/132723 [00:00<00:02, 61200.72KB/s]
11%|# | 14588/132723 [00:00<00:01, 74993.90KB/s]
17%|#7 | 22995/132723 [00:00<00:01, 79134.43KB/s]
24%|##3 | 31436/132723 [00:00<00:01, 81214.55KB/s]
30%|##9 | 39779/132723 [00:00<00:01, 82011.73KB/s]
36%|###6 | 48168/132723 [00:00<00:01, 82648.32KB/s]
43%|####2 | 56572/132723 [00:00<00:00, 83101.02KB/s]
49%|####9 | 65061/132723 [00:00<00:00, 83666.60KB/s]
55%|#####5 | 73430/132723 [00:00<00:00, 83671.70KB/s]
62%|######1 | 81894/132723 [00:01<00:00, 83967.73KB/s]
68%|######8 | 90381/132723 [00:01<00:00, 84241.73KB/s]
74%|#######4 | 98806/132723 [00:01<00:00, 70024.85KB/s]
81%|######## | 107253/132723 [00:01<00:00, 73854.61KB/s]
87%|########6 | 114969/132723 [00:01<00:00, 63019.21KB/s]
93%|#########3| 123433/132723 [00:01<00:00, 68392.94KB/s]
99%|########
#9| 131961/132723 [00:01<00:00, 72817.52KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76021.56KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|3 | 4538/132723 [00:00<00:02, 44814.51KB/s]
9%|9 | 11993/132723 [00:00<00:01, 62213.42KB/s]
15%|#5 | 20557/132723 [00:00<00:01, 72876.88KB/s]
22%|##1 | 29146/132723 [00:00<00:01, 77993.37KB/s]
28%|##8 | 37813/132723 [00:00<00:01, 81115.11KB/s]
35%|###4 | 46453/132723 [00:00<00:01, 82907.69KB/s]
41%|####1 | 55020/132723 [00:00<00:00, 83808.82KB/s]
48%|####8 | 63742/132723 [00:00<00:00, 84891.79KB/s]
55%|#####4 | 72422/132723 [00:00<00:00, 85485.81KB/s]
61%|######1 | 81184/132723 [00:01<00:00, 86142.15KB/s]
68%|######7 | 89799/132723 [00:01<00:00, 86131.44KB/s]
74%|#######4 | 98532/132723 [00:01<00:00, 86493.05KB/s]
81%|######## | 107215/132723 [00:01<00:00, 86593.44KB/s]
87%|########7 | 115918/132723 [00:01<00:00, 86724.06KB/s]
94%|#########3| 124591/132723 [00:01<00:00, 86465.60KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82996.38KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 59.365 seconds)
+ **Total running time of the script:** ( 3 minutes 4.738 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 b1e22857da..1d83277606 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:49.339** total execution time for **how_to_deploy_models** files:
+**13:32.624** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:18.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:16.418 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:59.365 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:04.738 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:21.857 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:23.458 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.186 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:15.534 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.277 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.492 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:01.800 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:01.226 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.594 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.516 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.734 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.416 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.502 | 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 515aa44bad..ef02b71081 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip768c7128-9046-4ec7-8beb-84bfd58b6b1d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip714dc02d-2f12-4161-a4c5-d99666d55c17 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 382c9c40f2..e239dd6b35 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
=================
-**00:49.113** total execution time for **how_to_extend_tvm** files:
+**00:49.266** 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``) | 00:45.631 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.688 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.425 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.509 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.062 | 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 619e150662..0a261519de 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: 7378us [7378us] (46.46%; 46.46%)
- FoldScaleAxis: 8501us [6us] (53.54%; 53.54%)
- FoldConstant: 8495us [1706us] (53.50%; 99.92%)
- InferType: 6789us [6789us] (42.75%; 79.92%)
+ InferType: 7449us [7449us] (46.52%; 46.52%)
+ FoldScaleAxis: 8566us [8us] (53.48%; 53.48%)
+ FoldConstant: 8557us [1755us] (53.43%; 99.91%)
+ InferType: 6802us [6802us] (42.47%; 79.49%)
@@ -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: 6781us [6781us] (45.09%; 45.09%)
- FoldScaleAxis: 8259us [5us] (54.91%; 54.91%)
- FoldConstant: 8254us [1660us] (54.88%; 99.94%)
- InferType: 6594us [6594us] (43.84%; 79.88%)
+ InferType: 6916us [6916us] (45.14%; 45.14%)
+ FoldScaleAxis: 8405us [6us] (54.86%; 54.86%)
+ FoldConstant: 8399us [1735us] (54.82%; 99.93%)
+ InferType: 6664us [6664us] (43.49%; 79.34%)
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 3217d596c2..beaa32e416 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: 54.145439 ms
+ Convolution: 49.608894 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 76991bfb41..2fd2adaa55 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.225891 ms
+ conv2d with tensor core: 12.536627 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 a4e3550294..e0e3738737 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: 0.017845
- Baseline: 3.513482
+ Numpy running time: 0.018991
+ Baseline: 3.245249
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.298230
+ Opt1: 0.307920
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.328769
+ Opt2: 0.337509
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114181
+ Opt3: 0.115460
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109886
+ Opt4: 0.109356
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111266
+ Opt5: 0.110808
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146703
+ Opt6: 0.146717
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 91538d140d..c38c1bc22c 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.135** total execution time for **how_to_optimize_operators** files:
+**00:34.543** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.423 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.963 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.480 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.100 | 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 1125517fb4..c79e4c6c57 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:17.222** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:57.170** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:52.068 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:31.898 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.925 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.389 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:00.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:00.664 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.646 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.814 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.474 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.058 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.690 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.347 | 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 8c0af3e0f4..b1765a3f7c 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
@@ -240,93 +240,152 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), 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" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 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" = 224;
- 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_3: Buffer(data_2, float32, [25088], [])[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- if @tir.likely((threadIdx.x_1 < 176), dtype=bool) {
- 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_3[((((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)
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12))] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + (floor [...]
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((7 < floormod((threadIdx.x_1*12), 63)) && (floormod((threadIdx.x_1*12), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod((threadIdx.x_1 [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 1)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 1), 63)) && (floormod(((threadIdx.x_1*12) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 1), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx.x_1* [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 2)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 2), 63)) && (floormod(((threadIdx.x_1*12) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 2), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx.x_1*5 [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 3)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 3), 63)) && (floormod(((threadIdx.x_1*12) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 3), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 4)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 4), 63)) && (floormod(((threadIdx.x_1*12) + 4), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 4), 63), 7)*7)) + rx.outer.outer) + floormod(((threadId [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 5)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 5), 63)) && (floormod(((threadIdx.x_1*12) + 5), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 5), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 6)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 6), 63)) && (floormod(((threadIdx.x_1*12) + 6), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 6), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 7)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 7), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)*7)) + rx.outer.outer) + floormod((threadIdx. [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 8)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 8), 63)) && (floormod(((threadIdx.x_1*12) + 8), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 8), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 9)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 9), 63)) && (floormod(((threadIdx.x_1*12) + 9), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 9), 63), 7)*7)) + rx.outer.outer) + floormod(((threadIdx [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 10)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 10), 63)) && (floormod(((threadIdx.x_1*12) + 10), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 10), 63), 7)*7)) + rx.outer.outer) + floormod(((thre [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 11)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 11), 63)) && (floormod(((threadIdx.x_1*12) + 11), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 11), 63), 7)*7)) + rx.outer.outer) + floormod(((threa [...]
}
}
- }
- for (rc.outer.inner: int32, 0, 8) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 2) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 48)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 164), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ }
+ 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*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 816)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 864)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 912)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 771)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 819)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 867)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 915)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 774)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 822)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 870)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 918)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 777)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 825)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 873)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 921)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 780)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 828)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 876)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 924)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 783)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 831)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 879)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 927)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 786)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 834)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 882)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 930)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 789)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 837)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 885)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 933)]))
}
}
}
}
}
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -381,7 +440,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.235 ms
+ Execution time of this operator: 0.392 ms
@@ -429,33 +488,33 @@ 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=1)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
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=32)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ 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=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=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_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=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ 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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -476,16 +535,16 @@ 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=12)
+ 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=224)
+ 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=196)
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)
+ 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=12)
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=224)
+ 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=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -503,84 +562,141 @@ 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__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+ extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[1008];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++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) + 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) + 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) + 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) + 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);
- if (((int)threadIdx.x) < 176) {
- 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);
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12))] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((7 < ((((int)threadIdx.x) * 12) % 63)) && (((((int)threadIdx.x) * 12) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + ((((((int)threadIdx.x) * 12) % 63) / 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.000000e+00f);
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((7 <= (((((int)threadIdx.x) * 12) + 1) % 63)) && ((((((int)threadIdx.x) * 12) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 1) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 1) % 7)) - 8)] : [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((7 < (((((int)threadIdx.x) * 12) + 2) % 63)) && ((((((int)threadIdx.x) * 12) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 2) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 2) % 7)) - 8)] : [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((7 < (((((int)threadIdx.x) * 12) + 3) % 63)) && ((((((int)threadIdx.x) * 12) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 3) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 3) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((7 <= (((((int)threadIdx.x) * 12) + 4) % 63)) && ((((((int)threadIdx.x) * 12) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 4) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 4) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((7 < (((((int)threadIdx.x) * 12) + 5) % 63)) && ((((((int)threadIdx.x) * 12) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 5) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 5) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((7 < (((((int)threadIdx.x) * 12) + 6) % 63)) && ((((((int)threadIdx.x) * 12) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 6) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 6) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 12) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) / 7) + 1) % 9) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.00000 [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((7 < (((((int)threadIdx.x) * 12) + 8) % 63)) && ((((((int)threadIdx.x) * 12) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 8) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 1) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((7 < (((((int)threadIdx.x) * 12) + 9) % 63)) && ((((((int)threadIdx.x) * 12) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 9) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 2) % 7)) - [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 10)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((7 <= (((((int)threadIdx.x) * 12) + 10) % 63)) && ((((((int)threadIdx.x) * 12) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 10) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 3) % 7 [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 11)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((7 < (((((int)threadIdx.x) * 12) + 11) % 63)) && ((((((int)threadIdx.x) * 12) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 11) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threadIdx.x) * 5) + 4) % 7) [...]
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 4) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 4) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 20) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 164) {
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 28) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 816)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 864)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 144)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 912)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 771)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 819)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 867)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 147)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 915)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 774)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 822)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 870)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 150)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 918)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 777)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 825)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 873)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 921)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 780)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 828)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 876)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 924)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 783)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 831)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 879)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 927)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 786)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 834)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 882)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 930)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 789)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 837)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 885)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 165)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 933)]));
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
@@ -642,7 +758,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 52.068 seconds)
+ **Total running time of the script:** ( 5 minutes 31.898 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 a81707725a..a18d7e601c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8948 7.8930 7.9033 7.8881 0.0063
+ 7.8485 7.8484 7.8516 7.8454 0.0025
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.418 seconds)
+ **Total running time of the script:** ( 1 minutes 0.664 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index fdfadbcb51..3a97629146 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 752.3145 753.0379 754.9002 749.0054 2.4603
+ 755.9013 755.2582 757.2791 755.1665 0.9750
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 30.925 seconds)
+ **Total running time of the script:** ( 1 minutes 31.389 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 adfc3a090b..df483ba956 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,178 +386,27 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [64]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.outer.inner: int32, 0, 2) {
- let cse_var_1: int32 = (i.outer.inner*32)
- {
- compute_4: Buffer(compute_3, float32, [64], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 0f32
- compute_4[(cse_var_1 + 16)] = 0f32
- compute_4[(cse_var_1 + 17)] = 0f32
- compute_4[(cse_var_1 + 18)] = 0f32
- compute_4[(cse_var_1 + 19)] = 0f32
- compute_4[(cse_var_1 + 20)] = 0f32
- compute_4[(cse_var_1 + 21)] = 0f32
- compute_4[(cse_var_1 + 22)] = 0f32
- compute_4[(cse_var_1 + 23)] = 0f32
- compute_4[(cse_var_1 + 24)] = 0f32
- compute_4[(cse_var_1 + 25)] = 0f32
- compute_4[(cse_var_1 + 26)] = 0f32
- compute_4[(cse_var_1 + 27)] = 0f32
- compute_4[(cse_var_1 + 28)] = 0f32
- compute_4[(cse_var_1 + 29)] = 0f32
- compute_4[(cse_var_1 + 30)] = 0f32
- compute_4[(cse_var_1 + 31)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i1.outer + 1)] - placeholder_15[i1.outer])) {
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[i1.outer]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_2: int32 = (cse_var_1 + 1)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_3: int32 = (cse_var_1 + 2)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_4: int32 = (cse_var_1 + 3)
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_5: int32 = (cse_var_1 + 4)
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_6: int32 = (cse_var_1 + 5)
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_7: int32 = (cse_var_1 + 6)
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_8: int32 = (cse_var_1 + 7)
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_9: int32 = (cse_var_1 + 8)
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_10: int32 = (cse_var_1 + 9)
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_11: int32 = (cse_var_1 + 10)
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_12: int32 = (cse_var_1 + 11)
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_13: int32 = (cse_var_1 + 12)
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_14: int32 = (cse_var_1 + 13)
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_15: int32 = (cse_var_1 + 14)
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_16: int32 = (cse_var_1 + 15)
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_17: int32 = (cse_var_1 + 16)
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[((placeholder_15[i1.outer]*16) + (elem_idx*16))]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_18: int32 = (cse_var_1 + 17)
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_19: int32 = (cse_var_1 + 18)
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_20: int32 = (cse_var_1 + 19)
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_21: int32 = (cse_var_1 + 20)
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_22: int32 = (cse_var_1 + 21)
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_23: int32 = (cse_var_1 + 22)
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_24: int32 = (cse_var_1 + 23)
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_25: int32 = (cse_var_1 + 24)
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_26: int32 = (cse_var_1 + 25)
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_27: int32 = (cse_var_1 + 26)
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_28: int32 = (cse_var_1 + 27)
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_29: int32 = (cse_var_1 + 28)
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_30: int32 = (cse_var_1 + 29)
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_31: int32 = (cse_var_1 + 30)
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_32: int32 = (cse_var_1 + 31)
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = ((i.inner*16) + j)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_33: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_33, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_33, 1, 16)]), broadcast(0f32, 16))
