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 2022/11/22 05:03:36 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@7cfa62e255409b083d07b537765726a634c449c4)
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 2b9c83b2ec deploying docs (apache/tvm@7cfa62e255409b083d07b537765726a634c449c4)
2b9c83b2ec is described below
commit 2b9c83b2ec7788ff290a31a13b0f1dd5f5339598
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Nov 22 05:03:29 2022 +0000
deploying docs (apache/tvm@7cfa62e255409b083d07b537765726a634c449c4)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 327199 -> 332190 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 22934 -> 23824 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 11 +-
.../tune_network_cuda.rst.txt | 7 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 412 +-----------
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 704 ++++++---------------
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 12 +-
.../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 | 4 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 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 | 13 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 34 +-
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 | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 8 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 3 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 412 +-----------
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 704 ++++++---------------
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 12 +-
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 | 4 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 277 ++++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
128 files changed, 1257 insertions(+), 2601 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9acba7fd3b..aaa507d64d 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index fb0f49ab60..5ff98f857f 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 9cb08188b9..2f6d1676b6 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 10.166 seconds)
+ **Total running time of the script:** ( 1 minutes 10.856 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 8d86fe4963..77f77d7e0f 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 973ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 925ms/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 4194bf1ade..42a0adabbd 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.zip6b750afc-1efa-4bcf-8409-efe2e0573a2b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4d78fb1a-458f-4d48-8f8a-1739d5c60dd8 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 9a6b0dafe3..f5ccd2af8d 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%|#8 | 7.79M/41.5M [00:00<00:00, 81.7MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 65.7MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
69%|######8 | 28.5M/41.5M [00:00<00:00, 60.8MB/s]
83%|########2 | 34.4M/41.5M [00:00<00:00, 50.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 63.2MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 54.4MB/s]
28%|##7 | 11.5M/41.5M [00:00<00:00, 52.4MB/s]
40%|###9 | 16.5M/41.5M [00:00<00:00, 51.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 52.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 62.0MB/s]
92%|#########1| 38.0M/41.5M [00:00<00:00, 61.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 51.1MB/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 096e54d425..c3c62f28c3 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]
19%|#9 | 8.53M/44.7M [00:00<00:00, 89.4MB/s]
49%|####8 | 21.7M/44.7M [00:00<00:00, 118MB/s]
74%|#######3 | 32.9M/44.7M [00:00<00:00, 99.4MB/s]
100%|#########9| 44.7M/44.7M [00:00<00:00, 108MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
28%|##8 | 12.7M/44.7M [00:00<00:00, 132MB/s]
57%|#####6 | 25.3M/44.7M [00:00<00:00, 111MB/s]
81%|######## | 36.1M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 4c55d54a50..57851d6a3f 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 12.047 seconds)
+ **Total running time of the script:** ( 1 minutes 10.392 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 9baa5cd523..d52d20b222 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
=================
-**05:43.043** total execution time for **how_to_compile_models** files:
+**05:39.658** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.047 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.856 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:10.166 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.392 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.739 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.945 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.737 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.272 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.259 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.827 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.451 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.476 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:21.845 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.246 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.504 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.386 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.397 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index d2e9084033..7f499fe1c1 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)
- 16.2368 16.1416 17.2407 15.8435 0.3782
+ 15.7418 15.6674 16.5301 15.5206 0.2778
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 8bcc49e8aa..21dc36ba04 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]
5%|4 | 7.99M/170M [00:00<00:02, 74.6MB/s]
13%|#2 | 21.8M/170M [00:00<00:01, 114MB/s]
19%|#9 | 32.8M/170M [00:00<00:01, 85.1MB/s]
27%|##7 | 46.3M/170M [00:00<00:01, 94.5MB/s]
37%|###6 | 62.3M/170M [00:00<00:01, 112MB/s]
43%|####3 | 73.5M/170M [00:00<00:00, 113MB/s]
50%|####9 | 84.7M/170M [00:00<00:00, 109MB/s]
56%|#####6 | 95.3M/170M [00:00<00:00, 106MB/s]
62%|######2 | 106M/170M [00:01<00:00, 102MB/s]
68%|######8 | 116M/170M [00:01<00:00, 103MB/s]
74%|#######4 | 126M/170M [00:01<00:00, 80.5MB/s]
85%|########5 | 145M/170M [00:01<00:00, 108MB/s]
92%|#########1| 156M/170M [00:01<00:00, 105MB/s]
98%|#########8| 167M/170M [00:01<00:00, 105MB/s]
100%|##########| 170M/170M [00:01<00:00, 102MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|7 | 11.9M/170M [00:00<00:01, 125MB/s]
14%|#4 | 23.8M/170M [00:00<00:01, 109MB/s]
20%|## | 34.4M/170M [00:00<00:01, 105MB/s]
26%|##6 | 44.4M/170M [00:00<00:01, 103MB/s]
32%|###1 | 54.3M/170M [00:00<00:01, 102MB/s]
38%|###7 | 64.1M/170M [00:00<00:01, 99.9MB/s]
43%|####3 | 73.6M/170M [00:00<00:01, 86.7MB/s]
52%|#####1 | 88.0M/170M [00:00<00:00, 104MB/s]
58%|#####7 | 98.3M/170M [00:01<00:00, 104MB/s]
64%|######3 | 108M/170M [00:01<00:00, 103MB/s]
70%|######9 | 118M/170M [00:01<00:00, 102MB/s]
76%|#######5 | 128M/170M [00:01<00:00, 101MB/s]
81%|########1 | 138M/170M [00:01<00:00, 95.2MB/s]
88%|########8 | 150M/170M [00:01<00:00, 103MB/s]
94%|#########3| 160M/170M [00:01<00:00, 102MB/s]
100%|#########9| 169M/170M [00:01<00:00, 99.9MB/s]
100%|##########| 170M/170M [00:01<00:00, 101MB/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 15.476 seconds)
+ **Total running time of the script:** ( 3 minutes 10.448 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 a097b1a21a..2f37eea101 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]
70%|####### | 9.53M/13.6M [00:00<00:00, 99.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 91.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
90%|########9 | 12.2M/13.6M [00:00<00:00, 90.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 96.4MB/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)
- 90.2577 90.1606 93.6899 90.0567 0.3853
+ 90.7002 90.6094 92.3397 90.3056 0.3502
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.518 seconds)
+ **Total running time of the script:** ( 1 minutes 4.883 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 d5390b9963..884f6251b9 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)
- 121.2431 121.1623 127.4660 119.8259 0.8353
+ 119.3615 119.2206 121.4561 118.0381 0.6789
@@ -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 28.050 seconds)
+ **Total running time of the script:** ( 2 minutes 28.380 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 4ae809b2b4..c42a6018ed 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 22.565 seconds)
+ **Total running time of the script:** ( 1 minutes 27.523 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 39bae1d3d7..64b68ae767 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]
1%| | 989/132723 [00:00<00:13, 9888.29KB/s]
3%|2 | 3888/132723 [00:00<00:06, 21123.09KB/s]
7%|6 | 9047/132723 [00:00<00:03, 35032.89KB/s]
13%|#3 | 17320/132723 [00:00<00:02, 53860.32KB/s]
19%|#9 | 25763/132723 [00:00<00:01, 64879.73KB/s]
26%|##5 | 34195/132723 [00:00<00:01, 71484.05KB/s]
32%|###2 | 42694/132723 [00:00<00:01, 75897.52KB/s]
39%|###8 | 51165/132723 [00:00<00:01, 78700.65KB/s]
45%|####4 | 59722/132723 [00:00<00:00, 80845.81KB/s]
51%|#####1 | 68227/132723 [00:01<00:00, 82137.56KB/s]
58%|#####7 | 76753/132723 [00:01<00:00, 83091.48KB/s]
64%|######4 | 85267/132723 [00:01<00:00, 83711.23KB/s]
71%|####### | 93830/132723 [00:01<00:00, 84290.46KB/s]
77%|#######7 | 102377/132723 [00:01<00:00, 84642.47KB/s]
84%|########3 | 110923/132723 [00:01<00:00, 84886.16KB/s]
90%|########9 | 1
19443/132723 [00:01<00:00, 84978.99KB/s]
96%|#########6| 127944/132723 [00:01<00:00, 84984.99KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75497.61KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5927/132723 [00:00<00:02, 59261.16KB/s]
10%|9 | 13157/132723 [00:00<00:01, 66910.83KB/s]
15%|#4 | 19848/132723 [00:00<00:02, 46435.05KB/s]
21%|## | 27435/132723 [00:00<00:01, 55602.91KB/s]
26%|##6 | 35069/132723 [00:00<00:01, 61988.32KB/s]
32%|###2 | 42665/132723 [00:00<00:01, 66254.47KB/s]
38%|###8 | 50526/132723 [00:00<00:01, 70006.50KB/s]
44%|####4 | 58437/132723 [00:00<00:01, 72755.47KB/s]
50%|####9 | 66321/132723 [00:00<00:00, 74590.20KB/s]
56%|#####5 | 74197/132723 [00:01<00:00, 75836.35KB/s]
62%|######1 | 82073/132723 [00:01<00:00, 76713.54KB/s]
68%|######7 | 90041/132723 [00:01<00:00, 77602.29KB/s]
74%|#######3 | 98013/132723 [00:01<00:00, 78234.41KB/s]
80%|#######9 | 105973/132723 [00:01<00:00, 78640.10KB/s]
86%|########5 | 113916/132723 [00:01<00:00, 78874.47KB/s]
92%|#########
1| 121831/132723 [00:01<00:00, 78954.48KB/s]
98%|#########7| 129765/132723 [00:01<00:00, 79063.85KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72363.74KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 1.538 seconds)
+ **Total running time of the script:** ( 2 minutes 58.266 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 84176d08e8..f910d174bd 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**12:41.659** total execution time for **how_to_deploy_models** files:
+**12:34.747** 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``) | 03:15.476 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:10.448 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:01.538 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:58.266 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.380 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:22.565 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:27.523 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.518 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:04.883 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.494 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.137 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.723 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.369 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.289 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.734 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 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 a571d95c8f..dd87185627 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.zip7655373e-66f5-49e7-ab2b-a4d074a21974 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip82c06671-e7b4-43d1-bd3e-1a651918a60e 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 c59c17cb73..2dcb945cad 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
=================
-**00:47.923** total execution time for **how_to_extend_tvm** files:
+**00:46.395** 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``) | 00:44.417 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.032 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.352 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.004 | 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 a74b65ec54..2968ae4b5e 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: 7185us [7185us] (46.20%; 46.20%)
- FoldScaleAxis: 8366us [6us] (53.80%; 53.80%)
- FoldConstant: 8360us [1739us] (53.76%; 99.93%)
- InferType: 6621us [6621us] (42.58%; 79.20%)
+ InferType: 7922us [7922us] (48.97%; 48.97%)
+ FoldScaleAxis: 8255us [7us] (51.03%; 51.03%)
+ FoldConstant: 8248us [1714us] (50.99%; 99.92%)
+ InferType: 6534us [6534us] (40.39%; 79.22%)
@@ -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: 6635us [6635us] (44.88%; 44.88%)
- FoldScaleAxis: 8148us [4us] (55.12%; 55.12%)
- FoldConstant: 8143us [1691us] (55.09%; 99.95%)
- InferType: 6452us [6452us] (43.65%; 79.23%)
+ InferType: 6511us [6511us] (45.08%; 45.08%)
+ FoldScaleAxis: 7931us [4us] (54.92%; 54.92%)
+ FoldConstant: 7927us [1651us] (54.89%; 99.95%)
+ InferType: 6276us [6276us] (43.46%; 79.17%)
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 400681b777..96b4d9a2a1 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: 33.681217 ms
+ Convolution: 54.108318 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 939cf7b270..5cb1f4ed39 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: 11.884211 ms