+ 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_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -613,7 +462,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.114 ms
+ Execution time of this operator: 1.684 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 af673d9196..5a55d2675f 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
=================
-**00:55.706** total execution time for **how_to_tune_with_autotvm** files:
+**00:38.701** 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``) | 00:55.671 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:38.663 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 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 cd95c18dd8..3a14c6ae1f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -387,7 +387,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1196325
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7737275
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,7 +510,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9278350
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3204802
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -633,7 +633,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7565676
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904150
No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -756,7 +756,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2219367
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7760839
No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -879,8 +879,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3131307
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620741
+ No: 6 GFLOPS: 2.34/2.34 result: MeasureResult(costs=(0.09906224799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9588117599487305, timestamp=1669636977.7683833) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746338
+ No: 7 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1002,9 +1003,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4829712
- No: 7 GFLOPS: 10.23/10.23 result: MeasureResult(costs=(0.022631632333333332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.106280088424683, timestamp=1669635993.7076814) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7153635
- No: 8 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7432442
+ No: 8 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,8 +1126,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8957809
- No: 9 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4755383
+ No: 9 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,8 +1249,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7859670
- No: 10 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6662910
+ No: 10 GFLOPS: 0.00/2.34 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
@@ -1372,26 +1372,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,215536
- No: 11 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9129256
- No: 12 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4233511
+ No: 11 GFLOPS: 0.00/2.34 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
@@ -1513,8 +1495,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2458452
- No: 13 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8818349
+ No: 12 GFLOPS: 0.00/2.34 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
@@ -1636,9 +1618,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3713559
- No: 14 GFLOPS: 6.77/10.23 result: MeasureResult(costs=(0.034220126999999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.805394887924194, timestamp=1669636010.9434955) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4493691
- No: 15 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2681356
+ No: 13 GFLOPS: 0.00/2.34 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
@@ -1760,8 +1741,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4830485
- No: 16 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5610233
+ No: 14 GFLOPS: 7.47/7.47 result: MeasureResult(costs=(0.03098774325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.33935809135437, timestamp=1669636981.5201042) [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
+ No: 15 GFLOPS: 0.00/7.47 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
@@ -1883,8 +1865,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9755364
- No: 17 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127872
+ No: 16 GFLOPS: 0.00/7.47 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
@@ -2006,8 +1988,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9872859
- No: 18 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,494076
+ No: 17 GFLOPS: 0.00/7.47 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
@@ -2129,8 +2111,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7461157
- No: 19 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10002729
+ No: 18 GFLOPS: 0.00/7.47 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
@@ -2252,8 +2234,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3120049
- No: 20 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,911536
+ No: 19 GFLOPS: 0.00/7.47 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
@@ -2375,7 +2357,130 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5641938
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9628256
+ No: 20 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1750
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1694
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1618
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1750
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1694
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1618
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9846618
@@ -2430,9 +2535,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7153635
+ [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
Finish loading 20 records
- Time cost of this operator: 0.020952
+ Time cost of this operator: 0.025340
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 e7a8868b11..ee57eac1b5 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.97 (1, 6, 10, 10) 1 1 [3.063]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.305 (1, 1, 10, 10, 3) 1 1 [0.964]
- Total_time - 315.827 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.709 (1, 2, 10, 10, 3) 2 1 [312.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.982 (1, 6, 10, 10) 1 1 [3.11]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.31 (1, 1, 10, 10, 3) 1 1 [0.982]
+ Total_time - 316.892 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.5 97.35 (1, 6, 10, 10, 1) 2 1 [101.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.711 (1, 6, 10, 10) 1 1 [1.784]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.939 (1, 1, 10, 10, 3) 1 1 [0.979]
- Total_time - 104.263 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.51 (1, 6, 10, 10, 1) 2 1 [103.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.687 (1, 6, 10, 10) 1 1 [1.782]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.803 (1, 3, 10, 10, 1) 1 1 [0.848]
+ Total_time - 105.63 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index f4e8e3f559..0a08803f44 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 93.7MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 73.8MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.554 seconds)
+ **Total running time of the script:** ( 1 minutes 4.758 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index c245b0480f..8785b7aad3 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/tmp6rp2qp8r/images/random'
+ '/tmp/tmpjto5t1tf/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp6rp2qp8r/images/target contains 8144 images
- /tmp/tmp6rp2qp8r/images/random contains 5000 images
+ /tmp/tmpjto5t1tf/images/target contains 8144 images
+ /tmp/tmpjto5t1tf/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2358 - accuracy: 0.9152 - val_loss: 0.1334 - val_accuracy: 0.9509 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2341 - accuracy: 0.9201 - val_loss: 0.1064 - val_accuracy: 0.9653 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1025 - accuracy: 0.9624 - val_loss: 0.1520 - val_accuracy: 0.9581 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.1084 - accuracy: 0.9589 - val_loss: 0.1079 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0681 - accuracy: 0.9740 - val_loss: 0.1073 - val_accuracy: 0.9645 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0589 - accuracy: 0.9781 - val_loss: 0.0970 - val_accuracy: 0.9675 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fed9571cd90>
+ <keras.callbacks.History object at 0x7fc15ed50990>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 29.433 seconds)
+ **Total running time of the script:** ( 3 minutes 59.372 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 58c5749360..5e147b6d1f 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:32.946** total execution time for **how_to_work_with_microtvm** files:
+**06:07.586** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:29.433 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 03:59.372 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.554 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:04.758 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.246 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.994 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.363 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.844 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 50ccee1acb..d1feff1f01 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.506** total execution time for **how_to_work_with_relay** files:
+**00:44.803** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.712 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.406 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.091 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.358 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.697 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:02.033 | 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 6439ae7834..d7a5f3a461 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 0x7fed911b0f80>
+ <function my_cuda_math_rule at 0x7fc1d85d5710>
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 9afc9b5c64..9e8a351d9c 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:07.806** total execution time for **how_to_work_with_schedules** files:
+**00:06.367** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.302 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.826 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.141 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.201 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.573 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.571 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.558 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.115 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 1a65daacc2..5a9b6a7dd1 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp2ane7p6d/input0.cc'\nsource_filename = \"/tmp/tmp2ane7p6d/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/tmpq6rzp0lm/input0.cc'\nsource_filename = \"/tmp/tmpq6rzp0lm/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 1d88e42dd7..2729aa314c 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:26.804** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:27.294** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.797 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.287 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index ca68114f11..229079fc64 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 28.00s!
+ resnet18_v1 inference graph built in 30.43s!
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 904137c534..0384c3a108 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.50s!
+ yolov3-tiny inference graph built in 20.39s!
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 a5d6d8ec6e..4ce6115ab1 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:41.033** total execution time for **topic_vta_tutorials_frontend** files:
+**01:42.511** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:53.106 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.033 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.927 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.478 | 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 b6ea2f2491..e4e81aeb2c 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
=================
-**00:03.433** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.166** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.964 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.709 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.469 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.456 | 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 1955309420..e3a691b31d 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
=================
-**00:00.817** total execution time for **topic_vta_tutorials** files:
+**00:00.804** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.440 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.377 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.374 | 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 6eb48ea34b..6962ab7f21 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -208,7 +208,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
*E
-
+ .T
@@ -332,7 +332,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.907 ms
+ Execution time of this operator: 95.375 ms
@@ -432,7 +432,7 @@ resume the status and do more 5 trials.
Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-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)
- *E
+
@@ -450,7 +450,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 37.097 seconds)
+ **Total running time of the script:** ( 1 minutes 36.969 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 fb6ec20bd5..6fd77423c9 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 4.45/4.45 result: MeasureResult(costs=(0.060319006200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1383030414581299, timestamp=1669634543.5370293) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 2 GFLOPS: 10.92/10.92 result: MeasureResult(costs=(0.0245707674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6365196704864502, timestamp=1669634544.1341) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 3 GFLOPS: 12.16/12.16 result: MeasureResult(costs=(0.0220767356,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.516369104385376, timestamp=1669634545.3876193) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
- No: 4 GFLOPS: 10.99/12.16 result: MeasureResult(costs=(0.024414915,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5305252075195312, timestamp=1669634546.6733775) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
- No: 5 GFLOPS: 3.86/12.16 result: MeasureResult(costs=(0.0695422342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2823612689971924, timestamp=1669634548.0687015) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
- No: 6 GFLOPS: 2.15/12.16 result: MeasureResult(costs=(0.12483302460000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1376290321350098, timestamp=1669634550.2290375) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 7 GFLOPS: 11.25/12.16 result: MeasureResult(costs=(0.0238624368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.536381721496582, timestamp=1669634551.5259862) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
- No: 8 GFLOPS: 0.50/12.16 result: MeasureResult(costs=(0.5372063008000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.775827169418335, timestamp=1669634560.3277595) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
- No: 9 GFLOPS: 3.53/12.16 result: MeasureResult(costs=(0.0759908606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3318145275115967, timestamp=1669634561.8010848) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
- No: 10 GFLOPS: 10.50/12.16 result: MeasureResult(costs=(0.0255610974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5622196197509766, timestamp=1669634562.3788826) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 1 GFLOPS: 2.57/2.57 result: MeasureResult(costs=(0.10462719839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8281018733978271, timestamp=1669635554.1587062) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 2 GFLOPS: 12.99/12.99 result: MeasureResult(costs=(0.020664898600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5226318836212158, timestamp=1669635554.699581) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 3 GFLOPS: 10.19/12.99 result: MeasureResult(costs=(0.026348740400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8465473651885986, timestamp=1669635556.0615485) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 4 GFLOPS: 8.70/12.99 result: MeasureResult(costs=(0.030860226799999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8248922824859619, timestamp=1669635557.4794347) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+ No: 5 GFLOPS: 4.07/12.99 result: MeasureResult(costs=(0.06600606540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2161962985992432, timestamp=1669635558.8116148) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
+ No: 6 GFLOPS: 2.43/12.99 result: MeasureResult(costs=(0.1103962426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.913161277770996, timestamp=1669635561.514688) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 7 GFLOPS: 0.90/12.99 result: MeasureResult(costs=(0.2998592632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942259311676025, timestamp=1669635566.4768138) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+ No: 8 GFLOPS: 1.91/12.99 result: MeasureResult(costs=(0.1405420992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.429777145385742, timestamp=1669635568.932175) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 9 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.018724787799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.47362279891967773, timestamp=1669635569.5193236) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 10 GFLOPS: 10.73/14.34 result: MeasureResult(costs=(0.0250093266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562950611114502, timestamp=1669635570.0888388) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 6c70f36b74..74f2eda5ed 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 509.48449451999295, 'median': 509.4376562999969, 'std': 2.30095285721133}
+ {'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
@@ -554,31 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.29/ 17.55 GFLOPS | Progress: (4/20) | 7.66 s
[Task 1/25] Current/Best: 23.79/ 23.79 GFLOPS | Progress: (8/20) | 11.32 s
[Task 1/25] Current/Best: 9.21/ 23.79 GFLOPS | Progress: (12/20) | 16.46 s
[Task 1/25] Current/Best: 4.26/ 23.79 GFLOPS | Progress: (16/20) | 20.00 s
[Task 1/25] Current/Best: 9.93/ 23.79 GFLOPS | Progress: (20/20) | 21.77 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 14.92/ 18.73 GFLOPS | Progress: (4/20) | 3.44 s
[Task 2/25] Current/Best: 6.37/ 18.73 GFLOPS | Progress: (8/20) | 4.92 s
[Task 2/25] Current/Best: 5.21/ 18.84 GFLOPS | Progress: (12/20) | 6.53 s
[Task 2/25] Current/Best: 17.01/ 18.84 GFLOPS | Progress: (16/20) | 8.26 s
[Task 2/25] Current/Best: 20.89/ 21.83 GFLOPS | Progress: (20/20) | 9.21 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 5.79/ 21.66 GFLOPS | Progress: (4/20) | 3.85 s
[Task 3/25] Current/Best: 12.71/ 21.66 GFLOPS | Progress: (8/20) | 6.24 s
[Task 3/25] Current/Best: 19.15/ 24.16 GFLOPS | Progress: (12/20) | 7.91 s
[Task 3/25] Current/Best: 11.98/ 24.16 GFLOPS | Progress: (16/20) | 9.60 s
[Task 3/25] Current/Best: 16.42/ 24.16 GFLOPS | Progress: (20/20) | 12.12 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 8.94/ 16.99 GFLOPS | Progress: (4/20) | 3.81 s
[Task 4/25] Current/Best: 5.38/ 16.99 GFLOPS | Progress: (8/20) | 9.52 s
[Task 4/25] Current/Best: 6.35/ 17.08 GFLOPS | Progress: (12/20) | 20.37 s
[Task 4/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (16/20) | 26.81 s
[Task 4/25] Current/Best: 2.94/ 18.10 GFLOPS | Progress: (20/20) | 28.45 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 8.37/ 13.49 GFLOPS | Progress: (4/20) | 3.63 s
[Task 5/25] Current/Best: 14.13/ 14.76 GFLOPS | Progress: (8/20) | 5.13 s
[Task 5/25] Current/Best: 5.29/ 19.80 GFLOPS | Progress: (12/20) | 7.19 s
[Task 5/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (16/20) | 8.73 s
[Task 5/25] Current/Best: 16.09/ 21.09 GFLOPS | Progress: (20/20) | 10.50 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 4.14 s
[Task 6/25] Current/Best: 9.51/ 18.18 GFLOPS | Progress: (8/20) | 6.48 s
[Task 6/25] Current/Best: 10.53/ 22.32 GFLOPS | Progress: (12/20) | 9.04 s
[Task 6/25] Current/Best: 4.07/ 22.32 GFLOPS | Progress: (16/20) | 11.39 s
[Task 6/25] Current/Best: 13.19/ 22.32 GFLOPS | Progress: (20/20) | 14.83 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.75/ 16.19 GFLOPS | Progress: (4/20) | 3.77 s
[Task 7/25] Current/Best: 12.69/ 16.19 GFLOPS | Progress: (8/20) | 6.13 s
[Task 7/25] Current/Best: 10.86/ 16.19 GFLOPS | Progress: (12/20) | 8.76 s
[Task 7/25] Current/Best: 11.53/ 16.19 GFLOPS | Progress: (16/20) | 12.18 s
[Task 7/25] Current/Best: 12.24/ 23.29 GFLOPS | Progress: (20/20) | 14.77 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 7.33/ 17.48 GFLOPS | Progress: (4/20) | 7.19 s
[Task 8/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (8/20) | 14.22 s
[Task 8/25] Current/Best: 6.44/ 20.84 GFLOPS | Progress: (12/20) | 16.69 s
[Task 8/25] Current/Best: 13.79/ 20.84 GFLOPS | Progress: (16/20) | 18.53 s
[Task 8/25] Current/Best: 14.61/ 20.84 GFLOPS | Progress: (20/20) | 23.75 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 9.18/ 18.92 GFLOPS | Progress: (4/20) | 6.00 s
[Task 9/25] Current/Best: 7.09/ 18.92 GFLOPS | Progress: (8/20) | 7.77 s
[Task 9/25] Current/Best: 4.79/ 18.92 GFLOPS | Progress: (12/20) | 18.89 s
[Task 9/25] Current/Best: 8.58/ 18.92 GFLOPS | Progress: (16/20) | 25.31 s
[Task 9/25] Current/Best: 12.40/ 18.92 GFLOPS | Progress: (20/20) | 26.68 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 11.44/ 17.30 GFLOPS | Progress: (4/20) | 3.39 s
[Task 10/25] Current/Best: 4.83/ 17.53 GFLOPS | Progress: (8/20) | 6.32 s
[Task 10/25] Current/Best: 9.25/ 19.48 GFLOPS | Progress: (12/20) | 7.68 s
[Task 10/25] Current/Best: 4.23/ 19.48 GFLOPS | Progress: (16/20) | 10.35 s
[Task 10/25] Current/Best: 11.74/ 19.48 GFLOPS | Progress: (20/20) | 13.06 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.35/ 14.30 GFLOPS | Progress: (4/20) | 4.27 s
[Task 11/25] Current/Best: 12.76/ 14.30 GFLOPS | Progress: (8/20) | 6.40 s
[Task 11/25] Current/Best: 16.03/ 20.86 GFLOPS | Progress: (12/20) | 8.36 s
[Task 11/25] Current/Best: 11.55/ 20.86 GFLOPS | Progress: (16/20) | 10.67 s
[Task 11/25] Current/Best: 18.32/ 20.86 GFLOPS | Progress: (20/20) | 14.10 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.40/ 16.43 GFLOPS | Progress: (4/20) | 4.49 s
[Task 12/25] Current/Best: 16.67/ 18.84 GFLOPS | Progress: (8/20) | 6.39 s
[Task 12/25] Current/Best: 7.61/ 18.84 GFLOPS | Progress: (12/20) | 9.92 s
[Task 12/25] Current/Best: 15.80/ 18.84 GFLOPS | Progress: (16/20) | 16.07 s
[Task 12/25] Current/Best: 16.88/ 18.84 GFLOPS | Progress: (20/20) | 18.32 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.40/ 16.27 GFLOPS | Progress: (4/20) | 4.15 s
[Task 13/25] Current/Best: 15.10/ 18.50 GFLOPS | Progress: (8/20) | 6.08 s
[Task 13/25] Current/Best: 11.61/ 23.09 GFLOPS | Progress: (12/20) | 10.19 s
[Task 13/25] Current/Best: 21.37/ 23.09 GFLOPS | Progress: (16/20) | 13.18 s
[Task 13/25] Current/Best: 14.70/ 23.09 GFLOPS | Progress: (20/20) | 16.94 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.46/ 14.58 GFLOPS | Progress: (4/20) | 4.17 s
[Task 14/25] Current/Best: 9.33/ 16.12 GFLOPS | Progress: (8/20) | 6.69 s
[Task 14/25] Current/Best: 8.12/ 16.12 GFLOPS | Progress: (12/20) | 9.17 s
[Task 14/25] Current/Best: 13.50/ 17.61 GFLOPS | Progress: (16/20) | 11.44 s
[Task 14/25] Current/Best: 17.37/ 17.61 GFLOPS | Progress: (20/20) | 13.59 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.30/ 22.41 GFLOPS | Progress: (4/20) | 3.36 s
[Task 15/25] Current/Best: 19.52/ 22.41 GFLOPS | Progress: (8/20) | 5.22 s
[Task 15/25] Current/Best: 20.09/ 22.41 GFLOPS | Progress: (12/20) | 7.29 s
[Task 15/25] Current/Best: 11.43/ 22.41 GFLOPS | Progress: (16/20) | 10.06 s
[Task 15/25] Current/Best: 14.03/ 23.67 GFLOPS | Progress: (20/20) | 11.34 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.93/ 16.93 GFLOPS | Progress: (4/20) | 3.86 s
[Task 16/25] Current/Best: 6.49/ 16.93 GFLOPS | Progress: (8/20) | 5.86 s
[Task 16/25] Current/Best: 16.61/ 18.21 GFLOPS | Progress: (12/20) | 7.12 s
[Task 16/25] Current/Best: 10.45/ 18.21 GFLOPS | Progress: (16/20) | 9.70 s
[Task 16/25] Current/Best: 18.03/ 18.21 GFLOPS | Progress: (20/20) |
11.31 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 5.45 s
[Task 17/25] Current/Best: 6.96/ 17.55 GFLOPS | Progress: (8/20) | 7.54 s
[Task 17/25] Current/Best: 17.31/ 17.67 GFLOPS | Progress: (12/20) | 9.19 s
[Task 17/25] Current/Best: 22.52/ 22.52 GFLOPS | Progress: (16/20) | 11.69 s
[Task 17/25] Current/Best: 18.83/ 22.52 GFLOPS | Progress: (20/20) | 14.17 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.72/ 22.55 GFLOPS | Progress: (4/20) | 3.32 s
[Task 18/25] Current/Best: 13.05/ 22.55 GFLOPS | Progress: (8/20) | 5.81 s Done.