+ conv2d with tensor core: 11.290620 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 41ef848da8..55d78a0e30 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: 0.019378
- Baseline: 3.254845
+ Numpy running time: 0.018161
+ Baseline: 3.438465
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.312445
+ Opt1: 0.294571
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.342553
+ Opt2: 0.328327
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117296
+ Opt3: 0.120637
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109728
+ Opt4: 0.109178
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111531
+ Opt5: 0.111052
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146557
+ Opt6: 0.146533
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 1203457612..ab87e688db 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.641** total execution time for **how_to_optimize_operators** files:
+**00:34.761** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.145 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.254 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.439 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.435 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.072 | 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 b9c9054b4a..61fff5415c 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
=================
-**08:57.679** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:11.146** 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``) | 05:31.333 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:50.059 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.063 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.953 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.134 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:59.922 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:29.653 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.599 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.778 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.431 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.836 | 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 136063a2f0..f9b6b2356d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -206,6 +206,13 @@ file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ .T
+ .T
+
@@ -770,7 +777,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.357 ms
+ Execution time of this operator: 0.355 ms
@@ -1377,7 +1384,7 @@ 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 31.333 seconds)
+ **Total running time of the script:** ( 5 minutes 50.059 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 c271ff3d36..3388c3f9c3 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)
- 7.8658 7.8691 7.8719 7.8564 0.0068
+ 7.8499 7.8405 7.8706 7.8385 0.0147
@@ -669,11 +669,6 @@ Other Tips
with :any:`auto_scheduler.RPCRunner`.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.134 seconds)
-
-
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
.. only:: html
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 81451534eb..a9c78145f0 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)
- 763.6102 762.2447 766.9282 761.6576 2.3584
+ 757.9457 759.6920 760.8923 753.2529 3.3543
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.063 seconds)
+ **Total running time of the script:** ( 1 minutes 30.953 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 0444867a25..05ebac5b6a 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
@@ -388,406 +388,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
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.i1.outer.fused: int32, 0, 32) "parallel" {
allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_2] = 0f32
- compute_4[(cse_var_2 + 1)] = 0f32
- compute_4[(cse_var_2 + 2)] = 0f32
- compute_4[(cse_var_2 + 3)] = 0f32
- compute_4[(cse_var_2 + 4)] = 0f32
- compute_4[(cse_var_2 + 5)] = 0f32
- compute_4[(cse_var_2 + 6)] = 0f32
- compute_4[(cse_var_2 + 7)] = 0f32
- compute_4[(cse_var_2 + 8)] = 0f32
- compute_4[(cse_var_2 + 9)] = 0f32
- compute_4[(cse_var_2 + 10)] = 0f32
- compute_4[(cse_var_2 + 11)] = 0f32
- compute_4[(cse_var_2 + 12)] = 0f32
- compute_4[(cse_var_2 + 13)] = 0f32
- compute_4[(cse_var_2 + 14)] = 0f32
- compute_4[(cse_var_2 + 15)] = 0f32
- compute_4[(cse_var_2 + 32)] = 0f32
- compute_4[(cse_var_2 + 33)] = 0f32
- compute_4[(cse_var_2 + 34)] = 0f32
- compute_4[(cse_var_2 + 35)] = 0f32
- compute_4[(cse_var_2 + 36)] = 0f32
- compute_4[(cse_var_2 + 37)] = 0f32
- compute_4[(cse_var_2 + 38)] = 0f32
- compute_4[(cse_var_2 + 39)] = 0f32
- compute_4[(cse_var_2 + 40)] = 0f32
- compute_4[(cse_var_2 + 41)] = 0f32
- compute_4[(cse_var_2 + 42)] = 0f32
- compute_4[(cse_var_2 + 43)] = 0f32
- compute_4[(cse_var_2 + 44)] = 0f32
- compute_4[(cse_var_2 + 45)] = 0f32
- compute_4[(cse_var_2 + 46)] = 0f32
- compute_4[(cse_var_2 + 47)] = 0f32
- compute_4[(cse_var_2 + 64)] = 0f32
- compute_4[(cse_var_2 + 65)] = 0f32
- compute_4[(cse_var_2 + 66)] = 0f32
- compute_4[(cse_var_2 + 67)] = 0f32
- compute_4[(cse_var_2 + 68)] = 0f32
- compute_4[(cse_var_2 + 69)] = 0f32
- compute_4[(cse_var_2 + 70)] = 0f32
- compute_4[(cse_var_2 + 71)] = 0f32
- compute_4[(cse_var_2 + 72)] = 0f32
- compute_4[(cse_var_2 + 73)] = 0f32
- compute_4[(cse_var_2 + 74)] = 0f32
- compute_4[(cse_var_2 + 75)] = 0f32
- compute_4[(cse_var_2 + 76)] = 0f32
- compute_4[(cse_var_2 + 77)] = 0f32
- compute_4[(cse_var_2 + 78)] = 0f32
- compute_4[(cse_var_2 + 79)] = 0f32
- compute_4[(cse_var_2 + 96)] = 0f32
- compute_4[(cse_var_2 + 97)] = 0f32
- compute_4[(cse_var_2 + 98)] = 0f32
- compute_4[(cse_var_2 + 99)] = 0f32
- compute_4[(cse_var_2 + 100)] = 0f32
- compute_4[(cse_var_2 + 101)] = 0f32
- compute_4[(cse_var_2 + 102)] = 0f32
- compute_4[(cse_var_2 + 103)] = 0f32
- compute_4[(cse_var_2 + 104)] = 0f32
- compute_4[(cse_var_2 + 105)] = 0f32
- compute_4[(cse_var_2 + 106)] = 0f32
- compute_4[(cse_var_2 + 107)] = 0f32
- compute_4[(cse_var_2 + 108)] = 0f32
- compute_4[(cse_var_2 + 109)] = 0f32
- compute_4[(cse_var_2 + 110)] = 0f32
- compute_4[(cse_var_2 + 111)] = 0f32
- compute_4[(cse_var_2 + 128)] = 0f32
- compute_4[(cse_var_2 + 129)] = 0f32
- compute_4[(cse_var_2 + 130)] = 0f32
- compute_4[(cse_var_2 + 131)] = 0f32
- compute_4[(cse_var_2 + 132)] = 0f32
- compute_4[(cse_var_2 + 133)] = 0f32
- compute_4[(cse_var_2 + 134)] = 0f32
- compute_4[(cse_var_2 + 135)] = 0f32
- compute_4[(cse_var_2 + 136)] = 0f32
- compute_4[(cse_var_2 + 137)] = 0f32
- compute_4[(cse_var_2 + 138)] = 0f32
- compute_4[(cse_var_2 + 139)] = 0f32
- compute_4[(cse_var_2 + 140)] = 0f32
- compute_4[(cse_var_2 + 141)] = 0f32
- compute_4[(cse_var_2 + 142)] = 0f32
- compute_4[(cse_var_2 + 143)] = 0f32
- compute_4[(cse_var_2 + 160)] = 0f32
- compute_4[(cse_var_2 + 161)] = 0f32
- compute_4[(cse_var_2 + 162)] = 0f32
- compute_4[(cse_var_2 + 163)] = 0f32
- compute_4[(cse_var_2 + 164)] = 0f32
- compute_4[(cse_var_2 + 165)] = 0f32
- compute_4[(cse_var_2 + 166)] = 0f32
- compute_4[(cse_var_2 + 167)] = 0f32
- compute_4[(cse_var_2 + 168)] = 0f32
- compute_4[(cse_var_2 + 169)] = 0f32
- compute_4[(cse_var_2 + 170)] = 0f32
- compute_4[(cse_var_2 + 171)] = 0f32
- compute_4[(cse_var_2 + 172)] = 0f32
- compute_4[(cse_var_2 + 173)] = 0f32
- compute_4[(cse_var_2 + 174)] = 0f32
- compute_4[(cse_var_2 + 175)] = 0f32
- compute_4[(cse_var_2 + 192)] = 0f32
- compute_4[(cse_var_2 + 193)] = 0f32
- compute_4[(cse_var_2 + 194)] = 0f32
- compute_4[(cse_var_2 + 195)] = 0f32
- compute_4[(cse_var_2 + 196)] = 0f32
- compute_4[(cse_var_2 + 197)] = 0f32
- compute_4[(cse_var_2 + 198)] = 0f32
- compute_4[(cse_var_2 + 199)] = 0f32
- compute_4[(cse_var_2 + 200)] = 0f32
- compute_4[(cse_var_2 + 201)] = 0f32
- compute_4[(cse_var_2 + 202)] = 0f32
- compute_4[(cse_var_2 + 203)] = 0f32
- compute_4[(cse_var_2 + 204)] = 0f32
- compute_4[(cse_var_2 + 205)] = 0f32
- compute_4[(cse_var_2 + 206)] = 0f32
- compute_4[(cse_var_2 + 207)] = 0f32
- compute_4[(cse_var_2 + 224)] = 0f32
- compute_4[(cse_var_2 + 225)] = 0f32
- compute_4[(cse_var_2 + 226)] = 0f32
- compute_4[(cse_var_2 + 227)] = 0f32
- compute_4[(cse_var_2 + 228)] = 0f32
- compute_4[(cse_var_2 + 229)] = 0f32
- compute_4[(cse_var_2 + 230)] = 0f32
- compute_4[(cse_var_2 + 231)] = 0f32
- compute_4[(cse_var_2 + 232)] = 0f32
- compute_4[(cse_var_2 + 233)] = 0f32
- compute_4[(cse_var_2 + 234)] = 0f32
- compute_4[(cse_var_2 + 235)] = 0f32
- compute_4[(cse_var_2 + 236)] = 0f32
- compute_4[(cse_var_2 + 237)] = 0f32
- compute_4[(cse_var_2 + 238)] = 0f32
- compute_4[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- let cse_var_131: int32 = (elem_idx*16)
- let cse_var_130: int32 = (cse_var_2 + 99)
- let cse_var_129: int32 = (cse_var_2 + 98)
- let cse_var_128: int32 = (cse_var_2 + 97)
- let cse_var_127: int32 = (cse_var_2 + 96)
- let cse_var_126: int32 = (cse_var_2 + 9)
- let cse_var_125: int32 = (cse_var_2 + 8)
- let cse_var_124: int32 = (cse_var_2 + 79)
- let cse_var_123: int32 = (cse_var_2 + 78)
- let cse_var_122: int32 = (cse_var_2 + 77)
- let cse_var_121: int32 = (cse_var_2 + 76)
- let cse_var_120: int32 = (cse_var_2 + 75)
- let cse_var_119: int32 = (cse_var_2 + 74)
- let cse_var_118: int32 = (cse_var_2 + 73)
- let cse_var_117: int32 = (cse_var_2 + 72)
- let cse_var_116: int32 = (cse_var_2 + 71)
- let cse_var_115: int32 = (cse_var_2 + 70)
- let cse_var_114: int32 = (cse_var_2 + 7)
- let cse_var_113: int32 = (cse_var_2 + 69)
- let cse_var_112: int32 = (cse_var_2 + 68)
- let cse_var_111: int32 = (cse_var_2 + 67)
- let cse_var_110: int32 = (cse_var_2 + 66)
- let cse_var_109: int32 = (cse_var_2 + 65)
- let cse_var_108: int32 = (cse_var_2 + 64)
- let cse_var_107: int32 = (cse_var_2 + 6)
- let cse_var_106: int32 = (cse_var_2 + 5)
- let cse_var_105: int32 = (cse_var_2 + 47)
- let cse_var_104: int32 = (cse_var_2 + 46)
- let cse_var_103: int32 = (cse_var_2 + 45)
- let cse_var_102: int32 = (cse_var_2 + 44)
- let cse_var_101: int32 = (cse_var_2 + 43)
- let cse_var_100: int32 = (cse_var_2 + 42)
- let cse_var_99: int32 = (cse_var_2 + 41)
- let cse_var_98: int32 = (cse_var_2 + 40)
- let cse_var_97: int32 = (cse_var_2 + 4)
- let cse_var_96: int32 = (cse_var_2 + 39)
- let cse_var_95: int32 = (cse_var_2 + 38)
- let cse_var_94: int32 = (cse_var_2 + 37)
- let cse_var_93: int32 = (cse_var_2 + 36)
- let cse_var_92: int32 = (cse_var_2 + 35)
- let cse_var_91: int32 = (cse_var_2 + 34)
- let cse_var_90: int32 = (cse_var_2 + 33)
- let cse_var_89: int32 = (cse_var_2 + 32)
- let cse_var_88: int32 = (cse_var_2 + 3)
- let cse_var_87: int32 = (cse_var_2 + 239)
- let cse_var_86: int32 = (cse_var_2 + 238)
- let cse_var_85: int32 = (cse_var_2 + 237)
- let cse_var_84: int32 = (cse_var_2 + 236)
- let cse_var_83: int32 = (cse_var_2 + 235)
- let cse_var_82: int32 = (cse_var_2 + 234)
- let cse_var_81: int32 = (cse_var_2 + 233)
- let cse_var_80: int32 = (cse_var_2 + 232)
- let cse_var_79: int32 = (cse_var_2 + 231)
- let cse_var_78: int32 = (cse_var_2 + 230)
- let cse_var_77: int32 = (cse_var_2 + 229)
- let cse_var_76: int32 = (cse_var_2 + 228)
- let cse_var_75: int32 = (cse_var_2 + 227)
- let cse_var_74: int32 = (cse_var_2 + 226)
- let cse_var_73: int32 = (cse_var_2 + 225)
- let cse_var_72: int32 = (cse_var_2 + 224)
- let cse_var_71: int32 = (cse_var_2 + 207)
- let cse_var_70: int32 = (cse_var_2 + 206)
- let cse_var_69: int32 = (cse_var_2 + 205)
- let cse_var_68: int32 = (cse_var_2 + 204)
- let cse_var_67: int32 = (cse_var_2 + 203)
- let cse_var_66: int32 = (cse_var_2 + 202)
- let cse_var_65: int32 = (cse_var_2 + 201)
- let cse_var_64: int32 = (cse_var_2 + 200)
- let cse_var_63: int32 = (cse_var_2 + 2)
- let cse_var_62: int32 = (cse_var_2 + 199)
- let cse_var_61: int32 = (cse_var_2 + 198)
- let cse_var_60: int32 = (cse_var_2 + 197)
- let cse_var_59: int32 = (cse_var_2 + 196)
- let cse_var_58: int32 = (cse_var_2 + 195)
- let cse_var_57: int32 = (cse_var_2 + 194)
- let cse_var_56: int32 = (cse_var_2 + 193)
- let cse_var_55: int32 = (cse_var_2 + 192)
- let cse_var_54: int32 = (cse_var_2 + 175)
- let cse_var_53: int32 = (cse_var_2 + 174)
- let cse_var_52: int32 = (cse_var_2 + 173)
- let cse_var_51: int32 = (cse_var_2 + 172)
- let cse_var_50: int32 = (cse_var_2 + 171)
- let cse_var_49: int32 = (cse_var_2 + 170)
- let cse_var_48: int32 = (cse_var_2 + 169)
- let cse_var_47: int32 = (cse_var_2 + 168)
- let cse_var_46: int32 = (cse_var_2 + 167)
- let cse_var_45: int32 = (cse_var_2 + 166)
- let cse_var_44: int32 = (cse_var_2 + 165)
- let cse_var_43: int32 = (cse_var_2 + 164)
- let cse_var_42: int32 = (cse_var_2 + 163)
- let cse_var_41: int32 = (cse_var_2 + 162)
- let cse_var_40: int32 = (cse_var_2 + 161)
- let cse_var_39: int32 = (cse_var_2 + 160)
- let cse_var_38: int32 = (cse_var_2 + 15)
- let cse_var_37: int32 = (cse_var_2 + 143)
- let cse_var_36: int32 = (cse_var_2 + 142)
- let cse_var_35: int32 = (cse_var_2 + 141)
- let cse_var_34: int32 = (cse_var_2 + 140)
- let cse_var_33: int32 = (cse_var_2 + 14)
- let cse_var_32: int32 = (cse_var_2 + 139)
- let cse_var_31: int32 = (cse_var_2 + 138)
- let cse_var_30: int32 = (cse_var_2 + 137)
- let cse_var_29: int32 = (cse_var_2 + 136)
- let cse_var_28: int32 = (cse_var_2 + 135)
- let cse_var_27: int32 = (cse_var_2 + 134)
- let cse_var_26: int32 = (cse_var_2 + 133)
- let cse_var_25: int32 = (cse_var_2 + 132)
- let cse_var_24: int32 = (cse_var_2 + 131)
- let cse_var_23: int32 = (cse_var_2 + 130)
- let cse_var_22: int32 = (cse_var_2 + 13)
- let cse_var_21: int32 = (cse_var_2 + 129)
- let cse_var_20: int32 = (cse_var_2 + 128)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048))
- {
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ for (i.outer.inner: int32, 0, 64) {
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*512) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_132, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -843,7 +463,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.742 ms
+ Execution time of this operator: 2.251 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 57741335e9..7db6628c08 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:27.982** total execution time for **how_to_tune_with_autotvm** files:
+**00:58.300** 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``) | 00:27.947 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:58.265 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index efb974c4c1..9bb4048b49 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, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5088019
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4256317
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)
@@ -510,9 +510,9 @@ 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, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1002025
- No: 3 GFLOPS: 210.89/210.89 result: MeasureResult(costs=(0.0010977583070175439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1155447959899902, timestamp=1669070470.1798065) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9009485
- No: 4 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9207409
+ No: 3 GFLOPS: 93.49/93.49 result: MeasureResult(costs=(0.0024761461886792457,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6428587436676025, timestamp=1669088249.5815248) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6016228
+ No: 4 GFLOPS: 0.00/93.49 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
@@ -634,9 +634,8 @@ 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, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8004212
- No: 5 GFLOPS: 5.40/210.89 result: MeasureResult(costs=(0.0429052085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1623175144195557, timestamp=1669070474.4587286) [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2914259
- No: 6 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8073709
+ No: 5 GFLOPS: 0.00/93.49 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
@@ -758,9 +757,8 @@ 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, 2, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4973955
- No: 7 GFLOPS: 64.79/210.89 result: MeasureResult(costs=(0.0035728547142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2142045497894287, timestamp=1669070476.026077) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619975
- No: 8 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2350035
+ No: 6 GFLOPS: 0.00/93.49 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
@@ -882,8 +880,8 @@ 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, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1254493
- No: 9 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7882644
+ No: 7 GFLOPS: 0.00/93.49 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
@@ -1005,8 +1003,9 @@ 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, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9845277
- No: 10 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5734517
+ No: 8 GFLOPS: 79.99/93.49 result: MeasureResult(costs=(0.0028942559736842106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.43855619430542, timestamp=1669088253.059729) [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,101361
+ No: 9 GFLOPS: 0.00/93.49 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
@@ -1128,8 +1127,11 @@ 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, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3985151
- No: 11 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ 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, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4635232
+ No: 10 GFLOPS: 0.83/93.49 result: MeasureResult(costs=(0.27840701274999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.333498001098633, timestamp=1669088261.5922532) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10272645
+ No: 11 GFLOPS: 193.58/193.58 result: MeasureResult(costs=(0.0011958714925373135,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.493093967437744, timestamp=1669088262.811639) [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8078868
+ No: 12 GFLOPS: 174.00/193.58 result: MeasureResult(costs=(0.0013304507603305786,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.409214973449707, timestamp=1669088263.7386754) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9684064
+ No: 13 GFLOPS: 0.00/193.58 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
@@ -1251,500 +1253,198 @@ 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, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10209975
- No: 12 GFLOPS: 0.00/210.89 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, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6657683
- No: 13 GFLOPS: 0.00/210.89 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, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2118363
- No: 14 GFLOPS: 0.00/210.89 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)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3613442
+ No: 14 GFLOPS: 5.32/193.58 result: MeasureResult(costs=(0.04352962475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8917021751403809, timestamp=1669088274.8652062) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5302204
+ No: 15 GFLOPS: 0.00/193.58 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: 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
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+ During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 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, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1917007
- No: 15 GFLOPS: 0.00/210.89 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
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f4eb71f9fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h: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
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+ TVMError:
+ ---------------------------------------------------------------
+ An error occurred during the execution of TVM.
+ For more information, please see: https://tvm.apache.org/docs/errors.html
+ ---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
Traceback (most recent call last):
- 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, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8925918
- No: 16 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1166849
+ No: 16 GFLOPS: 0.00/193.58 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, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9139038
+ No: 17 GFLOPS: 0.00/193.58 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, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9274321
+ No: 18 GFLOPS: 0.00/193.58 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
@@ -1866,9 +1566,8 @@ 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4734059
- No: 17 GFLOPS: 306.99/306.99 result: MeasureResult(costs=(0.0007540923517241379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.548452138900757, timestamp=1669070479.167015) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
- No: 18 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3768184
+ No: 19 GFLOPS: 0.00/193.58 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
@@ -1990,8 +1689,8 @@ 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, 128, 2, 1]), ('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, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1952737
- No: 19 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2213250
+ No: 20 GFLOPS: 0.00/193.58 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
@@ -2113,8 +1812,7 @@ 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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934185
- No: 20 GFLOPS: 39.90/306.99 result: MeasureResult(costs=(0.005802182888888888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9944984912872314, timestamp=1669070479.8508644) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422558
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9758688
@@ -2169,9 +1867,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
+ [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8078868
Finish loading 20 records
- Time cost of this operator: 0.001050
+ Time cost of this operator: 0.001583
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 75c32cc8d2..5af13b9f5e 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 313.2 98.621 (1, 2, 10, 10, 3) 2 1 [313.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.235 1.019 (1, 6, 10, 10) 1 1 [3.235]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.145 0.361 (1, 1, 10, 10, 3) 1 1 [1.145]
- Total_time - 317.58 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.9 98.729 (1, 2, 10, 10, 3) 2 1 [312.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.953 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 0.318 (1, 1, 10, 10, 3) 1 1 [1.008]
+ Total_time - 316.929 - - - - -
@@ -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 136.6 98.123 (1, 6, 10, 10, 1) 2 1 [136.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.273 (1, 6, 10, 10) 1 1 [1.772]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.605 (1, 3, 10, 10, 1) 1 1 [0.842]
- Total_time - 139.213 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.299 (1, 6, 10, 10, 1) 2 1 [102.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.785 1.691 (1, 6, 10, 10) 1 1 [1.785]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.066 1.01 (1, 3, 10, 10, 1) 1 1 [1.066]
+ Total_time - 105.551 - - - - -
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 a76746a182..43d06f16af 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]
96%|#########5| 3.28M/3.42M [00:00<00:00, 34.2MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 35.0MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 85.3MB/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 2.963 seconds)
+ **Total running time of the script:** ( 1 minutes 2.488 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 88cb8c7e86..04741aeccb 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/tmp59_o2aft/images/random'
+ '/tmp/tmpwmbvasan/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [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]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp59_o2aft/images/target contains 8144 images
- /tmp/tmp59_o2aft/images/random contains 5000 images
+ /tmp/tmpwmbvasan/images/target contains 8144 images
+ /tmp/tmpwmbvasan/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2390 - accuracy: 0.9168 - val_loss: 0.1144 - val_accuracy: 0.9603 - 46s/epoch - 142ms/step
+ 328/328 - 46s - loss: 0.2424 - accuracy: 0.9183 - val_loss: 0.1623 - val_accuracy: 0.9460 - 46s/epoch - 141ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1015 - accuracy: 0.9616 - val_loss: 0.0897 - val_accuracy: 0.9683 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0983 - accuracy: 0.9614 - val_loss: 0.1244 - val_accuracy: 0.9585 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0620 - accuracy: 0.9769 - val_loss: 0.1089 - val_accuracy: 0.9641 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0622 - accuracy: 0.9771 - val_loss: 0.1664 - val_accuracy: 0.9498 - 43s/epoch - 130ms/step
- <keras.callbacks.History object at 0x7ff34e46da90>
+ <keras.callbacks.History object at 0x7fb28649bed0>
@@ -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 4.174 seconds)
+ **Total running time of the script:** ( 4 minutes 19.910 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 06b40d1232..77f43becdd 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
=================
-**06:09.111** total execution time for **how_to_work_with_microtvm** files:
+**06:24.133** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:04.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:19.910 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.963 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.488 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.628 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.386 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.719 | 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 31a27b19ae..9d7c06b35a 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.665** total execution time for **how_to_work_with_relay** files:
+**00:43.291** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.924 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.757 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.115 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.009 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.619 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.518 | 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 cc6f4dd22f..de34f52673 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 0x7ff34cf0cef0>
+ <function my_cuda_math_rule at 0x7fb1036e9440>
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 7fedb8483d..fbbaa2fdda 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
@@ -5,18 +5,18 @@
Computation times
=================
-**00:06.967** total execution time for **how_to_work_with_schedules** files:
+**00:07.467** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.087 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.067 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.568 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.564 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.549 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.541 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.048 | 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 6d367aa1f5..d37c621c8d 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/tmp7gcvbn52/input0.cc'\nsource_filename = \"/tmp/tmp7gcvbn52/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/tmpu1k46lw3/input0.cc'\nsource_filename = \"/tmp/tmpu1k46lw3/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 6833ff79e3..93eae42d6f 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
=================
-**00:26.497** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:26.063** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.490 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.057 | 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 f4607b096e..995f3716b9 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 29.30s!