-
[Task 18/25] Current/Best: 11.43/ 22.55 GFLOPS | Progress: (12/20) | 8.11 s
[Task 18/25] Current/Best: 10.68/ 22.55 GFLOPS | Progress: (16/20) | 13.31 s
[Task 18/25] Current/Best: 20.06/ 22.55 GFLOPS | Progress: (20/20) | 15.28 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 2.70/ 20.16 GFLOPS | Progress: (4/20) | 4.70 s
[Task 19/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (8/20) | 6.97 s
[Task 19/25] Current/Best: 19.00/ 20.74 GFLOPS | Progress: (12/20) | 9.76 s
[Task 19/25] Current/Best: 17.96/ 21.39 GFLOPS | Progress: (16/20) | 13.52 s
[Task 19/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (20/20) | 16.30 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (4/20) | 3.89 s
[Task 20/25] Current/Best: 6.38/ 21.19 GFLOPS | Progress: (8/20) | 7.47 s
[Task 20/25] Current/Best: 8.97/ 21.19 GFLOPS | Progress: (12/20) | 9.84 s
[Task 20/25] Current/Best: 8.66/ 21.19 GFLOPS | Progress: (16/20) | 12.02 s
[Task 20/25] Current/Best: 2.08/ 21.19 GFLOPS | Progress: (20/20) | 16.70 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.44/ 9.98 GFLOPS | Progress: (4/20) | 3.02 s
[Task 21/25] Current/Best: 14.58/ 18.87 GFLOPS | Progress: (8/20) | 5.05 s
[Task 21/25] Current/Best: 12.51/ 18.87 GFLOPS | Progress: (12/20) | 6.32 s Done.
-
[Task 21/25] Current/Best: 10.76/ 20.82 GFLOPS | Progress: (16/20) | 7.98 s
[Task 21/25] Current/Best: 17.89/ 20.82 GFLOPS | Progress: (20/20) | 10.03 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.89/ 17.00 GFLOPS | Progress: (4/20) | 2.81 s
[Task 22/25] Current/Best: 10.19/ 20.47 GFLOPS | Progress: (8/20) | 5.58 s
[Task 22/25] Current/Best: 17.68/ 20.47 GFLOPS | Progress: (12/20) | 6.89 s
[Task 22/25] Current/Best: 2.70/ 22.02 GFLOPS | Progress: (16/20) | 8.62 s
[Task 22/25] Current/Best: 6.91/ 22.02 GFLOPS | Progress: (20/20) | 10.99 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 11.27/ 18.67 GFLOPS | Progress: (4/20) | 5.48 s
[Task 23/25] Current/Best: 9.52/ 20.81 GFLOPS | Progress: (8/20) | 7.91 s
[Task 23/25] Current/Best: 12.07/ 23.11 GFLOPS | Progress: (12/20) | 12.85 s
[Task 23/25] Current/Best: 3.09/ 23.11 GFLOPS | Progress: (16/20) | 15.98 s
[Task 23/25] Current/Best: 7.19/ 23.11 GFLOPS | Progress: (20/20) | 19.21 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.31/ 6.31 GFLOPS | Progress: (4/20) | 12.20 s
[Task 24/25] Current/Best: 6.58/ 6.58 GFLOPS | Progress: (8/20) | 17.95 s
[Task 24/25] Current/Best: 9.53/ 9.53 GFLOPS | Progress: (12/20) | 21.79 s
[Task 24/25] Current/Best: 6.24/ 9.53 GFLOPS | Progress: (16/20) | 32.04 s
[Task 24/25] Current/Best: 6.62/ 9.53 GFLOPS | Progress: (20/20) | 43.81 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 5.82/ 5.82 GFLOPS | Progress: (4/20) | 3.72 s
[Task 25/25] Current/Best: 6.81/ 6.87 GFLOPS | Progress: (8/20) | 11.45 s
[Task 25/25] Current/Best: 3.02/ 6.87 GFLOPS | Progress: (12/20) | 13.53 s
[Task 25/25] Current/Best: 7.43/ 8.91 GFLOPS | Progress: (16/20) | 14.90 s
[Task 25/25] Current/Best: 8.64/ 9.94 GFLOPS | Progress: (20/20) | 18.31 s Done.
-
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.35/ 17.91 GFLOPS | Progress: (4/20) | 7.20 s
[Task 1/25] Current/Best: 12.44/ 17.91 GFLOPS | Progress: (8/20) | 11.21 s
[Task 1/25] Current/Best: 11.17/ 17.91 GFLOPS | Progress: (12/20) | 13.91 s
[Task 1/25] Current/Best: 7.15/ 21.25 GFLOPS | Progress: (16/20) | 15.77 s
[Task 1/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 17.76 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 7.60/ 15.88 GFLOPS | Progress: (4/20) | 2.84 s
[Task 2/25] Current/Best: 6.13/ 15.88 GFLOPS | Progress: (8/20) | 4.18 s
[Task 2/25] Current/Best: 21.69/ 21.69 GFLOPS | Progress: (12/20) | 5.27 s
[Task 2/25] Current/Best: 9.51/ 21.69 GFLOPS | Progress: (16/20) | 6.84 s
[Task 2/25] Current/Best: 16.65/ 21.69 GFLOPS | Progress: (20/20) | 8.55 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.57/ 15.33 GFLOPS | Progress: (4/20) | 3.77 s
[Task 3/25] Current/Best: 11.61/ 15.33 GFLOPS | Progress: (8/20) | 6.09 s
[Task 3/25] Current/Best: 12.42/ 19.62 GFLOPS | Progress: (12/20) | 8.00 s
[Task 3/25] Current/Best: 17.84/ 19.62 GFLOPS | Progress: (16/20) | 10.12 s
[Task 3/25] Current/Best: 10.16/ 19.86 GFLOPS | Progress: (20/20) | 11.98 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 3.42 s
[Task 4/25] Current/Best: 6.16/ 17.31 GFLOPS | Progress: (8/20) | 5.18 s
[Task 4/25] Current/Best: 9.28/ 22.19 GFLOPS | Progress: (12/20) | 9.94 s
[Task 4/25] Current/Best: 6.47/ 22.19 GFLOPS | Progress: (16/20) | 11.93 s
[Task 4/25] Current/Best: 19.38/ 22.19 GFLOPS | Progress: (20/20) | 13.25 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 3.56 s
[Task 5/25] Current/Best: 6.00/ 12.20 GFLOPS | Progress: (8/20) | 5.54 s
[Task 5/25] Current/Best: 3.08/ 20.88 GFLOPS | Progress: (12/20) | 7.43 s
[Task 5/25] Current/Best: 8.04/ 22.55 GFLOPS | Progress: (16/20) | 9.54 s
[Task 5/25] Current/Best: 17.91/ 22.55 GFLOPS | Progress: (20/20) | 11.11 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/20) | 4.83 s
[Task 6/25] Current/Best: 10.60/ 18.77 GFLOPS | Progress: (8/20) | 9.56 s
[Task 6/25] Current/Best: 12.17/ 18.77 GFLOPS | Progress: (12/20) | 11.66 s
[Task 6/25] Current/Best: 8.38/ 18.77 GFLOPS | Progress: (16/20) | 14.00 s
[Task 6/25] Current/Best: 9.76/ 18.77 GFLOPS | Progress: (20/20) | 19.03 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.25/ 15.25 GFLOPS | Progress: (4/20) | 4.15 s
[Task 7/25] Current/Best: 12.06/ 15.25 GFLOPS | Progress: (8/20) | 6.06 s
[Task 7/25] Current/Best: 15.13/ 15.75 GFLOPS | Progress: (12/20) | 8.50 s
[Task 7/25] Current/Best: 7.11/ 15.84 GFLOPS | Progress: (16/20) | 11.07 s
[Task 7/25] Current/Best: 15.83/ 15.84 GFLOPS | Progress: (20/20) | 13.12 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.39/ 12.87 GFLOPS | Progress: (4/20) | 5.76 s
[Task 8/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (8/20) | 8.17 s
[Task 8/25] Current/Best: 11.20/ 20.71 GFLOPS | Progress: (12/20) | 16.64 s
[Task 8/25] Current/Best: 12.92/ 20.71 GFLOPS | Progress: (16/20) | 19.86 s
[Task 8/25] Current/Best: 4.14/ 20.71 GFLOPS | Progress: (20/20) | 22.65 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 22.53/ 22.53 GFLOPS | Progress: (4/20) | 4.80 s
[Task 9/25] Current/Best: 12.86/ 22.53 GFLOPS | Progress: (8/20) | 6.48 s
[Task 9/25] Current/Best: 16.12/ 22.53 GFLOPS | Progress: (12/20) | 10.27 s
[Task 9/25] Current/Best: 14.03/ 22.53 GFLOPS | Progress: (16/20) | 13.29 s
[Task 9/25] Current/Best: 14.10/ 22.53 GFLOPS | Progress: (20/20) | 17.00 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 3.60 s
[Task 10/25] Current/Best: 12.30/ 18.22 GFLOPS | Progress: (8/20) | 4.96 s
[Task 10/25] Current/Best: 11.81/ 20.44 GFLOPS | Progress: (12/20) | 7.80 s
[Task 10/25] Current/Best: 13.28/ 20.44 GFLOPS | Progress: (16/20) | 10.40 s
[Task 10/25] Current/Best: 18.40/ 20.44 GFLOPS | Progress: (20/20) | 12.83 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 13.02/ 20.82 GFLOPS | Progress: (4/20) | 4.99 s
[Task 11/25] Current/Best: 13.52/ 21.49 GFLOPS | Progress: (8/20) | 8.20 s
[Task 11/25] Current/Best: 11.47/ 21.49 GFLOPS | Progress: (12/20) | 10.32 s
[Task 11/25] Current/Best: 17.80/ 21.49 GFLOPS | Progress: (16/20) | 12.25 s
[Task 11/25] Current/Best: 6.15/ 22.38 GFLOPS | Progress: (20/20) | 14.79 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.13/ 13.79 GFLOPS | Progress: (4/20) | 3.64 s
[Task 12/25] Current/Best: 17.47/ 18.18 GFLOPS | Progress: (8/20) | 5.29 s
[Task 12/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 7.44 s
[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (16/20) | 9.65 s
[Task 12/25] Current/Best: 14.82/ 19.04 GFLOPS | Progress: (20/20) | 11.55 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.00/ 12.99 GFLOPS | Progress: (4/20) | 4.78 s
[Task 13/25] Current/Best: 15.11/ 16.32 GFLOPS | Progress: (8/20) | 7.61 s
[Task 13/25] Current/Best: 11.00/ 16.32 GFLOPS | Progress: (12/20) | 12.11 s
[Task 13/25] Current/Best: 8.41/ 18.24 GFLOPS | Progress: (16/20) | 16.97 s
[Task 13/25] Current/Best: 13.37/ 18.24 GFLOPS | Progress: (20/20) | 20.01 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 10.44/ 14.69 GFLOPS | Progress: (4/20) | 4.47 s
[Task 14/25] Current/Best: 14.24/ 14.69 GFLOPS | Progress: (8/20) | 9.95 s
[Task 14/25] Current/Best: 12.34/ 17.20 GFLOPS | Progress: (12/20) | 12.11 s
[Task 14/25] Current/Best: 18.32/ 18.97 GFLOPS | Progress: (16/20) | 14.80 s
[Task 14/25] Current/Best: 3.03/ 18.97 GFLOPS | Progress: (20/20) | 17.62 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 12.24/ 15.99 GFLOPS | Progress: (4/20) | 7.54 s
[Task 15/25] Current/Best: 12.69/ 18.08 GFLOPS | Progress: (8/20) | 9.63 s
[Task 15/25] Current/Best: 3.12/ 18.08 GFLOPS | Progress: (12/20) | 11.82 s Done.