+ resnet18_v1 inference graph built in 28.51s!
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 1a1a13138e..667ea61fe5 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 19.73s!
+ yolov3-tiny inference graph built in 19.10s!
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 db5a0f788f..4365cf34ef 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
=================
-**01:40.137** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.278** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.095 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.042 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.247 | 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 9ecd5c5cc0..ad3c891dc2 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
=================
-**00:03.128** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.093** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.689 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.658 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.438 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.435 | 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 13cc883c33..95ea2c1101 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
=================
-**00:00.757** total execution time for **topic_vta_tutorials** files:
+**00:00.776** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.418 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.358 | 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 56a646ceb6..aef810d809 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
- .T
+ *E
@@ -332,7 +332,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.093 ms
+ Execution time of this operator: 93.943 ms
@@ -450,7 +450,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.730 seconds)
+ **Total running time of the script:** ( 1 minutes 31.220 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 d75c67a003..ba92b8dbf7 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: 11.69/11.69 result: MeasureResult(costs=(0.0229614498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.550915002822876, timestamp=1669069093.9232368) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
- No: 2 GFLOPS: 0.50/11.69 result: MeasureResult(costs=(0.5346515846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.731043100357056, timestamp=1669069102.682373) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
- No: 3 GFLOPS: 1.55/11.69 result: MeasureResult(costs=(0.1727075166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9166369438171387, timestamp=1669069106.362152) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
- No: 4 GFLOPS: 8.24/11.69 result: MeasureResult(costs=(0.032565906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.653590202331543, timestamp=1669069107.798683) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
- No: 5 GFLOPS: 1.69/11.69 result: MeasureResult(costs=(0.1589572562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.681199312210083, timestamp=1669069110.6333787) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
- No: 6 GFLOPS: 12.19/12.19 result: MeasureResult(costs=(0.022028911800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5019567012786865, timestamp=1669069111.910717) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 7 GFLOPS: 13.38/13.38 result: MeasureResult(costs=(0.020057455600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4962158203125, timestamp=1669069112.4011486) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
- No: 8 GFLOPS: 12.85/13.38 result: MeasureResult(costs=(0.020884536399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5327770709991455, timestamp=1669069112.9469588) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
- No: 9 GFLOPS: 0.50/13.38 result: MeasureResult(costs=(0.5390465264000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.724902391433716, timestamp=1669069121.7890291) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 10 GFLOPS: 3.21/13.38 result: MeasureResult(costs=(0.08349640439999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4820079803466797, timestamp=1669069123.291861) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+ No: 1 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226330332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6061704158782959, timestamp=1669086902.1382785) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 2 GFLOPS: 3.93/11.86 result: MeasureResult(costs=(0.06823413739999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.27858567237854, timestamp=1669086904.1286464) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 3 GFLOPS: 2.00/11.86 result: MeasureResult(costs=(0.1340270294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.291276693344116, timestamp=1669086906.439967) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+ No: 4 GFLOPS: 11.39/11.86 result: MeasureResult(costs=(0.0235759818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5234189033508301, timestamp=1669086907.7067509) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+ No: 5 GFLOPS: 1.22/11.86 result: MeasureResult(costs=(0.2193744502,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.64174222946167, timestamp=1669086911.6997578) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+ No: 6 GFLOPS: 8.66/11.86 result: MeasureResult(costs=(0.0309889144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8616781234741211, timestamp=1669086913.1001549) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+ No: 7 GFLOPS: 11.94/11.94 result: MeasureResult(costs=(0.022490805,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4999420642852783, timestamp=1669086913.6278863) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 8 GFLOPS: 3.17/11.94 result: MeasureResult(costs=(0.084648184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5348148345947266, timestamp=1669086915.1869886) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+ No: 9 GFLOPS: 10.60/11.94 result: MeasureResult(costs=(0.0253301342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5456850528717041, timestamp=1669086915.9072635) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+ No: 10 GFLOPS: 9.07/11.94 result: MeasureResult(costs=(0.029611005999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6649487018585205, timestamp=1669086916.5419445) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 9be6a17e2c..0fe400daec 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': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
+ {'mean': 514.0096369799994, 'median': 513.533555500004, 'std': 2.507549372894095}
@@ -554,31 +554,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.02/ 18.79 GFLOPS | Progress: (4/20) | 6.98 s
[Task 1/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (8/20) | 11.43 s
[Task 1/25] Current/Best: 9.25/ 23.48 GFLOPS | Progress: (12/20) | 13.62 s
[Task 1/25] Current/Best: 17.21/ 23.48 GFLOPS | Progress: (16/20) | 16.07 s
[Task 1/25] Current/Best: 15.13/ 23.48 GFLOPS | Progress: (20/20) | 19.10 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.20/ 17.44 GFLOPS | Progress: (4/20) | 3.34 s
[Task 2/25] Current/Best: 14.45/ 17.44 GFLOPS | Progress: (8/20) | 4.54 s
[Task 2/25] Current/Best: 7.49/ 22.85 GFLOPS | Progress: (12/20) | 7.23 s
[Task 2/25] Current/Best: 21.95/ 22.85 GFLOPS | Progress: (16/20) | 8.47 s
[Task 2/25] Current/Best: 12.94/ 22.85 GFLOPS | Progress: (20/20) | 9.89 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.59/ 19.55 GFLOPS | Progress: (4/20) | 3.62 s
[Task 3/25] Current/Best: 10.19/ 19.55 GFLOPS | Progress: (8/20) | 5.39 s
[Task 3/25] Current/Best: 9.87/ 23.40 GFLOPS | Progress: (12/20) | 7.45 s
[Task 3/25] Current/Best: 14.59/ 23.92 GFLOPS | Progress: (16/20) | 9.06 s
[Task 3/25] Current/Best: 14.21/ 23.92 GFLOPS | Progress: (20/20) | 11.41 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.61/ 19.51 GFLOPS | Progress: (4/20) | 3.44 s
[Task 4/25] Current/Best: 12.42/ 19.51 GFLOPS | Progress: (8/20) | 5.20 s
[Task 4/25] Current/Best: 13.90/ 19.51 GFLOPS | Progress: (12/20) | 9.47 s
[Task 4/25] Current/Best: 15.62/ 19.51 GFLOPS | Progress: (16/20) | 17.50 s
[Task 4/25] Current/Best: 15.48/ 19.51 GFLOPS | Progress: (20/20) | 28.36 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 5/25] Current/Best: 19.33/ 23.48 GFLOPS | Progress: (4/20) | 3.62 s
[Task 5/25] Current/Best: 5.28/ 23.48 GFLOPS | Progress: (8/20) | 5.46 s
[Task 5/25] Current/Best: 10.84/ 23.48 GFLOPS | Progress: (12/20) | 7.00 s
[Task 5/25] Current/Best: 17.85/ 23.48 GFLOPS | Progress: (16/20) | 8.88 s
[Task 5/25] Current/Best: 15.50/ 23.48 GFLOPS | Progress: (20/20) | 10.89 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 14.04/ 19.54 GFLOPS | Progress: (4/20) | 3.43 s
[Task 6/25] Current/Best: 8.14/ 19.54 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 5.86/ 19.54 GFLOPS | Progress: (12/20) | 8.38 s
[Task 6/25] Current/Best: 3.19/ 19.54 GFLOPS | Progress: (16/20) | 11.57 s
[Task 6/25] Current/Best: 11.94/ 19.54 GFLOPS | Progress: (20/20) | 15.23 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.76/ 12.37 GFLOPS | Progress: (4/20) | 4.25 s
[Task 7/25] Current/Best: 14.38/ 16.97 GFLOPS | Progress: (8/20) | 7.34 s
[Task 7/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 9.52 s
[Task 7/25] Current/Best: 18.18/ 19.05 GFLOPS | Progress: (16/20) | 12.42 s
[Task 7/25] Current/Best: 12.08/ 19.05 GFLOPS | Progress: (20/20) | 14.78 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.24/ 10.24 GFLOPS | Progress: (4/20) | 13.36 s
[Task 8/25] Current/Best: 3.19/ 14.15 GFLOPS | Progress: (8/20) | 20.47 s
[Task 8/25] Current/Best: 7.72/ 20.42 GFLOPS | Progress: (12/20) | 24.06 s
[Task 8/25] Current/Best: 7.60/ 20.42 GFLOPS | Progress: (16/20) | 30.65 s
[Task 8/25] Current/Best: 13.17/ 20.42 GFLOPS | Progress: (20/20) | 34.73 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 4.90/ 13.76 GFLOPS | Progress: (4/20) | 7.58 s
[Task 9/25] Current/Best: 12.83/ 13.91 GFLOPS | Progress: (8/20) | 13.01 s
[Task 9/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (12/20) | 21.23 s
[Task 9/25] Current/Best: 18.55/ 22.86 GFLOPS | Progress: (16/20) | 24.05 s
[Task 9/25] Current/Best: 17.66/ 22.86 GFLOPS | Progress: (20
/20) | 34.82 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (4/20) | 4.12 s
[Task 10/25] Current/Best: 8.93/ 17.93 GFLOPS | Progress: (8/20) | 5.88 s
[Task 10/25] Current/Best: 16.89/ 17.93 GFLOPS | Progress: (12/20) | 7.58 s
[Task 10/25] Current/Best: 18.07/ 20.24 GFLOPS | Progress: (16/20) | 9.20 s
[Task 10/25] Current/Best: 6.70/ 20.24 GFLOPS | Progress: (20/20) | 11.15 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.11/ 12.69 GFLOPS | Progress: (4/20) | 3.72 s
[Task 11/25] Current/Best: 8.33/ 21.59 GFLOPS | Progress: (8/20) | 6.60 s
[Task 11/25] Current/Best: 7.72/ 23.63 GFLOPS | Progress: (12/20) | 9.20 s
[Task 11/25] Current/Best: 7.79/ 23.63 GFLOPS | Progress: (16/20) | 11.85 s
[Task 11/25] Current/Best: 7.12/ 23.63 GFLOPS | Progress: (20/20) | 13.96 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 9.44/ 12.43 GFLOPS | Progress: (4/20) | 4.98 s
[Task 12/25] Current/Best: 7.29/ 16.16 GFLOPS | Progress: (8/20) | 9.93 s
[Task 12/25] Current/Best: 9.17/ 18.54 GFLOPS | Progress: (12/20) | 14.06 s
[Task 12/25] Current/Best: 11.69/ 18.54 GFLOPS | Progress: (16/20) | 18.09 s
[Task 12/25] Current/Best: 8.27/ 18.54 GFLOPS | Progress: (20/20) | 21.96 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 6.03/ 12.06 GFLOPS | Progress: (4/20) | 4.63 s
[Task 13/25] Current/Best: 9.98/ 12.06 GFLOPS | Progress: (8/20) | 7.53 s
[Task 13/25] Current/Best: 17.34/ 17.48 GFLOPS | Progress: (12/20) | 10.26 s
[Task 13/25] Current/Best: 7.00/ 18.85 GFLOPS | Progress: (16/20) | 12.87 s
[Task 13/25] Current/Best: 1.57/ 19.19 GFLOPS | Progress: (20/20) | 17.32 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 3.23 s
[Task 14/25] Current/Best: 16.98/ 20.07 GFLOPS | Progress: (8/20) | 5.26 s
[Task 14/25] Current/Best: 10.49/ 20.07 GFLOPS | Progress: (12/20) | 11.04 s
[Task 14/25] Current/Best: 15.40/ 20.07 GFLOPS | Progress: (16/20) | 12.95 s
[Task 14/25] Current/Best: 4.84/ 20.07 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 3.13/ 19.20 GFLOPS | Progress: (4/20) | 5.62 s
[Task 15/25] Current/Best: 8.56/ 19.20 GFLOPS | Progress: (8/20) | 8.88 s
[Task 15/25] Current/Best: 11.80/ 19.20 GFLOPS | Progress: (12/20) | 12.71 s
[Task 15/25] Current/Best: 12.40/ 19.20 GFLOPS | Progress: (16/20) | 14.23 s
[Task 15/25] Current/Best: 19.01/ 19.20 GFLOPS | Progress: (20/20) | 20.36 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 16.27/ 16.36 GFLOPS | Progress: (4/20) | 3.61 s
[Task 16/25] Current/Best: 5.38/ 19.49 GFLOPS | Progress: (8/20) | 5.20 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 22.30/ 23.35 GFLOPS | Progress: (4/20) | 6.51 s
[Task 1/25] Current/Best: 3.45/ 23.35 GFLOPS | Progress: (8/20) | 11.55 s
[Task 1/25] Current/Best: 19.55/ 23.35 GFLOPS | Progress: (12/20) | 14.03 s
[Task 1/25] Current/Best: 9.61/ 23.35 GFLOPS | Progress: (16/20) | 15.74 s
[Task 1/25] Current/Best: 17.60/ 23.35 GFLOPS | Progress: (20/20) | 18.35 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.81/ 15.42 GFLOPS | Progress: (4/20) | 3.07 s
[Task 2/25] Current/Best: 12.88/ 15.42 GFLOPS | Progress: (8/20) | 4.13 s
[Task 2/25] Current/Best: 13.60/ 18.99 GFLOPS | Progress: (12/20) | 5.68 s
[Task 2/25] Current/Best: 13.13/ 18.99 GFLOPS | Progress: (16/20) | 7.22 s
[Task 2/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 8.62 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 8.57/ 15.67 GFLOPS | Progress: (4/20) | 4.00 s
[Task 3/25] Current/Best: 10.14/ 19.59 GFLOPS | Progress: (8/20) | 5.71 s
[Task 3/25] Current/Best: 7.71/ 19.59 GFLOPS | Progress: (12/20) | 9.11 s
[Task 3/25] Current/Best: 15.44/ 19.59 GFLOPS | Progress: (16/20) | 10.78 s
[Task 3/25] Current/Best: 6.42/ 19.59 GFLOPS | Progress: (20/20) | 13.08 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (4/20) | 3.26 s
[Task 4/25] Current/Best: 13.99/ 19.07 GFLOPS | Progress: (8/20) | 5.80 s
[Task 4/25] Current/Best: 5.80/ 22.04 GFLOPS | Progress: (12/20) | 8.93 s
[Task 4/25] Current/Best: 17.88/ 22.04 GFLOPS | Progress: (16/20) | 10.27 s
[Task 4/25] Current/Best: 10.44/ 22.04 GFLOPS | Progress: (20/20) | 11.99 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.24/ 18.03 GFLOPS | Progress: (4/20) | 3.75 s
[Task 5/25] Current/Best: 3.25/ 18.03 GFLOPS | Progress: (8/20) | 6.06 s
[Task 5/25] Current/Best: 5.95/ 18.03 GFLOPS | Progress: (12/20) | 7.98 s
[Task 5/25] Current/Best: 3.24/ 21.25 GFLOPS | Progress: (16/20) | 9.51 s
[Task 5/25] Current/Best: 10.43/ 21.25 GFLOPS | Progress: (20/20) | 13.16 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 5.91/ 17.13 GFLOPS | Progress: (4/20) | 3.55 s
[Task 6/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (8/20) | 7.55 s
[Task 6/25] Current/Best: 2.99/ 23.10 GFLOPS | Progress: (12/20) | 10.44 s
[Task 6/25] Current/Best: 7.93/ 23.10 GFLOPS | Progress: (16/20) | 12.48 s
[Task 6/25] Current/Best: 14.04/ 23.10 GFLOPS | Progress: (20/20) | 14.73 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.10/ 18.11 GFLOPS | Progress: (4/20) | 3.37 s
[Task 7/25] Current/Best: 13.57/ 18.11 GFLOPS | Progress: (8/20) | 5.62 s
[Task 7/25] Current/Best: 17.34/ 18.11 GFLOPS | Progress: (12/20) | 7.78 s
[Task 7/25] Current/Best: 11.62/ 18.11 GFLOPS | Progress: (16/20) | 10.95 s
[Task 7/25] Current/Best: 8.79/ 18.11 GFLOPS | Progress: (20/20) | 13.71 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.55/ 11.55 GFLOPS | Progress: (4/20) | 8.45 s
[Task 8/25] Current/Best: 12.16/ 14.79 GFLOPS | Progress: (8/20) | 13.84 s
[Task 8/25] Current/Best: 9.81/ 14.79 GFLOPS | Progress: (12/20) | 17.32 s
[Task 8/25] Current/Best: 12.85/ 14.79 GFLOPS | Progress: (16/20) | 24.21 s
[Task 8/25] Current/Best: 9.20/ 20.94 GFLOPS | Progress: (20/20) | 28.71 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.55/ 12.92 GFLOPS | Progress: (4/20) | 7.23 s
[Task 9/25] Current/Best: 3.35/ 18.90 GFLOPS | Progress: (8/20) | 9.15 s
[Task 9/25] Current/Best: 9.09/ 18.90 GFLOPS | Progress: (12/20) | 15.76 s
[Task 9/25] Current/Best: 9.49/ 18.90 GFLOPS | Progress: (16/20) | 17.79 s
[Task 9/25] Current/Best: 16.59/ 18.90 GFLOPS | Progress: (20/20) | 19.61 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.35/ 18.07 GFLOPS | Progress: (4/20) | 2.86 s
[Task 10/25] Current/Best: 10.50/ 18.07 GFLOPS | Progress: (8/20) | 4.31 s
[Task 10/25] Current/Best: 12.30/ 18.07 GFLOPS | Progress: (12/20) | 5.86 s
[Task 10/25] Current/Best: 16.12/ 20.15 GFLOPS | Progress: (16/20) | 7.60 s
[Task 10/25] Current/Best: 6.03/ 22.00 GFLOPS | Progress: (20/20) | 9.11 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 15.74/ 16.90 GFLOPS | Progress: (4/20) | 3.16 s
[Task 11/25] Current/Best: 15.42/ 19.91 GFLOPS | Progress: (8/20) | 5.07 s
[Task 11/25] Current/Best: 18.14/ 19.91 GFLOPS | Progress: (12/20) | 7.35 s
[Task 11/25] Current/Best: 21.05/ 21.14 GFLOPS | Progress: (16/20) | 9.37 s
[Task 11/25] Current/Best: 12.69/ 21.48 GFLOPS | Progress: (20/20) | 11.14 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.15/ 15.65 GFLOPS | Progress: (4/20) | 5.17 s
[Task 12/25] Current/Best: 13.69/ 15.65 GFLOPS | Progress: (8/20) | 8.58 s
[Task 12/25] Current/Best: 12.46/ 15.65 GFLOPS | Progress: (12/20) | 12.00 s
[Task 12/25] Current/Best: 7.80/ 15.65 GFLOPS | Progress: (16/20) | 14.18 s
[Task 12/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (20/20) | 16.29 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.64/ 16.40 GFLOPS | Progress: (4/20) | 4.59 s
[Task 13/25] Current/Best: 6.21/ 23.08 GFLOPS | Progress: (8/20) | 7.12 s
[Task 13/25] Current/Best: 11.83/ 23.08 GFLOPS | Progress: (12/20) | 10.01 s
[Task 13/25] Current/Best: 6.24/ 23.08 GFLOPS | Progress: (16/20) | 13.47 s
[Task 13/25] Current/Best: 8.52/ 23.08 GFLOPS | Progress: (20/20) | 16.93 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 5.91/ 13.77 GFLOPS | Progress: (4/20) | 3.78 s
[Task 14/25] Current/Best: 13.58/ 18.49 GFLOPS | Progress: (8/20) | 5.97 s
[Task 14/25] Current/Best: 21.45/ 21.45 GFLOPS | Progress: (12/20) | 9.03 s
[Task 14/25] Current/Best: 1.60/ 21.45 GFLOPS | Progress: (16/20) | 13.17 s
[Task 14/25] Current/Best: 13.59/ 21.45 GFLOPS | Progress: (20/20) | 15.36 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.66/ 20.03 GFLOPS | Progress: (4/20) | 4.45 s
[Task 15/25] Current/Best: 6.76/ 22.14 GFLOPS | Progress: (8/20) | 6.43 s
[Task 15/25] Current/Best: 8.35/ 22.14 GFLOPS | Progress: (12/20) | 10.91 s
[Task 15/25] Current/Best: 18.38/ 22.14 GFLOPS | Progress: (16/20) | 12.19 s
[Task 15/25] Current/Best: 14.92/ 22.14 GFLOPS | Progress: (20/20)
| 13.65 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 12.00/ 15.02 GFLOPS | Progress: (4/20) | 3.08 s Done.
Done.
-
[Task 16/25] Current/Best: 17.93/ 19.49 GFLOPS | Progress: (12/20) | 7.27 s
[Task 16/25] Current/Best: 13.82/ 19.49 GFLOPS | Progress: (16/20) | 8.72 s
[Task 16/25] Current/Best: 12.03/ 20.68 GFLOPS | Progress: (20/20) | 10.37 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.68/ 20.05 GFLOPS | Progress: (4/20) | 3.37 s
[Task 17/25] Current/Best: 11.62/ 20.05 GFLOPS | Progress: (8/20) | 7.16 s
[Task 17/25] Current/Best: 6.16/ 22.46 GFLOPS | Progress: (12/20) | 10.55 s
[Task 17/25] Current/Best: 14.59/ 23.13 GFLOPS | Progress: (16/20) | 12.38 s
[Task 17/25] Current/Best: 10.42/ 23.13 GFLOPS | Progress: (20/20) | 14.50 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (4/20) | 3.47 s
[Task 18/25] Current/Best: 3.11/ 21.21 GFLOPS | Progress: (8/20) | 5.68 s
[Task 18/25] Current/Best: 14.80/ 21.21 GFLOPS | Progress: (12/20) | 7.84 s
[Task 18/25] Current/Best: 10.90/ 21.21 GFLOPS | Progress: (16/20) | 11.63 s
[Task 18/25] Current/Best: 15.51/ 21.21 GFLOPS | Progress: (20/20) | 13.85 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 5.31 s
[Task 19/25] Current/Best: 10.28/ 21.30 GFLOPS | Progress: (8/20) | 10.31 s
[Task 19/25] Current/Best: 17.77/ 21.30 GFLOPS | Progress: (12/20) | 13.93 s
[Task 19/25] Current/Best: 11.87/ 21.30 GFLOPS | Progress: (16/20) | 16.63 s
[Task 19/25] Current/Best: 10.07/ 21.30 GFLOPS | Progress: (20/20) | 18.59 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.30/ 16.52 GFLOPS | Progress: (4/20) | 3.39 s
[Task 20/25] Current/Best: 15.42/ 17.94 GFLOPS | Progress: (8/20) | 5.39 s
[Task 20/25] Current/Best: 15.57/ 18.82 GFLOPS | Progress: (12/20) | 8.01 s
[Task 20/25] Current/Best: 16.59/ 18.82 GFLOPS | Progress: (16/20) | 10.84 s
[Task 20/25] Current/Best: 2.24/ 18.82 GFLOPS | Progress: (20/20) | 13.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 5.22/ 11.16 GFLOPS | Progress: (4/20) | 4.28 s
[Task 21/25] Current/Best: 8.84/ 14.51 GFLOPS | Progress: (8/20) | 6.79 s
[Task 21/25] Current/Best: 16.30/ 16.30 GFLOPS | Progress: (12/20) | 9.53 s Done.