+
[Task 15/25] Current/Best: 13.44/ 18.08 GFLOPS | Progress: (16/20) | 14.49 s
[Task 15/25] Current/Best: 15.82/ 18.08 GFLOPS | Progress: (20/20) | 16.39 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 18.27/ 21.01 GFLOPS | Progress: (4/20) | 3.27 s
[Task 16/25] Current/Best: 11.84/ 21.01 GFLOPS | Progress: (8/20) | 5.21 s
[Task 16/25] Current/Best: 13.75/ 21.66 GFLOPS | Progress: (12/20) | 6.83 s
[Task 16/25] Current/Best: 12.15/ 22.09 GFLOPS | Progress: (16/20) | 9.27 s
[Task 16/25] Current/Best: 12.27/ 22.09 GFLOPS | Progress: (20/20) | 11.17 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.03/ 22.98 GFLOPS | Progress: (4/20) | 3.54 s
[Task 17/25] Current/Best: 9.48/ 22.98 GFLOPS | Progress: (8/20) | 6.35 s
[Task 17/25] Current/Best: 10.16/ 22.98 GFLOPS | Progress: (12/20) | 8.84 s
[Task 17/25] Current/Best: 11.86/ 22.98 GFLOPS | Progress: (16/20) | 11.73 s
[Task 17/25] Current/Best: 5.20/ 22.98 GFLOPS | Progress: (20/20) | 14.23 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 14.35/ 14.35 GFLOPS | Progress: (4/20) | 3.93 s
[Task 18/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (8/20) | 5.40 s
[Task 18/25] Current/Best: 15.69/ 22.72 GFLOPS | Progress: (12/20) | 9.31 s
[Task 18/25] Current/Best: 13.96/ 22.72 GFLOPS | Progress: (16/20) | 11.42 s
[Task 18/25] Current/Best: 17.39/ 22.72 GFLOPS | Progress: (20/20) | 14.88 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.56/ 14.25 GFLOPS | Progress: (4/20) | 5.04 s
[Task 19/25] Current/Best: 21.33/ 21.97 GFLOPS | Progress: (8/20) | 7.31 s
[Task 19/25] Current/Best: 8.39/ 21.97 GFLOPS | Progress: (12/20) | 12.43 s
[Task 19/25] Current/Best: 10.35/ 21.97 GFLOPS | Progress: (16/20) | 17.63 s
[Task 19/25] Current/Best: 17.07/ 21.97 GFLOPS | Progress: (20/20) | 20.53 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 3.32 s
[Task 20/25] Current/Best: 11.65/ 18.84 GFLOPS | Progress: (8/20) | 6.55 s
[Task 20/25] Current/Best: 16.43/ 18.84 GFLOPS | Progress: (12/20) | 9.11 s
[Task 20/25] Current/Best: 8.84/ 18.84 GFLOPS | Progress: (16/20) | 12.91 s
[Task 20/25] Current/Best: 16.06/ 18.84 GFLOPS | Progress: (20/20) | 14.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 12.44/ 17.26 GFLOPS | Progress: (4/20) | 4.37 s
[Task 21/25] Current/Best: 10.99/ 17.26 GFLOPS | Progress: (8/20) | 6.21 s Done.
+
[Task 21/25] Current/Best: 7.57/ 17.26 GFLOPS | Progress: (12/20) | 8.48 s
[Task 21/25] Current/Best: 17.11/ 17.26 GFLOPS | Progress: (16/20) | 11.26 s
[Task 21/25] Current/Best: 14.08/ 17.26 GFLOPS | Progress: (20/20) | 15.30 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.55/ 13.88 GFLOPS | Progress: (4/20) | 4.35 s
[Task 22/25] Current/Best: 4.52/ 16.29 GFLOPS | Progress: (8/20) | 6.07 s
[Task 22/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.43 s
[Task 22/25] Current/Best: 7.08/ 19.56 GFLOPS | Progress: (16/20) | 9.63 s
[Task 22/25] Current/Best: 18.66/ 19.56 GFLOPS | Progress: (20/20) | 11.32 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 4.42/ 19.23 GFLOPS | Progress: (4/20) | 3.77 s
[Task 23/25] Current/Best: 11.96/ 20.75 GFLOPS | Progress: (8/20) | 5.70 s
[Task 23/25] Current/Best: 17.04/ 20.75 GFLOPS | Progress: (12/20) | 8.37 s
[Task 23/25] Current/Best: 20.41/ 20.75 GFLOPS | Progress: (16/20) | 11.13 s
[Task 23/25] Current/Best: 18.96/ 20.75 GFLOPS | Progress: (20/20) | 16.82 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.77/ 5.76 GFLOPS | Progress: (4/20) | 4.72 s
[Task 24/25] Current/Best: 1.45/ 7.07 GFLOPS | Progress: (8/20) | 15.22 s
[Task 24/25] Current/Best: 2.59/ 7.18 GFLOPS | Progress: (12/20) | 25.98 s
[Task 24/25] Current/Best: 2.80/ 7.18 GFLOPS | Progress: (16/20) | 37.65 s
[Task 24/25] Current/Best: 4.45/ 7.18 GFLOPS | Progress: (20/20) | 49.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 25/25] Current/Best: 3.02/ 8.42 GFLOPS | Progress: (4/20) | 4.89 s
[Task 25/25] Current/Best: 1.54/ 8.42 GFLOPS | Progress: (8/20) | 15.65 s
[Task 25/25] Current/Best: 3.00/ 9.40 GFLOPS | Progress: (12/20) | 19.98 s
[Task 25/25] Current/Best: 3.82/ 9.40 GFLOPS | Progress: (16/20) | 30.71 s
[Task 25/25] Current/Best: 5.73/ 9.40 GFLOPS | Progress: (20/20) | 34.15 s
@@ -674,8 +674,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.35988089999137, 'median': 414.94138310001745, 'std': 1.9609314523928856}
- unoptimized: {'mean': 509.48449451999295, 'median': 509.4376562999969, 'std': 2.30095285721133}
+ optimized: {'mean': 430.0801938499967, 'median': 430.3779723499929, 'std': 2.429183228660658}
+ unoptimized: {'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 35.977 seconds)
+ **Total running time of the script:** ( 10 minutes 43.197 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 7cee35c1a2..5335169695 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.27e-07 secs/op
+ 1.271e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 0b6332773b..30d2480849 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x219c9550)), stage(b, placeholder(b, 0x265e7b60)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0xe8b6070)), stage(b, placeholder(b, 0x28a726d0)), 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 22132cfad4..47beedc667 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:12.284** total execution time for **tutorial** files:
+**14:17.904** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:35.977 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:43.197 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:37.097 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.969 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.845 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.362 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:32.969 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.192 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.820 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:21.967 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.766 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.254 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.633 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.777 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.170 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.175 | 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``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index aad0c08dc7..0c32a022db 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -295,7 +295,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000009
+ naive: 0.000007
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.642809998993471e-06 1.0
- naive 8.7419e-06 1.3159942857502454
- parallel 6.0449e-06 0.9099914043779566
- vector 2.45548e-05 3.6964477387913526
+ numpy 7.441079999352951e-06 1.0
+ naive 6.696100000000001e-06 0.8998828127882337
+ parallel 6.950399999999999e-06 0.9340579594097067
+ vector 2.53151e-05 3.4020733552389317
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017584
+ Numpy running time: 0.019053
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.404196
+ none: 3.256209
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.301546
+ blocking: 0.314476
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.336378
+ vectorization: 0.345962
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.115073
+ loop permutation: 0.119863
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108399
+ array packing: 0.110230
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110960
+ block caching: 0.110165
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145340
+ parallelization: 0.146200
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4041964893999994 1.0
- blocking 0.3015460689 0.08858068852340203
- vectorization 0.3363781226 0.09881278112101212
- loop permutation 0.1150728701 0.033803239753731715
- array packing 0.1083985735 0.03184263124573799
- block caching 0.1109600669 0.032595082935285284
- parallelization 0.14534000419999998 0.042694364045248345
+ none 3.2562085157 1.0
+ blocking 0.3144764388 0.09657748798448669
+ vectorization 0.3459622566 0.10624696020906607
+ loop permutation 0.1198630473 0.036810617846514834
+ array packing 0.1102295502 0.033852116554735905
+ block caching 0.11016505830000001 0.03383231072851531
+ parallelization 0.14619960810000002 0.044898724204881245
@@ -1652,11 +1652,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.845 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 076e760356..195621ac50 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b6151bcaa239c48dbec3c79aeef62c9c7780e147
+fc59b6dbdf445c09f70d20c8156cc940f696fdcd
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index fb6994646d..9630ce4116 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.984 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.613 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index f2243608f5..71f55e8c3e 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 897ms/step
+1/1 [==============================] - 1s 1s/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index d0a68fcad1..2705446ccc 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6aac35ae-2a9c-4a6c-86ad-de7b9bfe0368 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.zip97a78d84-9dd6-45c0-a1bb-ed12a2d188dd 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 bf5e560c7b..6182647b39 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,12 +448,10 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 52.1MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 60.3MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 53.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 61.5MB/s]
- 92%|#########2| 38.2M/41.5M [00:00<00:00, 60.5MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 56.2MB/s]
+ 28%|##8 | 11.8M/41.5M [00:00<00:00, 124MB/s]
+ 57%|#####6 | 23.6M/41.5M [00:00<00:00, 109MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 105MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 106MB/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 bb724a8635..4e3cb71159 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,14 +431,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 14%|#4 | 6.30M/44.7M [00:00<00:00, 53.0MB/s]
- 27%|##7 | 12.1M/44.7M [00:00<00:00, 57.0MB/s]
- 39%|###9 | 17.5M/44.7M [00:00<00:00, 48.6MB/s]
- 58%|#####8 | 26.1M/44.7M [00:00<00:00, 55.5MB/s]
- 71%|####### | 31.7M/44.7M [00:00<00:00, 48.7MB/s]
- 86%|########5 | 38.3M/44.7M [00:00<00:00, 44.3MB/s]
- 98%|#########8| 43.8M/44.7M [00:00<00:00, 47.6MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 49.7MB/s]
+ 26%|##6 | 11.8M/44.7M [00:00<00:00, 123MB/s]
+ 53%|#####2 | 23.5M/44.7M [00:00<00:00, 109MB/s]
+ 76%|#######6 | 34.0M/44.7M [00:00<00:00, 105MB/s]
+ 99%|#########8| 44.0M/44.7M [00:00<00:00, 103MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/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 981ddc12dd..9655212b9f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.010 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.118 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 292dd0b97f..e9520af4ff 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:48.431</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:42.732</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -348,44 +348,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:13.984</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>01:13.118</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>01:12.010</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>01:09.613</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>00:47.848</p></td>
+<td><p>00:46.430</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.496</p></td>
+<td><p>00:31.885</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:28.549</p></td>
+<td><p>00:29.059</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:26.412</p></td>
+<td><p>00:26.510</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.399</p></td>
+<td><p>00:24.404</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.461</p></td>
+<td><p>00:22.305</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>00:16.784</p></td>
+<td><p>00:17.022</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>00:02.488</p></td>
+<td><p>00:02.386</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index e77eef3104..1b37eda98e 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,10 +919,10 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3339.1324 3338.3742 3343.3233 3336.8353 2.0746
+ 3344.6771 3343.5188 3359.0259 3336.9567 6.5112
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.800 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.226 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 14a4f0919b..50b794c140 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9765 15.9888 16.5506 15.4907 0.3792
+ 16.1232 15.9256 16.9046 15.7265 0.4393
</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 ae130b23a3..01d6bae03b 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,30 +453,23 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:03, 52.3MB/s]
- 7%|6 | 11.3M/170M [00:00<00:04, 36.8MB/s]
- 9%|9 | 16.0M/170M [00:00<00:04, 36.1MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 43.8MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 50.6MB/s]
- 24%|##3 | 40.0M/170M [00:00<00:02, 58.1MB/s]
- 28%|##8 | 48.0M/170M [00:00<00:02, 61.0MB/s]
- 34%|###3 | 56.9M/170M [00:01<00:01, 69.7MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 61.4MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 65.4MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 68.6MB/s]
- 51%|#####1 | 86.7M/170M [00:01<00:01, 69.1MB/s]
- 55%|#####5 | 93.5M/170M [00:01<00:01, 57.3MB/s]
- 58%|#####8 | 99.4M/170M [00:01<00:01, 55.8MB/s]
- 62%|######1 | 105M/170M [00:01<00:01, 55.5MB/s]
- 67%|######7 | 114M/170M [00:02<00:00, 63.7MB/s]
- 71%|####### | 120M/170M [00:02<00:00, 63.8MB/s]
- 76%|#######5 | 129M/170M [00:02<00:00, 70.2MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 72.5MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 74.2MB/s]
- 89%|########9 | 152M/170M [00:02<00:00, 65.8MB/s]
- 93%|#########3| 158M/170M [00:02<00:00, 65.1MB/s]
- 97%|#########6| 165M/170M [00:02<00:00, 61.2MB/s]
-100%|##########| 170M/170M [00:02<00:00, 60.0MB/s]
+ 9%|8 | 14.6M/170M [00:00<00:01, 153MB/s]
+ 17%|#7 | 29.2M/170M [00:00<00:01, 116MB/s]
+ 24%|##4 | 40.8M/170M [00:00<00:01, 108MB/s]
+ 30%|### | 51.3M/170M [00:00<00:01, 106MB/s]
+ 36%|###6 | 61.6M/170M [00:00<00:01, 104MB/s]
+ 42%|####2 | 71.6M/170M [00:00<00:01, 99.5MB/s]
+ 48%|####7 | 81.2M/170M [00:00<00:00, 97.9MB/s]
+ 53%|#####3 | 90.5M/170M [00:00<00:00, 87.2MB/s]
+ 59%|#####8 | 100M/170M [00:01<00:00, 90.8MB/s]
+ 64%|######4 | 109M/170M [00:01<00:00, 90.8MB/s]
+ 69%|######9 | 118M/170M [00:01<00:00, 90.5MB/s]
+ 75%|#######4 | 127M/170M [00:01<00:00, 92.4MB/s]
+ 80%|######## | 136M/170M [00:01<00:00, 68.0MB/s]
+ 87%|########6 | 147M/170M [00:01<00:00, 78.7MB/s]
+ 92%|#########1| 156M/170M [00:01<00:00, 78.4MB/s]
+ 96%|#########6| 164M/170M [00:01<00:00, 74.2MB/s]
+100%|##########| 170M/170M [00:01<00:00, 90.0MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -574,7 +567,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 18.004 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 16.418 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 37dbfa7937..11f706ceec 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 90%|######### | 12.2M/13.6M [00:00<00:00, 128MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 124MB/s]
+ 86%|########6 | 11.7M/13.6M [00:00<00:00, 91.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 99.0MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2100 90.1585 91.5626 89.9461 0.2206
+ 90.2859 90.1851 92.7542 90.0537 0.3070
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.277 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.492 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 408545d716..e065426b6c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.9358 118.8613 125.9193 117.8568 0.8452
+ 120.6198 120.6334 122.5440 119.6961 0.4538
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.857 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.458 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 0aec425222..63f5d4c34a 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.186 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.534 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 18aa9eb7c7..1b11900ab1 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6121/132723 [00:00<00:02, 61200.72KB/s]
- 11%|# | 14588/132723 [00:00<00:01, 74993.90KB/s]
- 17%|#7 | 22995/132723 [00:00<00:01, 79134.43KB/s]
- 24%|##3 | 31436/132723 [00:00<00:01, 81214.55KB/s]
- 30%|##9 | 39779/132723 [00:00<00:01, 82011.73KB/s]
- 36%|###6 | 48168/132723 [00:00<00:01, 82648.32KB/s]
- 43%|####2 | 56572/132723 [00:00<00:00, 83101.02KB/s]
- 49%|####9 | 65061/132723 [00:00<00:00, 83666.60KB/s]
- 55%|#####5 | 73430/132723 [00:00<00:00, 83671.70KB/s]
- 62%|######1 | 81894/132723 [00:01<00:00, 83967.73KB/s]
- 68%|######8 | 90381/132723 [00:01<00:00, 84241.73KB/s]
- 74%|#######4 | 98806/132723 [00:01<00:00, 70024.85KB/s]
- 81%|######## | 107253/132723 [00:01<00:00, 73854.61KB/s]
- 87%|########6 | 114969/132723 [00:01<00:00, 63019.21KB/s]
- 93%|#########3| 123433/132723 [00:01<00:00, 68392.94KB/s]
- 99%|#########9| 131961/132723 [00:01<00:00, 72817.52KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 76021.56KB/s]
+ 3%|3 | 4538/132723 [00:00<00:02, 44814.51KB/s]
+ 9%|9 | 11993/132723 [00:00<00:01, 62213.42KB/s]
+ 15%|#5 | 20557/132723 [00:00<00:01, 72876.88KB/s]
+ 22%|##1 | 29146/132723 [00:00<00:01, 77993.37KB/s]
+ 28%|##8 | 37813/132723 [00:00<00:01, 81115.11KB/s]
+ 35%|###4 | 46453/132723 [00:00<00:01, 82907.69KB/s]
+ 41%|####1 | 55020/132723 [00:00<00:00, 83808.82KB/s]
+ 48%|####8 | 63742/132723 [00:00<00:00, 84891.79KB/s]
+ 55%|#####4 | 72422/132723 [00:00<00:00, 85485.81KB/s]
+ 61%|######1 | 81184/132723 [00:01<00:00, 86142.15KB/s]
+ 68%|######7 | 89799/132723 [00:01<00:00, 86131.44KB/s]
+ 74%|#######4 | 98532/132723 [00:01<00:00, 86493.05KB/s]
+ 81%|######## | 107215/132723 [00:01<00:00, 86593.44KB/s]
+ 87%|########7 | 115918/132723 [00:01<00:00, 86724.06KB/s]
+ 94%|#########3| 124591/132723 [00:01<00:00, 86465.60KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 82996.38KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +516,7 @@ 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 59.365 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.738 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 2f3d38c404..5b969f604c 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:49.339</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:32.624</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:18.004</p></td>
+<td><p>03:16.418</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>02:59.365</p></td>
+<td><p>03:04.738</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>02:21.857</p></td>