-
[Task 21/25] Current/Best: 11.45/ 20.16 GFLOPS | Progress: (16/20) | 11.91 s
[Task 21/25] Current/Best: 9.53/ 20.16 GFLOPS | Progress: (20/20) | 14.02 s Done.
-
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.60/ 11.59 GFLOPS | Progress: (4/20) | 3.54 s
[Task 22/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.39 s
[Task 22/25] Current/Best: 4.46/ 17.28 GFLOPS | Progress: (12/20) | 6.87 s
[Task 22/25] Current/Best: 16.47/ 17.28 GFLOPS | Progress: (16/20) | 8.19 s
[Task 22/25] Current/Best: 11.96/ 17.28 GFLOPS | Progress: (20/20) | 10.24 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (4/20) | 4.67 s
[Task 23/25] Current/Best: 13.42/ 16.38 GFLOPS | Progress: (8/20) | 7.15 s
[Task 23/25] Current/Best: 9.81/ 16.38 GFLOPS | Progress: (12/20) | 10.47 s
[Task 23/25] Current/Best: 9.80/ 18.98 GFLOPS | Progress: (16/20) | 12.89 s
[Task 23/25] Current/Best: 8.33/ 18.98 GFLOPS | Progress: (20/20) | 15.21 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 7.90/ 8.24 GFLOPS | Progress: (4/20) | 12.27 s
[Task 24/25] Current/Best: 9.93/ 9.93 GFLOPS | Progress: (8/20) | 22.97 s
[Task 24/25] Current/Best: 3.74/ 9.93 GFLOPS | Progress: (12/20) | 33.71 s
[Task 24/25] Current/Best: 3.94/ 9.93 GFLOPS | Progress: (16/20) | 44.41 s
[Task 24/25] Current/Best: 1.71/ 9.93 GFLOPS | Progress: (20/20) | 54.91 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 3.02/ 3.02 GFLOPS | Progress: (4/20) | 12.98 s
[Task 25/25] Current/Best: 3.04/ 9.07 GFLOPS | Progress: (8/20) | 18.78 s
[Task 25/25] Current/Best: 7.75/ 9.07 GFLOPS | Progress: (12/20) | 19.82 s
[Task 25/25] Current/Best: 1.54/ 9.07 GFLOPS | Progress: (16/20) | 30.55 s
[Task 25/25] Current/Best: 1.55/ 9.29 GFLOPS | Progress: (20/20) | 35.59 s
+
[Task 16/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (8/20) | 4.35 s
[Task 16/25] Current/Best: 5.98/ 20.97 GFLOPS | Progress: (12/20) | 6.58 s
[Task 16/25] Current/Best: 15.07/ 20.97 GFLOPS | Progress: (16/20) | 8.51 s
[Task 16/25] Current/Best: 2.96/ 20.97 GFLOPS | Progress: (20/20) | 10.57 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.71/ 19.16 GFLOPS | Progress: (4/20) | 4.40 s
[Task 17/25] Current/Best: 11.85/ 19.16 GFLOPS | Progress: (8/20) | 7.05 s
[Task 17/25] Current/Best: 4.31/ 19.16 GFLOPS | Progress: (12/20) | 10.80 s
[Task 17/25] Current/Best: 3.09/ 19.16 GFLOPS | Progress: (16/20) | 13.35 s
[Task 17/25] Current/Best: 6.14/ 19.58 GFLOPS | Progress: (20/20) | 15.19 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (4/20) | 3.51 s
[Task 18/25] Current/Best: 10.17/ 20.25 GFLOPS | Progress: (8/20) | 7.09 s
[Task 18/25] Current/Best: 5.89/ 21.14 GFLOPS | Progress: (12/20) | 8.72 s
[Task 18/25] Current/Best: 15.33/ 21.14 GFLOPS | Progress: (16/20) | 11.80 s
[Task 18/25] Current/Best: 10.48/ 21.14 GFLOPS | Progress: (20/20) | 17.66 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 12.09/ 20.81 GFLOPS | Progress: (4/20) | 4.19 s
[Task 19/25] Current/Best: 3.09/ 20.81 GFLOPS | Progress: (8/20) | 7.62 s
[Task 19/25] Current/Best: 11.95/ 20.81 GFLOPS | Progress: (12/20) | 10.57 s
[Task 19/25] Current/Best: 10.89/ 20.81 GFLOPS | Progress: (16/20) | 14.44 s
[Task 19/25] Current/Best: 11.66/ 20.81 GFLOPS | Progress: (20/20) | 17.74 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (4/20) | 3.60 s
[Task 20/25] Current/Best: 15.56/ 22.49 GFLOPS | Progress: (8/20) | 6.27 s
[Task 20/25] Current/Best: 5.21/ 22.49 GFLOPS | Progress: (12/20) | 10.14 s
[Task 20/25] Current/Best: 6.76/ 22.49 GFLOPS | Progress: (16/20) | 15.72 s
[Task 20/25] Current/Best: 16.71/ 22.49 GFLOPS | Progress: (20/20) | 17.71 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 2.70/ 20.64 GFLOPS | Progress: (4/20) | 3.83 s
[Task 21/25] Current/Best: 6.38/ 20.64 GFLOPS | Progress: (8/20) | 7.13 s
[Task 21/25] Current/Best: 13.17/ 20.64 GFLOPS | Progress: (12/20) | 8.52 s
[Task 21/25] Current/Best: 17.82/ 20.64 GFLOPS | Progress: (16/20) | 10.10 s
[Task 21/25] Current/Best: 8.66/ 20.64 GFLOPS | Progress: (20/20)
| 13.25 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 4.48 s
[Task 22/25] Current/Best: 6.87/ 19.86 GFLOPS | Progress: (8/20) | 7.70 s
[Task 22/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (12/20) | 12.63 s
[Task 22/25] Current/Best: 19.49/ 19.96 GFLOPS | Progress: (16/20) | 14.16 s
[Task 22/25] Current/Best: 5.20/ 19.96 GFLOPS | Progress: (20/20) | 16.16 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.96/ 21.02 GFLOPS | Progress: (4/20) | 3.81 s
[Task 23/25] Current/Best: 20.66/ 21.02 GFLOPS | Progress: (8/20) | 7.05 s
[Task 23/25] Current/Best: 19.74/ 21.02 GFLOPS | Progress: (12/20) | 9.99 s
[Task 23/25] Current/Best: 12.20/ 22.75 GFLOPS | Progress: (16/20) | 12.86 s
[Task 23/25] Current/Best: 21.49/ 22.75 GFLOPS | Progress: (20/20) | 18.15 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 10.67/ 10.67 GFLOPS | Progress: (4/20) | 12.17 s Done.
+ Done.
+
[Task 24/25] Current/Best: 3.21/ 10.67 GFLOPS | Progress: (8/20) | 23.22 s
[Task 24/25] Current/Best: 8.55/ 10.67 GFLOPS | Progress: (12/20) | 24.93 s
[Task 24/25] Current/Best: 10.61/ 10.67 GFLOPS | Progress: (16/20) | 35.38 s
[Task 24/25] Current/Best: 1.38/ 10.67 GFLOPS | Progress: (20/20) | 47.28 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 6.40/ 6.40 GFLOPS | Progress: (4/20) | 12.18 s
[Task 25/25] Current/Best: 2.83/ 9.36 GFLOPS | Progress: (8/20) | 15.10 s
[Task 25/25] Current/Best: 6.74/ 9.36 GFLOPS | Progress: (12/20) | 24.56 s
[Task 25/25] Current/Best: 3.01/ 9.36 GFLOPS | Progress: (16/20) | 27.19 s
[Task 25/25] Current/Best: 4.28/ 9.36 GFLOPS | Progress: (20/20) | 37.92 s
@@ -674,8 +673,8 @@ 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=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 416.1014501600016, 'median': 415.50952905000713, 'std': 4.321109686634458}
- unoptimized: {'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
+ optimized: {'mean': 413.7397979600041, 'median': 412.7553719000048, 'std': 4.334746790432081}
+ unoptimized: {'mean': 514.0096369799994, 'median': 513.533555500004, 'std': 2.507549372894095}
@@ -756,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 28.828 seconds)
+ **Total running time of the script:** ( 10 minutes 42.113 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 5bd5893e5a..22fbd15343 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
- 1.25e-07 secs/op
+ 1.222e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index b2e47ba4c5..bcf0d57ecf 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, 0x8a10b00)), stage(b, placeholder(b, 0x2399d1b0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x220e1dc0)), stage(b, placeholder(b, 0x220b6320)), 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 [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index bea1da69ea..102b49d219 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
=================
-**15:11.609** total execution time for **tutorial** files:
+**14:09.492** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:28.828 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:42.113 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.730 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:31.220 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.170 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.399 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:33.794 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.563 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.784 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.717 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.355 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.543 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.761 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.176 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_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 |
++------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index c22e762e2d..37690c0294 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -448,7 +448,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000046
+ vector: 0.000025
@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, [n: int32], [stride: int32], type="auto"),
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.813590000296245e-06 1.0
- naive 6.7472e-06 0.8635211215003842
- parallel 6.9564e-06 0.8902949860097925
- vector 4.60098e-05 5.888432845626093
+ numpy 7.007709998561041e-06 1.0
+ naive 6.9286e-06 0.9887110056527332
+ parallel 7.2283e-06 1.0314781863810367
+ vector 2.45875e-05 3.5086354893465606
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018505
+ Numpy running time: 0.018952
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.251925
+ none: 3.453091
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.306264
+ blocking: 0.289743
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.341208
+ vectorization: 0.330403
@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: 0.119167
+ loop permutation: 0.114389
@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: 0.110721
+ array packing: 0.108428
@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: 0.111180
+ block caching: 0.115082
@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: 0.146938
+ parallelization: 0.151680
@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 3.2519253935 1.0
- blocking 0.30626426110000005 0.09417936269760858
- vectorization 0.3412077699 0.10492484562592103
- loop permutation 0.1191673078 0.036645154294804395
- array packing 0.1107214522 0.034047968142600006
- block caching 0.11117954749999999 0.03418883708778419
- parallelization 0.1469377231 0.04518483830954469
+ none 3.4530912585999998 1.0
+ blocking 0.2897431765 0.08390834611694326
+ vectorization 0.3304027778 0.09568318734036484
+ loop permutation 0.1143893309 0.033126645759827766
+ array packing 0.10842805429999999 0.031400286346315795
+ block caching 0.11508194040000001 0.03332722241654804
+ parallelization 0.1516800285 0.043925867328944046
@@ -1652,6 +1652,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.399 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index d832c0dcd9..37e282cd2c 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-545f8dc927d4dc9fb1394c67c681ea40ec16db8d
+7cfa62e255409b083d07b537765726a634c449c4
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index b12b4f1596..97f52f8cfd 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 10.166 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.856 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 7a05342014..ef597fa16f 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 973ms/step
+1/1 [==============================] - 1s 925ms/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 1205ebefdb..4379597791 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.zip6b750afc-1efa-4bcf-8409-efe2e0573a2b 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.zip4d78fb1a-458f-4d48-8f8a-1739d5c60dd8 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 35b57c890f..741810f101 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,12 +448,13 @@ 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%|#8 | 7.79M/41.5M [00:00<00:00, 81.7MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 65.7MB/s]
- 54%|#####4 | 22.5M/41.5M [00:00<00:00, 62.7MB/s]
- 69%|######8 | 28.5M/41.5M [00:00<00:00, 60.8MB/s]
- 83%|########2 | 34.4M/41.5M [00:00<00:00, 50.9MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 63.2MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 54.4MB/s]
+ 28%|##7 | 11.5M/41.5M [00:00<00:00, 52.4MB/s]
+ 40%|###9 | 16.5M/41.5M [00:00<00:00, 51.3MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 52.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 62.0MB/s]
+ 92%|#########1| 38.0M/41.5M [00:00<00:00, 61.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 51.1MB/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 15aedda7ee..e46d70c1d4 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,11 +431,10 @@ 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]
- 19%|#9 | 8.53M/44.7M [00:00<00:00, 89.4MB/s]
- 49%|####8 | 21.7M/44.7M [00:00<00:00, 118MB/s]
- 74%|#######3 | 32.9M/44.7M [00:00<00:00, 99.4MB/s]
-100%|#########9| 44.7M/44.7M [00:00<00:00, 108MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 106MB/s]
+ 28%|##8 | 12.7M/44.7M [00:00<00:00, 132MB/s]
+ 57%|#####6 | 25.3M/44.7M [00:00<00:00, 111MB/s]
+ 81%|######## | 36.1M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 14dcefa05b..0d366a74c5 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 12.047 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.392 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 9e1d0d7bd3..2addce9700 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>05:43.043</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:39.658</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_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>01:12.047</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:10.856</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:10.166</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:10.392</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>00:46.739</p></td>
+<td><p>00:45.945</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>00:32.094</p></td>
+<td><p>00:31.737</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>00:28.559</p></td>
+<td><p>00:28.272</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>00:26.503</p></td>
+<td><p>00:26.259</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.827</p></td>
+<td><p>00:24.451</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>00:22.476</p></td>
+<td><p>00:21.845</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>00:17.246</p></td>
+<td><p>00:17.504</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>00:02.386</p></td>
+<td><p>00:02.397</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 7f57cca972..906754f24c 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)
- 16.2368 16.1416 17.2407 15.8435 0.3782
+ 15.7418 15.6674 16.5301 15.5206 0.2778
</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 526b95f9e0..6cd0580e31 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,21 +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]
- 5%|4 | 7.99M/170M [00:00<00:02, 74.6MB/s]
- 13%|#2 | 21.8M/170M [00:00<00:01, 114MB/s]
- 19%|#9 | 32.8M/170M [00:00<00:01, 85.1MB/s]
- 27%|##7 | 46.3M/170M [00:00<00:01, 94.5MB/s]
- 37%|###6 | 62.3M/170M [00:00<00:01, 112MB/s]
- 43%|####3 | 73.5M/170M [00:00<00:00, 113MB/s]
- 50%|####9 | 84.7M/170M [00:00<00:00, 109MB/s]
- 56%|#####6 | 95.3M/170M [00:00<00:00, 106MB/s]
- 62%|######2 | 106M/170M [00:01<00:00, 102MB/s]
- 68%|######8 | 116M/170M [00:01<00:00, 103MB/s]
- 74%|#######4 | 126M/170M [00:01<00:00, 80.5MB/s]
- 85%|########5 | 145M/170M [00:01<00:00, 108MB/s]
- 92%|#########1| 156M/170M [00:01<00:00, 105MB/s]
- 98%|#########8| 167M/170M [00:01<00:00, 105MB/s]
-100%|##########| 170M/170M [00:01<00:00, 102MB/s]
+ 7%|7 | 11.9M/170M [00:00<00:01, 125MB/s]
+ 14%|#4 | 23.8M/170M [00:00<00:01, 109MB/s]
+ 20%|## | 34.4M/170M [00:00<00:01, 105MB/s]
+ 26%|##6 | 44.4M/170M [00:00<00:01, 103MB/s]
+ 32%|###1 | 54.3M/170M [00:00<00:01, 102MB/s]
+ 38%|###7 | 64.1M/170M [00:00<00:01, 99.9MB/s]
+ 43%|####3 | 73.6M/170M [00:00<00:01, 86.7MB/s]
+ 52%|#####1 | 88.0M/170M [00:00<00:00, 104MB/s]
+ 58%|#####7 | 98.3M/170M [00:01<00:00, 104MB/s]
+ 64%|######3 | 108M/170M [00:01<00:00, 103MB/s]
+ 70%|######9 | 118M/170M [00:01<00:00, 102MB/s]
+ 76%|#######5 | 128M/170M [00:01<00:00, 101MB/s]
+ 81%|########1 | 138M/170M [00:01<00:00, 95.2MB/s]
+ 88%|########8 | 150M/170M [00:01<00:00, 103MB/s]
+ 94%|#########3| 160M/170M [00:01<00:00, 102MB/s]
+100%|#########9| 169M/170M [00:01<00:00, 99.9MB/s]
+100%|##########| 170M/170M [00:01<00:00, 101MB/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=& [...]
@@ -565,7 +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 15.476 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 10.448 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 29a8638c66..bf6b2b8441 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]
- 70%|####### | 9.53M/13.6M [00:00<00:00, 99.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 91.7MB/s]
+ 90%|########9 | 12.2M/13.6M [00:00<00:00, 90.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 96.4MB/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)
- 90.2577 90.1606 93.6899 90.0567 0.3853
+ 90.7002 90.6094 92.3397 90.3056 0.3502
</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 6.518 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.883 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 b0d09679e2..37b3327327 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)
- 121.2431 121.1623 127.4660 119.8259 0.8353
+ 119.3615 119.2206 121.4561 118.0381 0.6789
</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 28.050 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.380 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 7ad85744d9..4d3909ce71 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 22.565 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.523 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 d3149c6249..1d0641fb72 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,24 +462,24 @@ 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]
- 1%| | 989/132723 [00:00<00:13, 9888.29KB/s]
- 3%|2 | 3888/132723 [00:00<00:06, 21123.09KB/s]
- 7%|6 | 9047/132723 [00:00<00:03, 35032.89KB/s]
- 13%|#3 | 17320/132723 [00:00<00:02, 53860.32KB/s]
- 19%|#9 | 25763/132723 [00:00<00:01, 64879.73KB/s]
- 26%|##5 | 34195/132723 [00:00<00:01, 71484.05KB/s]
- 32%|###2 | 42694/132723 [00:00<00:01, 75897.52KB/s]
- 39%|###8 | 51165/132723 [00:00<00:01, 78700.65KB/s]
- 45%|####4 | 59722/132723 [00:00<00:00, 80845.81KB/s]
- 51%|#####1 | 68227/132723 [00:01<00:00, 82137.56KB/s]
- 58%|#####7 | 76753/132723 [00:01<00:00, 83091.48KB/s]
- 64%|######4 | 85267/132723 [00:01<00:00, 83711.23KB/s]
- 71%|####### | 93830/132723 [00:01<00:00, 84290.46KB/s]
- 77%|#######7 | 102377/132723 [00:01<00:00, 84642.47KB/s]
- 84%|########3 | 110923/132723 [00:01<00:00, 84886.16KB/s]
- 90%|########9 | 119443/132723 [00:01<00:00, 84978.99KB/s]
- 96%|#########6| 127944/132723 [00:01<00:00, 84984.99KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75497.61KB/s]
+ 4%|4 | 5927/132723 [00:00<00:02, 59261.16KB/s]
+ 10%|9 | 13157/132723 [00:00<00:01, 66910.83KB/s]
+ 15%|#4 | 19848/132723 [00:00<00:02, 46435.05KB/s]
+ 21%|## | 27435/132723 [00:00<00:01, 55602.91KB/s]
+ 26%|##6 | 35069/132723 [00:00<00:01, 61988.32KB/s]
+ 32%|###2 | 42665/132723 [00:00<00:01, 66254.47KB/s]
+ 38%|###8 | 50526/132723 [00:00<00:01, 70006.50KB/s]
+ 44%|####4 | 58437/132723 [00:00<00:01, 72755.47KB/s]
+ 50%|####9 | 66321/132723 [00:00<00:00, 74590.20KB/s]
+ 56%|#####5 | 74197/132723 [00:01<00:00, 75836.35KB/s]
+ 62%|######1 | 82073/132723 [00:01<00:00, 76713.54KB/s]
+ 68%|######7 | 90041/132723 [00:01<00:00, 77602.29KB/s]
+ 74%|#######3 | 98013/132723 [00:01<00:00, 78234.41KB/s]
+ 80%|#######9 | 105973/132723 [00:01<00:00, 78640.10KB/s]
+ 86%|########5 | 113916/132723 [00:01<00:00, 78874.47KB/s]
+ 92%|#########1| 121831/132723 [00:01<00:00, 78954.48KB/s]
+ 98%|#########7| 129765/132723 [00:01<00:00, 79063.85KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72363.74KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -518,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.538 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.266 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 6e1aa96623..b509eb4b06 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>12:41.659</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:34.747</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:15.476</p></td>
+<td><p>03:10.448</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>03:01.538</p></td>
+<td><p>02:58.266</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>02:28.050</p></td>
+<td><p>02:28.380</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>01:22.565</p></td>
+<td><p>01:27.523</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>01:06.518</p></td>
+<td><p>01:04.883</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:36.494</p></td>
+<td><p>00:35.137</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>00:25.723</p></td>
+<td><p>00:25.369</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>00:25.289</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_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 7b77debb24..ea12d5c172 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.zip7655373e-66f5-49e7-ab2b-a4d074a21974 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.zip82c06671-e7b4-43d1-bd3e-1a651918a60e 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 76f313a4b2..de2ae18132 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>00:47.923</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.395</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:44.417</p></td>
+<td><p>00:43.032</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>00:02.447</p></td>
+<td><p>00:02.352</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>00:01.052</p></td>
+<td><p>00:01.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 1b22e6ab46..bd2841b761 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: 7185us [7185us] (46.20%; 46.20%)
-FoldScaleAxis: 8366us [6us] (53.80%; 53.80%)
- FoldConstant: 8360us [1739us] (53.76%; 99.93%)
- InferType: 6621us [6621us] (42.58%; 79.20%)
+InferType: 7922us [7922us] (48.97%; 48.97%)
+FoldScaleAxis: 8255us [7us] (51.03%; 51.03%)
+ FoldConstant: 8248us [1714us] (50.99%; 99.92%)
+ InferType: 6534us [6534us] (40.39%; 79.22%)
</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: 6635us [6635us] (44.88%; 44.88%)
-FoldScaleAxis: 8148us [4us] (55.12%; 55.12%)
- FoldConstant: 8143us [1691us] (55.09%; 99.95%)
- InferType: 6452us [6452us] (43.65%; 79.23%)
+InferType: 6511us [6511us] (45.08%; 45.08%)
+FoldScaleAxis: 7931us [4us] (54.92%; 54.92%)
+ FoldConstant: 7927us [1651us] (54.89%; 99.95%)
+ InferType: 6276us [6276us] (43.46%; 79.17%)
</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 ff0be5c608..c8ea5003da 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: 33.681217 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.108318 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 9e1da1a766..23de416c0d 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: 11.884211 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.290620 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 cef6101619..8bf1b96b49 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: 0.019378
-Baseline: 3.254845