+<td><p>02:23.458</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>01:36.186</p></td>
+<td><p>01:15.534</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>01:08.277</p></td>
+<td><p>01:06.492</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>01:01.800</p></td>
+<td><p>01:01.226</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:34.594</p></td>
+<td><p>00:35.516</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>00:24.834</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
+<td><p>00:24.734</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>00:24.416</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
+<td><p>00:24.502</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index ac9bbaeec5..6d9b6c569c 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip768c7128-9046-4ec7-8beb-84bfd58b6b1d 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.zip714dc02d-2f12-4161-a4c5-d99666d55c17 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 7e45148b30..c2f7c7d827 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:49.113</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:49.266</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.631</p></td>
+<td><p>00:45.688</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>00:02.425</p></td>
+<td><p>00:02.509</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.050</p></td>
+<td><p>00:01.062</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 127d485ff5..6354c3419b 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7378us [7378us] (46.46%; 46.46%)
-FoldScaleAxis: 8501us [6us] (53.54%; 53.54%)
- FoldConstant: 8495us [1706us] (53.50%; 99.92%)
- InferType: 6789us [6789us] (42.75%; 79.92%)
+InferType: 7449us [7449us] (46.52%; 46.52%)
+FoldScaleAxis: 8566us [8us] (53.48%; 53.48%)
+ FoldConstant: 8557us [1755us] (53.43%; 99.91%)
+ InferType: 6802us [6802us] (42.47%; 79.49%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6781us [6781us] (45.09%; 45.09%)
-FoldScaleAxis: 8259us [5us] (54.91%; 54.91%)
- FoldConstant: 8254us [1660us] (54.88%; 99.94%)
- InferType: 6594us [6594us] (43.84%; 79.88%)
+InferType: 6916us [6916us] (45.14%; 45.14%)
+FoldScaleAxis: 8405us [6us] (54.86%; 54.86%)
+ FoldConstant: 8399us [1735us] (54.82%; 99.93%)
+ InferType: 6664us [6664us] (43.49%; 79.34%)
</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 0e68747007..bb0f1ef762 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.145439 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 49.608894 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 4e68bfdb70..e46fd0cccf 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.225891 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.536627 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 267ade662e..2edb696079 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017845
-Baseline: 3.513482
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018991
+Baseline: 3.245249
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298230
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.307920
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328769
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337509
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114181
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115460
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109886
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109356
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111266
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110808
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146703
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146717
</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 b7178a5b6d..fdb1b2c3e0 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.135</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.543</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.423</p></td>
+<td><p>00:31.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.529</p></td>
+<td><p>00:01.480</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.183</p></td>
+<td><p>00:01.100</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 1171ab12b3..f5b0f57b14 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:17.222</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:57.170</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:52.068</p></td>
+<td><p>05:31.898</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>01:30.925</p></td>
+<td><p>01:31.389</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:00.418</p></td>
+<td><p>01:00.664</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>00:29.646</p></td>
+<td><p>00:29.814</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.474</p></td>
+<td><p>00:12.058</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.690</p></td>
+<td><p>00:11.347</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 f37bd12f42..f1d8d6815e 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
@@ -504,93 +504,152 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [7]), 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" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 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" = 224;
- 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_3: Buffer(data_2, float32, [25088], [])[((((cse_var_1 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- 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_3[((((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" = 224;
- if @tir.likely((threadIdx.x_1 < 176), dtype=bool) {
- 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_3[((((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)
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12))] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + [...]
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((7 < floormod((threadIdx.x_1*12), 63)) && (floormod((threadIdx.x_1*12), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21 [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 1)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 1), 63)) && (floormod(((threadIdx.x_1*12) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 1), 63), 7)*7)) + rx.outer.ou [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 2)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*32) + (threadIdx.x_2*4)), 48), 3)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 2), 63)) && (floormod(((threadIdx.x_1*12) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*4), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 2), 63), 7)*7)) + rx.outer.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 3)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 3), 63)) && (floormod(((threadIdx.x_1*12) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 3), 63), 7)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 4)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 4), 63)) && (floormod(((threadIdx.x_1*12) + 4), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 4), 63), 7)*7)) + rx.ou [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 5)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 1), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 1), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 5), 63)) && (floormod(((threadIdx.x_1*12) + 5), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 1), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 5), 63), 7)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 6)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 6), 63)) && (floormod(((threadIdx.x_1*12) + 6), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 6), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 6), 63), 7)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 7)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 7), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*5), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*5), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floormod((floordiv((threadIdx.x_1*12), 7) + 1), 9)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 8)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)) + 2), 48), 3)*9)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_2) + 2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 8), 63)) && (floormod(((threadIdx.x_1*12) + 8), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 1), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 2), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 8), 63), 7)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 9)] = kernel_3[(((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3))]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 9), 63)) && (floormod(((threadIdx.x_1*12) + 9), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 2), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 9), 63), 7)*7)) + rx.out [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 10)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 1)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*12) + 10), 63)) && (floormod(((threadIdx.x_1*12) + 10), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 3), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 10), 63), 7)*7)) + r [...]
}
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*7) + floordiv(threadIdx.x_2, 32)) < 12), dtype=bool) {
- kernel.shared_1[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2688) + (threadIdx.x_2*12)) + 11)] = kernel_3[((((((blockIdx.x*147456) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*896) + (threadIdx.x_2*4)), 3) + 1), 16)*9)) + (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + threadIdx.x_2), 3)*3)) + 2)]
+ if @tir.likely((threadIdx.x_1 < 84), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((7 < floormod(((threadIdx.x_1*12) + 11), 63)) && (floormod(((threadIdx.x_1*12) + 11), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*5) + 4), 7)) < 8)), data_3[((((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*4) + 3), 21)*49)) + (floordiv(floormod(((threadIdx.x_1*12) + 11), 63), 7)*7)) + rx [...]
}
}
- }
- for (rc.outer.inner: int32, 0, 8) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 2) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 48)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 48)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 48), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 48)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 16)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 164), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 48)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 48), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ }
+ 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*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 816)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 864)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 912)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 771)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 819)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 867)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 915)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 774)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 822)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 870)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 918)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 777)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 825)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 873)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 921)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 780)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 828)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 876)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 924)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 783)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 831)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 879)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 927)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 786)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 834)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 882)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 930)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 789)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 837)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 885)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (ry.outer.inner*7)) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*192) + (rc.outer.inner*24)) + ry.outer.inner) + 933)]))
}
}
}
}
}
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -627,7 +686,7 @@ 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: 0.235 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.392 ms
</pre></div>
</div>
</div>
@@ -656,33 +715,33 @@ 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=1)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=4)
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=32)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+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=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=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_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=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+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=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -703,16 +762,16 @@ 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=12)
+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=224)
+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=196)
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)
+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=12)
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=224)
+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=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -730,84 +789,141 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[7];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[4608];
+extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[1008];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++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) + 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) + 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) + 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) + 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);
- if (((int)threadIdx.x) < 176) {
- 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);
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12))] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((7 < ((((int)threadIdx.x) * 12) % 63)) && (((((int)threadIdx.x) * 12) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + ((((((int)threadIdx.x) * 12) % 63) / 7) * 7)) + rx_outer_outer) + ((((int)threadIdx.x) * 5) % 7)) - 8)] : 0.000000e+00f);
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 1)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 1)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((7 <= (((((int)threadIdx.x) * 12) + 1) % 63)) && ((((((int)threadIdx.x) * 12) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 1) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)thre [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 2)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 32) + (((int)threadIdx.x) * 4)) % 48) / 3) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3)) + 2)];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((7 < (((((int)threadIdx.x) * 12) + 2) % 63)) && ((((((int)threadIdx.x) * 12) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 2) % 63) / 7) * 7)) + rx_outer_outer) + (((((int)threa [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((7 < (((((int)threadIdx.x) * 12) + 3) % 63)) && ((((((int)threadIdx.x) * 12) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 3) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 4)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((7 <= (((((int)threadIdx.x) * 12) + 4) % 63)) && ((((((int)threadIdx.x) * 12) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 4) % 63) / 7) * 7)) + rx_outer_outer) + (((((in [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 5)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 1) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 1) % 3) [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((7 < (((((int)threadIdx.x) * 12) + 5) % 63)) && ((((((int)threadIdx.x) * 12) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 5) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((7 < (((((int)threadIdx.x) * 12) + 6) % 63)) && ((((((int)threadIdx.x) * 12) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 6) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 6) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 7)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 12) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 5) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) / 7) + 1) % 9) * 7)) + rx_outer_outer) + ((((int)threadI [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 8)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) + 2) % 48) / 3) * 9)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x)) + 2) % 3) [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((7 < (((((int)threadIdx.x) * 12) + 8) % 63)) && ((((((int)threadIdx.x) * 12) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 8) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * 3))];
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((7 < (((((int)threadIdx.x) * 12) + 9) % 63)) && ((((((int)threadIdx.x) * 12) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 9) % 63) / 7) * 7)) + rx_outer_outer) + (((((int [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 10)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((7 <= (((((int)threadIdx.x) * 12) + 10) % 63)) && ((((((int)threadIdx.x) * 12) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 10) % 63) / 7) * 7)) + rx_outer_outer) + ((( [...]
}
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 7) + (((int)threadIdx.x) >> 5)) < 12) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2688) + (((int)threadIdx.x) * 12)) + 11)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 144)) + ((((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 896) + (((int)threadIdx.x) * 4)) / 3) + 1) & 15) * 9)) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + ((int)threadIdx.x)) % 3) * [...]
+ if (((int)threadIdx.x) < 84) {
+ pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((7 < (((((int)threadIdx.x) * 12) + 11) % 63)) && ((((((int)threadIdx.x) * 12) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 5) + 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 21) * 49)) + (((((((int)threadIdx.x) * 12) + 11) % 63) / 7) * 7)) + rx_outer_outer) + (((( [...]
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 4) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 4) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 20) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 164) {
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 28) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 816)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 864)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 144)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 912)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 771)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 819)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 867)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 147)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 915)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 774)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 822)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 870)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 150)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 918)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 777)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 825)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 873)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 921)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 780)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 828)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 876)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 924)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 783)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 831)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 879)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 927)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 786)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 834)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 882)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 930)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 789)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 837)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 885)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 165)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 504) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 192) + (rc_outer_inner * 24)) + ry_outer_inner) + 933)]));
}
}
}
}
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
</pre></div>
@@ -844,7 +960,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 52.068 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 31.898 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 e0f44970a7..166b5e6bf4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8948 7.8930 7.9033 7.8881 0.0063
+ 7.8485 7.8484 7.8516 7.8454 0.0025
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.418 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.664 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 2072a8f2b8..261a8b44dd 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 752.3145 753.0379 754.9002 749.0054 2.4603
+ 755.9013 755.2582 757.2791 755.1665 0.9750
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.925 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.389 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 6456e02081..9705f2d496 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,178 +632,27 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer: int32, 0, 32) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [64]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.outer.inner: int32, 0, 2) {
- let cse_var_1: int32 = (i.outer.inner*32)
- {
- compute_4: Buffer(compute_3, float32, [64], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 0f32
- compute_4[(cse_var_1 + 16)] = 0f32
- compute_4[(cse_var_1 + 17)] = 0f32
- compute_4[(cse_var_1 + 18)] = 0f32
- compute_4[(cse_var_1 + 19)] = 0f32
- compute_4[(cse_var_1 + 20)] = 0f32
- compute_4[(cse_var_1 + 21)] = 0f32
- compute_4[(cse_var_1 + 22)] = 0f32
- compute_4[(cse_var_1 + 23)] = 0f32
- compute_4[(cse_var_1 + 24)] = 0f32
- compute_4[(cse_var_1 + 25)] = 0f32
- compute_4[(cse_var_1 + 26)] = 0f32
- compute_4[(cse_var_1 + 27)] = 0f32
- compute_4[(cse_var_1 + 28)] = 0f32
- compute_4[(cse_var_1 + 29)] = 0f32
- compute_4[(cse_var_1 + 30)] = 0f32
- compute_4[(cse_var_1 + 31)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i1.outer + 1)] - placeholder_15[i1.outer])) {
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[i1.outer]*16) + (elem_idx*16))]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_2: int32 = (cse_var_1 + 1)
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_3: int32 = (cse_var_1 + 2)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_4: int32 = (cse_var_1 + 3)
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_5: int32 = (cse_var_1 + 4)
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_6: int32 = (cse_var_1 + 5)
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_7: int32 = (cse_var_1 + 6)
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_8: int32 = (cse_var_1 + 7)
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_9: int32 = (cse_var_1 + 8)
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_10: int32 = (cse_var_1 + 9)
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_11: int32 = (cse_var_1 + 10)
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_12: int32 = (cse_var_1 + 11)
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_13: int32 = (cse_var_1 + 12)
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_14: int32 = (cse_var_1 + 13)
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_15: int32 = (cse_var_1 + 14)
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_16: int32 = (cse_var_1 + 15)
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[(((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_17: int32 = (cse_var_1 + 16)
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[((placeholder_15[i1.outer]*16) + (elem_idx*16))]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_18: int32 = (cse_var_1 + 17)
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_19: int32 = (cse_var_1 + 18)
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_20: int32 = (cse_var_1 + 19)
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_21: int32 = (cse_var_1 + 20)
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_22: int32 = (cse_var_1 + 21)
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_23: int32 = (cse_var_1 + 22)
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_24: int32 = (cse_var_1 + 23)
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_25: int32 = (cse_var_1 + 24)
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_26: int32 = (cse_var_1 + 25)
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_27: int32 = (cse_var_1 + 26)
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_28: int32 = (cse_var_1 + 27)
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_29: int32 = (cse_var_1 + 28)
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_30: int32 = (cse_var_1 + 29)
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_31: int32 = (cse_var_1 + 30)
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_15[(i1.outer + 1)] - placeholder_15[i1.outer])), dtype=bool) {
- let cse_var_32: int32 = (cse_var_1 + 31)
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder_17[((((i0.outer*1024) + (i.outer.inner*512)) + placeholder_18[(placeholder_15[i1.outer] + elem_idx)]) + 256)], 0f32)))
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.inner.init: int32, 0, 32) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = ((i.inner*16) + j)
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 4) {
- let cse_var_33: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_33, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_33, 1, 16)]), broadcast(0f32, 16))
+ 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_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -841,7 +690,7 @@ 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: 3.114 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.684 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 5b3e7abebc..7be26b6640 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:55.706</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:38.701</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:55.671</p></td>
+<td><p>00:38.663</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>00:00.020</p></td>
+<td><p>00:00.022</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 60d3e186bd..bbd2fdcf0d 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -689,7 +689,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1196325
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7737275
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -812,7 +812,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9278350
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3204802
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -935,7 +935,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7565676
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904150
No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1058,7 +1058,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2219367
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7760839
No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -1181,8 +1181,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3131307
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8620741
+No: 6 GFLOPS: 2.34/2.34 result: MeasureResult(costs=(0.09906224799999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.9588117599487305, timestamp=1669636977.7683833) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3746338
+No: 7 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1304,9 +1305,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4829712
-No: 7 GFLOPS: 10.23/10.23 result: MeasureResult(costs=(0.022631632333333332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.106280088424683, timestamp=1669635993.7076814) [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7153635
-No: 8 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7432442
+No: 8 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1428,8 +1428,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8957809
-No: 9 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4755383
+No: 9 GFLOPS: 0.00/2.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1551,8 +1551,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7859670
-No: 10 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6662910
+No: 10 GFLOPS: 0.00/2.34 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
@@ -1674,26 +1674,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,215536
-No: 11 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9129256
-No: 12 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4233511
+No: 11 GFLOPS: 0.00/2.34 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
@@ -1815,8 +1797,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2458452
-No: 13 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8818349
+No: 12 GFLOPS: 0.00/2.34 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
@@ -1938,9 +1920,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3713559
-No: 14 GFLOPS: 6.77/10.23 result: MeasureResult(costs=(0.034220126999999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.805394887924194, timestamp=1669636010.9434955) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4493691
-No: 15 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2681356
+No: 13 GFLOPS: 0.00/2.34 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
@@ -2062,8 +2043,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4830485
-No: 16 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5610233
+No: 14 GFLOPS: 7.47/7.47 result: MeasureResult(costs=(0.03098774325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.33935809135437, timestamp=1669636981.5201042) [('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
+No: 15 GFLOPS: 0.00/7.47 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
@@ -2185,8 +2167,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9755364
-No: 17 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7127872
+No: 16 GFLOPS: 0.00/7.47 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
@@ -2308,8 +2290,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9872859
-No: 18 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,494076
+No: 17 GFLOPS: 0.00/7.47 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
@@ -2431,8 +2413,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7461157
-No: 19 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10002729
+No: 18 GFLOPS: 0.00/7.47 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
@@ -2554,8 +2536,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3120049
-No: 20 GFLOPS: 0.00/10.23 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,911536
+No: 19 GFLOPS: 0.00/7.47 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
@@ -2677,7 +2659,130 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5641938
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9628256
+No: 20 GFLOPS: 0.00/7.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1750
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1694
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1618
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:389
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:375
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:270
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1750
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1694
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1618
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9846618
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2716,9 +2821,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7153635
+[('tile_f', [-1, 16, 8, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9301285
Finish loading 20 records
-Time cost of this operator: 0.020952
+Time cost of this operator: 0.025340
</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 7efc0e6744..5debb6e495 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -596,10 +596,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.725 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.97 (1, 6, 10, 10) 1 1 [3.063]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.305 (1, 1, 10, 10, 3) 1 1 [0.964]
-Total_time - 315.827 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.709 (1, 2, 10, 10, 3) 2 1 [312.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.11 0.982 (1, 6, 10, 10) 1 1 [3.11]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.31 (1, 1, 10, 10, 3) 1 1 [0.982]
+Total_time - 316.892 - - - - -
</pre></div>
</div>
</div>
@@ -650,10 +650,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 101.5 97.35 (1, 6, 10, 10, 1) 2 1 [101.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.711 (1, 6, 10, 10) 1 1 [1.784]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.939 (1, 1, 10, 10, 3) 1 1 [0.979]
-Total_time - 104.263 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.0 97.51 (1, 6, 10, 10, 1) 2 1 [103.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.687 (1, 6, 10, 10) 1 1 [1.782]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.803 (1, 3, 10, 10, 1) 1 1 [0.848]
+Total_time - 105.63 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index b1ee0b2c9e..8cdba227a5 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,7 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 93.7MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 73.8MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -564,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.554 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.758 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index df4a06beb2..13434f8f24 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp6rp2qp8r/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpjto5t1tf/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp6rp2qp8r/images/target contains 8144 images
-/tmp/tmp6rp2qp8r/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpjto5t1tf/images/target contains 8144 images
+/tmp/tmpjto5t1tf/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2358 - accuracy: 0.9152 - val_loss: 0.1334 - val_accuracy: 0.9509 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2341 - accuracy: 0.9201 - val_loss: 0.1064 - val_accuracy: 0.9653 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1025 - accuracy: 0.9624 - val_loss: 0.1520 - val_accuracy: 0.9581 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.1084 - accuracy: 0.9589 - val_loss: 0.1079 - val_accuracy: 0.9603 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0681 - accuracy: 0.9740 - val_loss: 0.1073 - val_accuracy: 0.9645 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0589 - accuracy: 0.9781 - val_loss: 0.0970 - val_accuracy: 0.9675 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7fed9571cd90>
+<keras.callbacks.History object at 0x7fc15ed50990>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 29.433 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 59.372 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 e484a0b15f..9803dc5fab 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:32.946</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:07.586</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:29.433</p></td>
+<td><p>03:59.372</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:02.554</p></td>
+<td><p>01:04.758</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.217</p></td>
+<td><p>00:51.246</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.994</p></td>
+<td><p>00:08.363</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.745</p></td>
+<td><p>00:03.844</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index ca115308ee..abef18a04f 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.506</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.803</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.712</p></td>
+<td><p>00:32.406</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>00:10.091</p></td>
+<td><p>00:10.358</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>00:01.697</p></td>
+<td><p>00:02.033</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 ecfeb9a782..165c54939b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fed911b0f80>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc1d85d5710>
</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 ad2ef1a481..6730dec7b8 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.806</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:06.367</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.302</p></td>
+<td><p>00:03.826</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.141</p></td>
+<td><p>00:01.201</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.573</p></td>
+<td><p>00:00.571</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>00:00.569</p></td>
+<td><p>00:00.558</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>00:00.118</p></td>
+<td><p>00:00.115</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.050</p></td>
+<td><p>00:00.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.032</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 880a1fc9d0..0e347290ca 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp2ane7p6d/input0.cc'\nsource_filename = \"/tmp/tmp2ane7p6d/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/tmpq6rzp0lm/input0.cc'\nsource_filename = \"/tmp/tmpq6rzp0lm/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 38a5061a1f..ae038e6855 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index cd07705b45..ad752e0c39 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/b6151bcaa/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 0df55a5454..e06874eb44 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/b6151bcaa/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 02457333d7..1257f8d494 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/b6151bcaa/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 00df364961..f2ec8c6ca8 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/b6151bcaa/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 a0dd1eb09e..65be0bf244 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/b6151bcaa/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 bf9c4ec6e8..a28e18a141 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/b6151bcaa/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 c63d08fd1b..2a325b6e7e 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/b6151bcaa/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 25419dfd8b..4a635042e5 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/b6151bcaa/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b6151bcaa/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 5ebddead82..045bfc455d 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/b6151bcaa/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 658fa1f4f0..b97c720d7a 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/b6151bcaa/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 21bdc1ef9d..b8987c2b2d 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/b6151bcaa/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 cf0f676946..cf1cff2f2b 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/b6151bcaa/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 cb75fe38c4..13b980b44d 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/b6151bcaa/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 e4690e8a05..16696f4acc 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/b6151bcaa/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 5f1409171b..51f42a843a 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/b6151bcaa/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 1b136fdac5..1d0ce5d272 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/b6151bcaa/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 c7f5b99ad4..de16ca81fb 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/b6151bcaa/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 1231e94a54..7caca5d181 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/b6151bcaa/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 a761991e5a..0d1f8eb87e 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/b6151bcaa/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 d8c21812ff..41afdfb8c0 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/b6151bcaa/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 912c3d1906..980f75bee6 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/b6151bcaa/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b6151bcaa/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 828f3c15fa..8add31aaeb 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/b6151bcaa/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 63e1053112..c7ca4e7707 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/b6151bcaa/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 7ae5e805ab..1858a8a909 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/b6151bcaa/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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/b6151bcaa/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fc59b6dbd/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 0e205aa5d1..f05c74f30d 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 0c01c9926e..c282a6786b 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:26.804</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:27.294</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.797</p></td>
+<td><p>00:27.287</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index b89a93bc28..c1f5e6c9db 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 28.00s!
+resnet18_v1 inference graph built in 30.43s!
</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 1c83547176..e289757d92 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.50s!
+yolov3-tiny inference graph built in 20.39s!
</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 8600829749..8edb89caeb 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:41.033</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:42.511</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:53.106</p></td>
+<td><p>00:52.033</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:47.927</p></td>
+<td><p>00:50.478</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 4835eefaea..dd26f73801 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.433</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.166</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.964</p></td>
+<td><p>00:02.709</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>00:00.469</p></td>
+<td><p>00:00.456</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 745a26e893..3313ce649d 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.817</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.804</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.440</p></td>
+<td><p>00:00.430</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>00:00.377</p></td>
+<td><p>00:00.374</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 99bd603659..7beb86e8a6 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -492,6 +492,7 @@ trials, we can load the best schedule from the log file and apply it.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+.T
</pre></div>
</div>
</div>
@@ -580,7 +581,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.907 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.375 ms
</pre></div>
</div>
</div>
@@ -644,7 +645,6 @@ 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:
/venv/apache-tvm-py3.7/lib/python3.7/site-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)
-*E
</pre></div>
</div>
</div>
@@ -655,7 +655,7 @@ 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 37.097 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.969 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 96a89cba70..4a7731c2d3 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 4.45/4.45 result: MeasureResult(costs=(0.060319006200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1383030414581299, timestamp=1669634543.5370293) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 2 GFLOPS: 10.92/10.92 result: MeasureResult(costs=(0.0245707674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6365196704864502, timestamp=1669634544.1341) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
-No: 3 GFLOPS: 12.16/12.16 result: MeasureResult(costs=(0.0220767356,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.516369104385376, timestamp=1669634545.3876193) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-No: 4 GFLOPS: 10.99/12.16 result: MeasureResult(costs=(0.024414915,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5305252075195312, timestamp=1669634546.6733775) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
-No: 5 GFLOPS: 3.86/12.16 result: MeasureResult(costs=(0.0695422342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2823612689971924, timestamp=1669634548.0687015) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
-No: 6 GFLOPS: 2.15/12.16 result: MeasureResult(costs=(0.12483302460000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1376290321350098, timestamp=1669634550.2290375) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 7 GFLOPS: 11.25/12.16 result: MeasureResult(costs=(0.0238624368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.536381721496582, timestamp=1669634551.5259862) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
-No: 8 GFLOPS: 0.50/12.16 result: MeasureResult(costs=(0.5372063008000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.775827169418335, timestamp=1669634560.3277595) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
-No: 9 GFLOPS: 3.53/12.16 result: MeasureResult(costs=(0.0759908606,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3318145275115967, timestamp=1669634561.8010848) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
-No: 10 GFLOPS: 10.50/12.16 result: MeasureResult(costs=(0.0255610974,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5622196197509766, timestamp=1669634562.3788826) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 1 GFLOPS: 2.57/2.57 result: MeasureResult(costs=(0.10462719839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8281018733978271, timestamp=1669635554.1587062) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+No: 2 GFLOPS: 12.99/12.99 result: MeasureResult(costs=(0.020664898600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5226318836212158, timestamp=1669635554.699581) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+No: 3 GFLOPS: 10.19/12.99 result: MeasureResult(costs=(0.026348740400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8465473651885986, timestamp=1669635556.0615485) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 4 GFLOPS: 8.70/12.99 result: MeasureResult(costs=(0.030860226799999994,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8248922824859619, timestamp=1669635557.4794347) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+No: 5 GFLOPS: 4.07/12.99 result: MeasureResult(costs=(0.06600606540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2161962985992432, timestamp=1669635558.8116148) [('tile_y', [-1, 4]), ('tile_x', [-1, 16])],None,42
+No: 6 GFLOPS: 2.43/12.99 result: MeasureResult(costs=(0.1103962426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.913161277770996, timestamp=1669635561.514688) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 7 GFLOPS: 0.90/12.99 result: MeasureResult(costs=(0.2998592632,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.942259311676025, timestamp=1669635566.4768138) [('tile_y', [-1, 64]), ('tile_x', [-1, 2])],None,16
+No: 8 GFLOPS: 1.91/12.99 result: MeasureResult(costs=(0.1405420992,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.429777145385742, timestamp=1669635568.932175) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 9 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.018724787799999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.47362279891967773, timestamp=1669635569.5193236) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+No: 10 GFLOPS: 10.73/14.34 result: MeasureResult(costs=(0.0250093266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562950611114502, timestamp=1669635570.0888388) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
</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 26519bc7fa..646322a3aa 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 509.48449451999295, 'median': 509.4376562999969, 'std': 2.30095285721133}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
</pre></div>
</div>
</div>
@@ -712,178 +712,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 14.29/ 17.55 GFLOPS | Progress: (4/20) | 7.66 s
-[Task 1/25] Current/Best: 23.79/ 23.79 GFLOPS | Progress: (8/20) | 11.32 s
-[Task 1/25] Current/Best: 9.21/ 23.79 GFLOPS | Progress: (12/20) | 16.46 s
-[Task 1/25] Current/Best: 4.26/ 23.79 GFLOPS | Progress: (16/20) | 20.00 s
-[Task 1/25] Current/Best: 9.93/ 23.79 GFLOPS | Progress: (20/20) | 21.77 s Done.
+[Task 1/25] Current/Best: 12.35/ 17.91 GFLOPS | Progress: (4/20) | 7.20 s
+[Task 1/25] Current/Best: 12.44/ 17.91 GFLOPS | Progress: (8/20) | 11.21 s
+[Task 1/25] Current/Best: 11.17/ 17.91 GFLOPS | Progress: (12/20) | 13.91 s
+[Task 1/25] Current/Best: 7.15/ 21.25 GFLOPS | Progress: (16/20) | 15.77 s
+[Task 1/25] Current/Best: 23.17/ 23.17 GFLOPS | Progress: (20/20) | 17.76 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 14.92/ 18.73 GFLOPS | Progress: (4/20) | 3.44 s
-[Task 2/25] Current/Best: 6.37/ 18.73 GFLOPS | Progress: (8/20) | 4.92 s
-[Task 2/25] Current/Best: 5.21/ 18.84 GFLOPS | Progress: (12/20) | 6.53 s
-[Task 2/25] Current/Best: 17.01/ 18.84 GFLOPS | Progress: (16/20) | 8.26 s
-[Task 2/25] Current/Best: 20.89/ 21.83 GFLOPS | Progress: (20/20) | 9.21 s Done.
+[Task 2/25] Current/Best: 7.60/ 15.88 GFLOPS | Progress: (4/20) | 2.84 s
+[Task 2/25] Current/Best: 6.13/ 15.88 GFLOPS | Progress: (8/20) | 4.18 s
+[Task 2/25] Current/Best: 21.69/ 21.69 GFLOPS | Progress: (12/20) | 5.27 s
+[Task 2/25] Current/Best: 9.51/ 21.69 GFLOPS | Progress: (16/20) | 6.84 s
+[Task 2/25] Current/Best: 16.65/ 21.69 GFLOPS | Progress: (20/20) | 8.55 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 5.79/ 21.66 GFLOPS | Progress: (4/20) | 3.85 s
-[Task 3/25] Current/Best: 12.71/ 21.66 GFLOPS | Progress: (8/20) | 6.24 s
-[Task 3/25] Current/Best: 19.15/ 24.16 GFLOPS | Progress: (12/20) | 7.91 s
-[Task 3/25] Current/Best: 11.98/ 24.16 GFLOPS | Progress: (16/20) | 9.60 s
-[Task 3/25] Current/Best: 16.42/ 24.16 GFLOPS | Progress: (20/20) | 12.12 s Done.
+[Task 3/25] Current/Best: 14.57/ 15.33 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 3/25] Current/Best: 11.61/ 15.33 GFLOPS | Progress: (8/20) | 6.09 s
+[Task 3/25] Current/Best: 12.42/ 19.62 GFLOPS | Progress: (12/20) | 8.00 s
+[Task 3/25] Current/Best: 17.84/ 19.62 GFLOPS | Progress: (16/20) | 10.12 s
+[Task 3/25] Current/Best: 10.16/ 19.86 GFLOPS | Progress: (20/20) | 11.98 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 8.94/ 16.99 GFLOPS | Progress: (4/20) | 3.81 s
-[Task 4/25] Current/Best: 5.38/ 16.99 GFLOPS | Progress: (8/20) | 9.52 s
-[Task 4/25] Current/Best: 6.35/ 17.08 GFLOPS | Progress: (12/20) | 20.37 s
-[Task 4/25] Current/Best: 18.10/ 18.10 GFLOPS | Progress: (16/20) | 26.81 s
-[Task 4/25] Current/Best: 2.94/ 18.10 GFLOPS | Progress: (20/20) | 28.45 s Done.
+[Task 4/25] Current/Best: 17.31/ 17.31 GFLOPS | Progress: (4/20) | 3.42 s
+[Task 4/25] Current/Best: 6.16/ 17.31 GFLOPS | Progress: (8/20) | 5.18 s
+[Task 4/25] Current/Best: 9.28/ 22.19 GFLOPS | Progress: (12/20) | 9.94 s
+[Task 4/25] Current/Best: 6.47/ 22.19 GFLOPS | Progress: (16/20) | 11.93 s
+[Task 4/25] Current/Best: 19.38/ 22.19 GFLOPS | Progress: (20/20) | 13.25 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 8.37/ 13.49 GFLOPS | Progress: (4/20) | 3.63 s
-[Task 5/25] Current/Best: 14.13/ 14.76 GFLOPS | Progress: (8/20) | 5.13 s
-[Task 5/25] Current/Best: 5.29/ 19.80 GFLOPS | Progress: (12/20) | 7.19 s
-[Task 5/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (16/20) | 8.73 s
-[Task 5/25] Current/Best: 16.09/ 21.09 GFLOPS | Progress: (20/20) | 10.50 s Done.
+[Task 5/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 3.56 s
+[Task 5/25] Current/Best: 6.00/ 12.20 GFLOPS | Progress: (8/20) | 5.54 s
+[Task 5/25] Current/Best: 3.08/ 20.88 GFLOPS | Progress: (12/20) | 7.43 s
+[Task 5/25] Current/Best: 8.04/ 22.55 GFLOPS | Progress: (16/20) | 9.54 s
+[Task 5/25] Current/Best: 17.91/ 22.55 GFLOPS | Progress: (20/20) | 11.11 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 4.14 s
-[Task 6/25] Current/Best: 9.51/ 18.18 GFLOPS | Progress: (8/20) | 6.48 s
-[Task 6/25] Current/Best: 10.53/ 22.32 GFLOPS | Progress: (12/20) | 9.04 s
-[Task 6/25] Current/Best: 4.07/ 22.32 GFLOPS | Progress: (16/20) | 11.39 s
-[Task 6/25] Current/Best: 13.19/ 22.32 GFLOPS | Progress: (20/20) | 14.83 s Done.
+[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 6/25] Current/Best: 10.60/ 18.77 GFLOPS | Progress: (8/20) | 9.56 s
+[Task 6/25] Current/Best: 12.17/ 18.77 GFLOPS | Progress: (12/20) | 11.66 s
+[Task 6/25] Current/Best: 8.38/ 18.77 GFLOPS | Progress: (16/20) | 14.00 s
+[Task 6/25] Current/Best: 9.76/ 18.77 GFLOPS | Progress: (20/20) | 19.03 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.75/ 16.19 GFLOPS | Progress: (4/20) | 3.77 s
-[Task 7/25] Current/Best: 12.69/ 16.19 GFLOPS | Progress: (8/20) | 6.13 s
-[Task 7/25] Current/Best: 10.86/ 16.19 GFLOPS | Progress: (12/20) | 8.76 s
-[Task 7/25] Current/Best: 11.53/ 16.19 GFLOPS | Progress: (16/20) | 12.18 s
-[Task 7/25] Current/Best: 12.24/ 23.29 GFLOPS | Progress: (20/20) | 14.77 s Done.
+[Task 7/25] Current/Best: 15.25/ 15.25 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 7/25] Current/Best: 12.06/ 15.25 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 7/25] Current/Best: 15.13/ 15.75 GFLOPS | Progress: (12/20) | 8.50 s
+[Task 7/25] Current/Best: 7.11/ 15.84 GFLOPS | Progress: (16/20) | 11.07 s
+[Task 7/25] Current/Best: 15.83/ 15.84 GFLOPS | Progress: (20/20) | 13.12 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 7.33/ 17.48 GFLOPS | Progress: (4/20) | 7.19 s
-[Task 8/25] Current/Best: 17.51/ 17.51 GFLOPS | Progress: (8/20) | 14.22 s
-[Task 8/25] Current/Best: 6.44/ 20.84 GFLOPS | Progress: (12/20) | 16.69 s
-[Task 8/25] Current/Best: 13.79/ 20.84 GFLOPS | Progress: (16/20) | 18.53 s
-[Task 8/25] Current/Best: 14.61/ 20.84 GFLOPS | Progress: (20/20) | 23.75 s Done.
+[Task 8/25] Current/Best: 4.39/ 12.87 GFLOPS | Progress: (4/20) | 5.76 s
+[Task 8/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (8/20) | 8.17 s
+[Task 8/25] Current/Best: 11.20/ 20.71 GFLOPS | Progress: (12/20) | 16.64 s
+[Task 8/25] Current/Best: 12.92/ 20.71 GFLOPS | Progress: (16/20) | 19.86 s
+[Task 8/25] Current/Best: 4.14/ 20.71 GFLOPS | Progress: (20/20) | 22.65 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 9.18/ 18.92 GFLOPS | Progress: (4/20) | 6.00 s
-[Task 9/25] Current/Best: 7.09/ 18.92 GFLOPS | Progress: (8/20) | 7.77 s
-[Task 9/25] Current/Best: 4.79/ 18.92 GFLOPS | Progress: (12/20) | 18.89 s
-[Task 9/25] Current/Best: 8.58/ 18.92 GFLOPS | Progress: (16/20) | 25.31 s
-[Task 9/25] Current/Best: 12.40/ 18.92 GFLOPS | Progress: (20/20) | 26.68 s Done.
+[Task 9/25] Current/Best: 22.53/ 22.53 GFLOPS | Progress: (4/20) | 4.80 s
+[Task 9/25] Current/Best: 12.86/ 22.53 GFLOPS | Progress: (8/20) | 6.48 s
+[Task 9/25] Current/Best: 16.12/ 22.53 GFLOPS | Progress: (12/20) | 10.27 s
+[Task 9/25] Current/Best: 14.03/ 22.53 GFLOPS | Progress: (16/20) | 13.29 s
+[Task 9/25] Current/Best: 14.10/ 22.53 GFLOPS | Progress: (20/20) | 17.00 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 11.44/ 17.30 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 10/25] Current/Best: 4.83/ 17.53 GFLOPS | Progress: (8/20) | 6.32 s
-[Task 10/25] Current/Best: 9.25/ 19.48 GFLOPS | Progress: (12/20) | 7.68 s
-[Task 10/25] Current/Best: 4.23/ 19.48 GFLOPS | Progress: (16/20) | 10.35 s
-[Task 10/25] Current/Best: 11.74/ 19.48 GFLOPS | Progress: (20/20) | 13.06 s Done.
+[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 3.60 s
+[Task 10/25] Current/Best: 12.30/ 18.22 GFLOPS | Progress: (8/20) | 4.96 s
+[Task 10/25] Current/Best: 11.81/ 20.44 GFLOPS | Progress: (12/20) | 7.80 s
+[Task 10/25] Current/Best: 13.28/ 20.44 GFLOPS | Progress: (16/20) | 10.40 s
+[Task 10/25] Current/Best: 18.40/ 20.44 GFLOPS | Progress: (20/20) | 12.83 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.35/ 14.30 GFLOPS | Progress: (4/20) | 4.27 s
-[Task 11/25] Current/Best: 12.76/ 14.30 GFLOPS | Progress: (8/20) | 6.40 s
-[Task 11/25] Current/Best: 16.03/ 20.86 GFLOPS | Progress: (12/20) | 8.36 s
-[Task 11/25] Current/Best: 11.55/ 20.86 GFLOPS | Progress: (16/20) | 10.67 s
-[Task 11/25] Current/Best: 18.32/ 20.86 GFLOPS | Progress: (20/20) | 14.10 s Done.
+[Task 11/25] Current/Best: 13.02/ 20.82 GFLOPS | Progress: (4/20) | 4.99 s
+[Task 11/25] Current/Best: 13.52/ 21.49 GFLOPS | Progress: (8/20) | 8.20 s
+[Task 11/25] Current/Best: 11.47/ 21.49 GFLOPS | Progress: (12/20) | 10.32 s
+[Task 11/25] Current/Best: 17.80/ 21.49 GFLOPS | Progress: (16/20) | 12.25 s
+[Task 11/25] Current/Best: 6.15/ 22.38 GFLOPS | Progress: (20/20) | 14.79 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 9.40/ 16.43 GFLOPS | Progress: (4/20) | 4.49 s
-[Task 12/25] Current/Best: 16.67/ 18.84 GFLOPS | Progress: (8/20) | 6.39 s
-[Task 12/25] Current/Best: 7.61/ 18.84 GFLOPS | Progress: (12/20) | 9.92 s
-[Task 12/25] Current/Best: 15.80/ 18.84 GFLOPS | Progress: (16/20) | 16.07 s
-[Task 12/25] Current/Best: 16.88/ 18.84 GFLOPS | Progress: (20/20) | 18.32 s Done.
+[Task 12/25] Current/Best: 9.13/ 13.79 GFLOPS | Progress: (4/20) | 3.64 s
+[Task 12/25] Current/Best: 17.47/ 18.18 GFLOPS | Progress: (8/20) | 5.29 s
+[Task 12/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 7.44 s
+[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (16/20) | 9.65 s
+[Task 12/25] Current/Best: 14.82/ 19.04 GFLOPS | Progress: (20/20) | 11.55 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 10.40/ 16.27 GFLOPS | Progress: (4/20) | 4.15 s
-[Task 13/25] Current/Best: 15.10/ 18.50 GFLOPS | Progress: (8/20) | 6.08 s
-[Task 13/25] Current/Best: 11.61/ 23.09 GFLOPS | Progress: (12/20) | 10.19 s
-[Task 13/25] Current/Best: 21.37/ 23.09 GFLOPS | Progress: (16/20) | 13.18 s
-[Task 13/25] Current/Best: 14.70/ 23.09 GFLOPS | Progress: (20/20) | 16.94 s Done.
+[Task 13/25] Current/Best: 10.00/ 12.99 GFLOPS | Progress: (4/20) | 4.78 s
+[Task 13/25] Current/Best: 15.11/ 16.32 GFLOPS | Progress: (8/20) | 7.61 s
+[Task 13/25] Current/Best: 11.00/ 16.32 GFLOPS | Progress: (12/20) | 12.11 s
+[Task 13/25] Current/Best: 8.41/ 18.24 GFLOPS | Progress: (16/20) | 16.97 s
+[Task 13/25] Current/Best: 13.37/ 18.24 GFLOPS | Progress: (20/20) | 20.01 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.46/ 14.58 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 14/25] Current/Best: 9.33/ 16.12 GFLOPS | Progress: (8/20) | 6.69 s
-[Task 14/25] Current/Best: 8.12/ 16.12 GFLOPS | Progress: (12/20) | 9.17 s
-[Task 14/25] Current/Best: 13.50/ 17.61 GFLOPS | Progress: (16/20) | 11.44 s
-[Task 14/25] Current/Best: 17.37/ 17.61 GFLOPS | Progress: (20/20) | 13.59 s Done.
-
+[Task 14/25] Current/Best: 10.44/ 14.69 GFLOPS | Progress: (4/20) | 4.47 s
+[Task 14/25] Current/Best: 14.24/ 14.69 GFLOPS | Progress: (8/20) | 9.95 s
+[Task 14/25] Current/Best: 12.34/ 17.20 GFLOPS | Progress: (12/20) | 12.11 s
+[Task 14/25] Current/Best: 18.32/ 18.97 GFLOPS | Progress: (16/20) | 14.80 s
+[Task 14/25] Current/Best: 3.03/ 18.97 GFLOPS | Progress: (20/20) | 17.62 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 10.30/ 22.41 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 15/25] Current/Best: 19.52/ 22.41 GFLOPS | Progress: (8/20) | 5.22 s
-[Task 15/25] Current/Best: 20.09/ 22.41 GFLOPS | Progress: (12/20) | 7.29 s
-[Task 15/25] Current/Best: 11.43/ 22.41 GFLOPS | Progress: (16/20) | 10.06 s
-[Task 15/25] Current/Best: 14.03/ 23.67 GFLOPS | Progress: (20/20) | 11.34 s
+[Task 15/25] Current/Best: 12.24/ 15.99 GFLOPS | Progress: (4/20) | 7.54 s
+[Task 15/25] Current/Best: 12.69/ 18.08 GFLOPS | Progress: (8/20) | 9.63 s
+[Task 15/25] Current/Best: 3.12/ 18.08 GFLOPS | Progress: (12/20) | 11.82 s Done.
+
+[Task 15/25] Current/Best: 13.44/ 18.08 GFLOPS | Progress: (16/20) | 14.49 s
+[Task 15/25] Current/Best: 15.82/ 18.08 GFLOPS | Progress: (20/20) | 16.39 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 16.93/ 16.93 GFLOPS | Progress: (4/20) | 3.86 s
-[Task 16/25] Current/Best: 6.49/ 16.93 GFLOPS | Progress: (8/20) | 5.86 s
-[Task 16/25] Current/Best: 16.61/ 18.21 GFLOPS | Progress: (12/20) | 7.12 s
-[Task 16/25] Current/Best: 10.45/ 18.21 GFLOPS | Progress: (16/20) | 9.70 s
-[Task 16/25] Current/Best: 18.03/ 18.21 GFLOPS | Progress: (20/20) | 11.31 s Done.
+[Task 16/25] Current/Best: 18.27/ 21.01 GFLOPS | Progress: (4/20) | 3.27 s
+[Task 16/25] Current/Best: 11.84/ 21.01 GFLOPS | Progress: (8/20) | 5.21 s
+[Task 16/25] Current/Best: 13.75/ 21.66 GFLOPS | Progress: (12/20) | 6.83 s
+[Task 16/25] Current/Best: 12.15/ 22.09 GFLOPS | Progress: (16/20) | 9.27 s
+[Task 16/25] Current/Best: 12.27/ 22.09 GFLOPS | Progress: (20/20) | 11.17 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 5.45 s
-[Task 17/25] Current/Best: 6.96/ 17.55 GFLOPS | Progress: (8/20) | 7.54 s
-[Task 17/25] Current/Best: 17.31/ 17.67 GFLOPS | Progress: (12/20) | 9.19 s
-[Task 17/25] Current/Best: 22.52/ 22.52 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 17/25] Current/Best: 18.83/ 22.52 GFLOPS | Progress: (20/20) | 14.17 s Done.
+[Task 17/25] Current/Best: 19.03/ 22.98 GFLOPS | Progress: (4/20) | 3.54 s
+[Task 17/25] Current/Best: 9.48/ 22.98 GFLOPS | Progress: (8/20) | 6.35 s
+[Task 17/25] Current/Best: 10.16/ 22.98 GFLOPS | Progress: (12/20) | 8.84 s
+[Task 17/25] Current/Best: 11.86/ 22.98 GFLOPS | Progress: (16/20) | 11.73 s
+[Task 17/25] Current/Best: 5.20/ 22.98 GFLOPS | Progress: (20/20) | 14.23 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.72/ 22.55 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 18/25] Current/Best: 13.05/ 22.55 GFLOPS | Progress: (8/20) | 5.81 s Done.
-
-[Task 18/25] Current/Best: 11.43/ 22.55 GFLOPS | Progress: (12/20) | 8.11 s
-[Task 18/25] Current/Best: 10.68/ 22.55 GFLOPS | Progress: (16/20) | 13.31 s
-[Task 18/25] Current/Best: 20.06/ 22.55 GFLOPS | Progress: (20/20) | 15.28 s Done.
+[Task 18/25] Current/Best: 14.35/ 14.35 GFLOPS | Progress: (4/20) | 3.93 s
+[Task 18/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (8/20) | 5.40 s
+[Task 18/25] Current/Best: 15.69/ 22.72 GFLOPS | Progress: (12/20) | 9.31 s
+[Task 18/25] Current/Best: 13.96/ 22.72 GFLOPS | Progress: (16/20) | 11.42 s
+[Task 18/25] Current/Best: 17.39/ 22.72 GFLOPS | Progress: (20/20) | 14.88 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 2.70/ 20.16 GFLOPS | Progress: (4/20) | 4.70 s
-[Task 19/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 19/25] Current/Best: 19.00/ 20.74 GFLOPS | Progress: (12/20) | 9.76 s
-[Task 19/25] Current/Best: 17.96/ 21.39 GFLOPS | Progress: (16/20) | 13.52 s
-[Task 19/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (20/20) | 16.30 s Done.
+[Task 19/25] Current/Best: 10.56/ 14.25 GFLOPS | Progress: (4/20) | 5.04 s
+[Task 19/25] Current/Best: 21.33/ 21.97 GFLOPS | Progress: (8/20) | 7.31 s
+[Task 19/25] Current/Best: 8.39/ 21.97 GFLOPS | Progress: (12/20) | 12.43 s
+[Task 19/25] Current/Best: 10.35/ 21.97 GFLOPS | Progress: (16/20) | 17.63 s
+[Task 19/25] Current/Best: 17.07/ 21.97 GFLOPS | Progress: (20/20) | 20.53 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (4/20) | 3.89 s
-[Task 20/25] Current/Best: 6.38/ 21.19 GFLOPS | Progress: (8/20) | 7.47 s
-[Task 20/25] Current/Best: 8.97/ 21.19 GFLOPS | Progress: (12/20) | 9.84 s
-[Task 20/25] Current/Best: 8.66/ 21.19 GFLOPS | Progress: (16/20) | 12.02 s
-[Task 20/25] Current/Best: 2.08/ 21.19 GFLOPS | Progress: (20/20) | 16.70 s
+[Task 20/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 3.32 s
+[Task 20/25] Current/Best: 11.65/ 18.84 GFLOPS | Progress: (8/20) | 6.55 s
+[Task 20/25] Current/Best: 16.43/ 18.84 GFLOPS | Progress: (12/20) | 9.11 s
+[Task 20/25] Current/Best: 8.84/ 18.84 GFLOPS | Progress: (16/20) | 12.91 s
+[Task 20/25] Current/Best: 16.06/ 18.84 GFLOPS | Progress: (20/20) | 14.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 7.44/ 9.98 GFLOPS | Progress: (4/20) | 3.02 s
-[Task 21/25] Current/Best: 14.58/ 18.87 GFLOPS | Progress: (8/20) | 5.05 s
-[Task 21/25] Current/Best: 12.51/ 18.87 GFLOPS | Progress: (12/20) | 6.32 s Done.
+[Task 21/25] Current/Best: 12.44/ 17.26 GFLOPS | Progress: (4/20) | 4.37 s
+[Task 21/25] Current/Best: 10.99/ 17.26 GFLOPS | Progress: (8/20) | 6.21 s Done.
-[Task 21/25] Current/Best: 10.76/ 20.82 GFLOPS | Progress: (16/20) | 7.98 s
-[Task 21/25] Current/Best: 17.89/ 20.82 GFLOPS | Progress: (20/20) | 10.03 s
+[Task 21/25] Current/Best: 7.57/ 17.26 GFLOPS | Progress: (12/20) | 8.48 s
+[Task 21/25] Current/Best: 17.11/ 17.26 GFLOPS | Progress: (16/20) | 11.26 s
+[Task 21/25] Current/Best: 14.08/ 17.26 GFLOPS | Progress: (20/20) | 15.30 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 10.89/ 17.00 GFLOPS | Progress: (4/20) | 2.81 s
-[Task 22/25] Current/Best: 10.19/ 20.47 GFLOPS | Progress: (8/20) | 5.58 s
-[Task 22/25] Current/Best: 17.68/ 20.47 GFLOPS | Progress: (12/20) | 6.89 s
-[Task 22/25] Current/Best: 2.70/ 22.02 GFLOPS | Progress: (16/20) | 8.62 s
-[Task 22/25] Current/Best: 6.91/ 22.02 GFLOPS | Progress: (20/20) | 10.99 s Done.
+[Task 22/25] Current/Best: 10.55/ 13.88 GFLOPS | Progress: (4/20) | 4.35 s
+[Task 22/25] Current/Best: 4.52/ 16.29 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 22/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (12/20) | 7.43 s
+[Task 22/25] Current/Best: 7.08/ 19.56 GFLOPS | Progress: (16/20) | 9.63 s
+[Task 22/25] Current/Best: 18.66/ 19.56 GFLOPS | Progress: (20/20) | 11.32 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 11.27/ 18.67 GFLOPS | Progress: (4/20) | 5.48 s
-[Task 23/25] Current/Best: 9.52/ 20.81 GFLOPS | Progress: (8/20) | 7.91 s
-[Task 23/25] Current/Best: 12.07/ 23.11 GFLOPS | Progress: (12/20) | 12.85 s
-[Task 23/25] Current/Best: 3.09/ 23.11 GFLOPS | Progress: (16/20) | 15.98 s
-[Task 23/25] Current/Best: 7.19/ 23.11 GFLOPS | Progress: (20/20) | 19.21 s Done.
+[Task 23/25] Current/Best: 4.42/ 19.23 GFLOPS | Progress: (4/20) | 3.77 s
+[Task 23/25] Current/Best: 11.96/ 20.75 GFLOPS | Progress: (8/20) | 5.70 s
+[Task 23/25] Current/Best: 17.04/ 20.75 GFLOPS | Progress: (12/20) | 8.37 s
+[Task 23/25] Current/Best: 20.41/ 20.75 GFLOPS | Progress: (16/20) | 11.13 s
+[Task 23/25] Current/Best: 18.96/ 20.75 GFLOPS | Progress: (20/20) | 16.82 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 6.31/ 6.31 GFLOPS | Progress: (4/20) | 12.20 s
-[Task 24/25] Current/Best: 6.58/ 6.58 GFLOPS | Progress: (8/20) | 17.95 s
-[Task 24/25] Current/Best: 9.53/ 9.53 GFLOPS | Progress: (12/20) | 21.79 s
-[Task 24/25] Current/Best: 6.24/ 9.53 GFLOPS | Progress: (16/20) | 32.04 s
-[Task 24/25] Current/Best: 6.62/ 9.53 GFLOPS | Progress: (20/20) | 43.81 s
+[Task 24/25] Current/Best: 1.77/ 5.76 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 24/25] Current/Best: 1.45/ 7.07 GFLOPS | Progress: (8/20) | 15.22 s
+[Task 24/25] Current/Best: 2.59/ 7.18 GFLOPS | Progress: (12/20) | 25.98 s
+[Task 24/25] Current/Best: 2.80/ 7.18 GFLOPS | Progress: (16/20) | 37.65 s
+[Task 24/25] Current/Best: 4.45/ 7.18 GFLOPS | Progress: (20/20) | 49.43 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
-[Task 25/25] Current/Best: 5.82/ 5.82 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 25/25] Current/Best: 6.81/ 6.87 GFLOPS | Progress: (8/20) | 11.45 s
-[Task 25/25] Current/Best: 3.02/ 6.87 GFLOPS | Progress: (12/20) | 13.53 s
-[Task 25/25] Current/Best: 7.43/ 8.91 GFLOPS | Progress: (16/20) | 14.90 s
-[Task 25/25] Current/Best: 8.64/ 9.94 GFLOPS | Progress: (20/20) | 18.31 s Done.
+[Task 25/25] Current/Best: 3.02/ 8.42 GFLOPS | Progress: (4/20) | 4.89 s
+[Task 25/25] Current/Best: 1.54/ 8.42 GFLOPS | Progress: (8/20) | 15.65 s
+[Task 25/25] Current/Best: 3.00/ 9.40 GFLOPS | Progress: (12/20) | 19.98 s
+[Task 25/25] Current/Best: 3.82/ 9.40 GFLOPS | Progress: (16/20) | 30.71 s
+[Task 25/25] Current/Best: 5.73/ 9.40 GFLOPS | Progress: (20/20) | 34.15 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -944,8 +945,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
+class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -982,8 +983,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 415.35988089999137, 'median': 414.94138310001745, 'std': 1.9609314523928856}
-unoptimized: {'mean': 509.48449451999295, 'median': 509.4376562999969, 'std': 2.30095285721133}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 430.0801938499967, 'median': 430.3779723499929, 'std': 2.429183228660658}
+unoptimized: {'mean': 520.1350239500016, 'median': 520.6004449500028, 'std': 1.8481651835144155}
</pre></div>
</div>
</div>
@@ -997,7 +998,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 35.977 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 43.197 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 f2af2ea41a..81dd4c37ee 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.27e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.271e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 12cec638a4..bb9e1848db 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x219c9550)), stage(b, placeholder(b, 0x265e7b60)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xe8b6070)), stage(b, placeholder(b, 0x28a726d0)), 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 008086bd26..272de94265 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:12.284</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:17.904</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,50 +349,50 @@
</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>10:35.977</p></td>
+<td><p>10:43.197</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>01:37.097</p></td>
+<td><p>01:36.969</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.845</p></td>
+<td><p>00:59.362</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>00:32.969</p></td>
+<td><p>00:34.192</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:23.820</p></td>
+<td><p>00:21.967</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.766</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:01.254</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:00.633</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.777</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>00:00.170</p></td>
+<td><p>00:00.175</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>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d9f0f5cffd..ac8039a1cd 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -552,7 +552,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000009
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -600,7 +600,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
</pre></div>
</div>
</div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 6.642809998993471e-06 1.0
- naive 8.7419e-06 1.3159942857502454
-parallel 6.0449e-06 0.9099914043779566
- vector 2.45548e-05 3.6964477387913526
+ numpy 7.441079999352951e-06 1.0
+ naive 6.696100000000001e-06 0.8998828127882337
+parallel 6.950399999999999e-06 0.9340579594097067
+ vector 2.53151e-05 3.4020733552389317
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017584
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019053
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.404196
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.256209
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.301546
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.314476
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.345962
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.115073
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119863
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108399
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110230
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110960
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110165
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145340
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146200
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4041964893999994 1.0
- blocking 0.3015460689 0.08858068852340203
- vectorization 0.3363781226 0.09881278112101212
-loop permutation 0.1150728701 0.033803239753731715
- array packing 0.1083985735 0.03184263124573799
- block caching 0.1109600669 0.032595082935285284
- parallelization 0.14534000419999998 0.042694364045248345
+ none 3.2562085157 1.0
+ blocking 0.3144764388 0.09657748798448669
+ vectorization 0.3459622566 0.10624696020906607
+loop permutation 0.1198630473 0.036810617846514834
+ array packing 0.1102295502 0.033852116554735905
+ block caching 0.11016505830000001 0.03383231072851531
+ parallelization 0.14619960810000002 0.044898724204881245
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,7 +1520,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.845 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>