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018161
+Baseline: 3.438465
</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: 0.312445
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.294571
</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: 0.342553
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328327
</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: 0.117296
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120637
</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: 0.109728
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109178
</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: 0.111531
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111052
</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: 0.146557
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146533
</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 6f84252a0e..a78d3c7606 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>00:34.641</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.761</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>00:32.145</p></td>
+<td><p>00:32.254</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>00:01.439</p></td>
+<td><p>00:01.435</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>00:01.057</p></td>
+<td><p>00:01.072</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 b169ad76b5..6f26fe9e12 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>08:57.679</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:11.146</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>05:31.333</p></td>
+<td><p>05:50.059</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>01:32.063</p></td>
+<td><p>01:30.953</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>01:01.134</p></td>
+<td><p>00:59.922</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>00:29.653</p></td>
+<td><p>00:27.599</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>00:12.065</p></td>
+<td><p>00:11.778</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>00:11.431</p></td>
+<td><p>00:10.836</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 44b5d91805..642a711f13 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
@@ -488,6 +488,10 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+.T
+</pre></div>
+</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -1016,7 +1020,7 @@ 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: 0.357 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.355 ms
</pre></div>
</div>
</div>
@@ -1579,7 +1583,7 @@ 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 31.333 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 50.059 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 32c3aafba4..b707f4c59e 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)
- 7.8658 7.8691 7.8719 7.8564 0.0068
+ 7.8499 7.8405 7.8706 7.8385 0.0147
</pre></div>
</div>
</div>
@@ -937,7 +937,6 @@ 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 1.134 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 18ae7c6135..71fbd9835d 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)
- 763.6102 762.2447 766.9282 761.6576 2.3584
+ 757.9457 759.6920 760.8923 753.2529 3.3543
</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 32.063 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.953 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 5c7ce6b272..02855a6bab 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -634,406 +634,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
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.i1.outer.fused: int32, 0, 32) "parallel" {
allocate(compute_3: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
- for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i.outer.inner*256) + (nb_j.inner*16))
- let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- {
- compute_4: Buffer(compute_3, float32, [2048], [])[cse_var_2] = 0f32
- compute_4[(cse_var_2 + 1)] = 0f32
- compute_4[(cse_var_2 + 2)] = 0f32
- compute_4[(cse_var_2 + 3)] = 0f32
- compute_4[(cse_var_2 + 4)] = 0f32
- compute_4[(cse_var_2 + 5)] = 0f32
- compute_4[(cse_var_2 + 6)] = 0f32
- compute_4[(cse_var_2 + 7)] = 0f32
- compute_4[(cse_var_2 + 8)] = 0f32
- compute_4[(cse_var_2 + 9)] = 0f32
- compute_4[(cse_var_2 + 10)] = 0f32
- compute_4[(cse_var_2 + 11)] = 0f32
- compute_4[(cse_var_2 + 12)] = 0f32
- compute_4[(cse_var_2 + 13)] = 0f32
- compute_4[(cse_var_2 + 14)] = 0f32
- compute_4[(cse_var_2 + 15)] = 0f32
- compute_4[(cse_var_2 + 32)] = 0f32
- compute_4[(cse_var_2 + 33)] = 0f32
- compute_4[(cse_var_2 + 34)] = 0f32
- compute_4[(cse_var_2 + 35)] = 0f32
- compute_4[(cse_var_2 + 36)] = 0f32
- compute_4[(cse_var_2 + 37)] = 0f32
- compute_4[(cse_var_2 + 38)] = 0f32
- compute_4[(cse_var_2 + 39)] = 0f32
- compute_4[(cse_var_2 + 40)] = 0f32
- compute_4[(cse_var_2 + 41)] = 0f32
- compute_4[(cse_var_2 + 42)] = 0f32
- compute_4[(cse_var_2 + 43)] = 0f32
- compute_4[(cse_var_2 + 44)] = 0f32
- compute_4[(cse_var_2 + 45)] = 0f32
- compute_4[(cse_var_2 + 46)] = 0f32
- compute_4[(cse_var_2 + 47)] = 0f32
- compute_4[(cse_var_2 + 64)] = 0f32
- compute_4[(cse_var_2 + 65)] = 0f32
- compute_4[(cse_var_2 + 66)] = 0f32
- compute_4[(cse_var_2 + 67)] = 0f32
- compute_4[(cse_var_2 + 68)] = 0f32
- compute_4[(cse_var_2 + 69)] = 0f32
- compute_4[(cse_var_2 + 70)] = 0f32
- compute_4[(cse_var_2 + 71)] = 0f32
- compute_4[(cse_var_2 + 72)] = 0f32
- compute_4[(cse_var_2 + 73)] = 0f32
- compute_4[(cse_var_2 + 74)] = 0f32
- compute_4[(cse_var_2 + 75)] = 0f32
- compute_4[(cse_var_2 + 76)] = 0f32
- compute_4[(cse_var_2 + 77)] = 0f32
- compute_4[(cse_var_2 + 78)] = 0f32
- compute_4[(cse_var_2 + 79)] = 0f32
- compute_4[(cse_var_2 + 96)] = 0f32
- compute_4[(cse_var_2 + 97)] = 0f32
- compute_4[(cse_var_2 + 98)] = 0f32
- compute_4[(cse_var_2 + 99)] = 0f32
- compute_4[(cse_var_2 + 100)] = 0f32
- compute_4[(cse_var_2 + 101)] = 0f32
- compute_4[(cse_var_2 + 102)] = 0f32
- compute_4[(cse_var_2 + 103)] = 0f32
- compute_4[(cse_var_2 + 104)] = 0f32
- compute_4[(cse_var_2 + 105)] = 0f32
- compute_4[(cse_var_2 + 106)] = 0f32
- compute_4[(cse_var_2 + 107)] = 0f32
- compute_4[(cse_var_2 + 108)] = 0f32
- compute_4[(cse_var_2 + 109)] = 0f32
- compute_4[(cse_var_2 + 110)] = 0f32
- compute_4[(cse_var_2 + 111)] = 0f32
- compute_4[(cse_var_2 + 128)] = 0f32
- compute_4[(cse_var_2 + 129)] = 0f32
- compute_4[(cse_var_2 + 130)] = 0f32
- compute_4[(cse_var_2 + 131)] = 0f32
- compute_4[(cse_var_2 + 132)] = 0f32
- compute_4[(cse_var_2 + 133)] = 0f32
- compute_4[(cse_var_2 + 134)] = 0f32
- compute_4[(cse_var_2 + 135)] = 0f32
- compute_4[(cse_var_2 + 136)] = 0f32
- compute_4[(cse_var_2 + 137)] = 0f32
- compute_4[(cse_var_2 + 138)] = 0f32
- compute_4[(cse_var_2 + 139)] = 0f32
- compute_4[(cse_var_2 + 140)] = 0f32
- compute_4[(cse_var_2 + 141)] = 0f32
- compute_4[(cse_var_2 + 142)] = 0f32
- compute_4[(cse_var_2 + 143)] = 0f32
- compute_4[(cse_var_2 + 160)] = 0f32
- compute_4[(cse_var_2 + 161)] = 0f32
- compute_4[(cse_var_2 + 162)] = 0f32
- compute_4[(cse_var_2 + 163)] = 0f32
- compute_4[(cse_var_2 + 164)] = 0f32
- compute_4[(cse_var_2 + 165)] = 0f32
- compute_4[(cse_var_2 + 166)] = 0f32
- compute_4[(cse_var_2 + 167)] = 0f32
- compute_4[(cse_var_2 + 168)] = 0f32
- compute_4[(cse_var_2 + 169)] = 0f32
- compute_4[(cse_var_2 + 170)] = 0f32
- compute_4[(cse_var_2 + 171)] = 0f32
- compute_4[(cse_var_2 + 172)] = 0f32
- compute_4[(cse_var_2 + 173)] = 0f32
- compute_4[(cse_var_2 + 174)] = 0f32
- compute_4[(cse_var_2 + 175)] = 0f32
- compute_4[(cse_var_2 + 192)] = 0f32
- compute_4[(cse_var_2 + 193)] = 0f32
- compute_4[(cse_var_2 + 194)] = 0f32
- compute_4[(cse_var_2 + 195)] = 0f32
- compute_4[(cse_var_2 + 196)] = 0f32
- compute_4[(cse_var_2 + 197)] = 0f32
- compute_4[(cse_var_2 + 198)] = 0f32
- compute_4[(cse_var_2 + 199)] = 0f32
- compute_4[(cse_var_2 + 200)] = 0f32
- compute_4[(cse_var_2 + 201)] = 0f32
- compute_4[(cse_var_2 + 202)] = 0f32
- compute_4[(cse_var_2 + 203)] = 0f32
- compute_4[(cse_var_2 + 204)] = 0f32
- compute_4[(cse_var_2 + 205)] = 0f32
- compute_4[(cse_var_2 + 206)] = 0f32
- compute_4[(cse_var_2 + 207)] = 0f32
- compute_4[(cse_var_2 + 224)] = 0f32
- compute_4[(cse_var_2 + 225)] = 0f32
- compute_4[(cse_var_2 + 226)] = 0f32
- compute_4[(cse_var_2 + 227)] = 0f32
- compute_4[(cse_var_2 + 228)] = 0f32
- compute_4[(cse_var_2 + 229)] = 0f32
- compute_4[(cse_var_2 + 230)] = 0f32
- compute_4[(cse_var_2 + 231)] = 0f32
- compute_4[(cse_var_2 + 232)] = 0f32
- compute_4[(cse_var_2 + 233)] = 0f32
- compute_4[(cse_var_2 + 234)] = 0f32
- compute_4[(cse_var_2 + 235)] = 0f32
- compute_4[(cse_var_2 + 236)] = 0f32
- compute_4[(cse_var_2 + 237)] = 0f32
- compute_4[(cse_var_2 + 238)] = 0f32
- compute_4[(cse_var_2 + 239)] = 0f32
- for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- let cse_var_131: int32 = (elem_idx*16)
- let cse_var_130: int32 = (cse_var_2 + 99)
- let cse_var_129: int32 = (cse_var_2 + 98)
- let cse_var_128: int32 = (cse_var_2 + 97)
- let cse_var_127: int32 = (cse_var_2 + 96)
- let cse_var_126: int32 = (cse_var_2 + 9)
- let cse_var_125: int32 = (cse_var_2 + 8)
- let cse_var_124: int32 = (cse_var_2 + 79)
- let cse_var_123: int32 = (cse_var_2 + 78)
- let cse_var_122: int32 = (cse_var_2 + 77)
- let cse_var_121: int32 = (cse_var_2 + 76)
- let cse_var_120: int32 = (cse_var_2 + 75)
- let cse_var_119: int32 = (cse_var_2 + 74)
- let cse_var_118: int32 = (cse_var_2 + 73)
- let cse_var_117: int32 = (cse_var_2 + 72)
- let cse_var_116: int32 = (cse_var_2 + 71)
- let cse_var_115: int32 = (cse_var_2 + 70)
- let cse_var_114: int32 = (cse_var_2 + 7)
- let cse_var_113: int32 = (cse_var_2 + 69)
- let cse_var_112: int32 = (cse_var_2 + 68)
- let cse_var_111: int32 = (cse_var_2 + 67)
- let cse_var_110: int32 = (cse_var_2 + 66)
- let cse_var_109: int32 = (cse_var_2 + 65)
- let cse_var_108: int32 = (cse_var_2 + 64)
- let cse_var_107: int32 = (cse_var_2 + 6)
- let cse_var_106: int32 = (cse_var_2 + 5)
- let cse_var_105: int32 = (cse_var_2 + 47)
- let cse_var_104: int32 = (cse_var_2 + 46)
- let cse_var_103: int32 = (cse_var_2 + 45)
- let cse_var_102: int32 = (cse_var_2 + 44)
- let cse_var_101: int32 = (cse_var_2 + 43)
- let cse_var_100: int32 = (cse_var_2 + 42)
- let cse_var_99: int32 = (cse_var_2 + 41)
- let cse_var_98: int32 = (cse_var_2 + 40)
- let cse_var_97: int32 = (cse_var_2 + 4)
- let cse_var_96: int32 = (cse_var_2 + 39)
- let cse_var_95: int32 = (cse_var_2 + 38)
- let cse_var_94: int32 = (cse_var_2 + 37)
- let cse_var_93: int32 = (cse_var_2 + 36)
- let cse_var_92: int32 = (cse_var_2 + 35)
- let cse_var_91: int32 = (cse_var_2 + 34)
- let cse_var_90: int32 = (cse_var_2 + 33)
- let cse_var_89: int32 = (cse_var_2 + 32)
- let cse_var_88: int32 = (cse_var_2 + 3)
- let cse_var_87: int32 = (cse_var_2 + 239)
- let cse_var_86: int32 = (cse_var_2 + 238)
- let cse_var_85: int32 = (cse_var_2 + 237)
- let cse_var_84: int32 = (cse_var_2 + 236)
- let cse_var_83: int32 = (cse_var_2 + 235)
- let cse_var_82: int32 = (cse_var_2 + 234)
- let cse_var_81: int32 = (cse_var_2 + 233)
- let cse_var_80: int32 = (cse_var_2 + 232)
- let cse_var_79: int32 = (cse_var_2 + 231)
- let cse_var_78: int32 = (cse_var_2 + 230)
- let cse_var_77: int32 = (cse_var_2 + 229)
- let cse_var_76: int32 = (cse_var_2 + 228)
- let cse_var_75: int32 = (cse_var_2 + 227)
- let cse_var_74: int32 = (cse_var_2 + 226)
- let cse_var_73: int32 = (cse_var_2 + 225)
- let cse_var_72: int32 = (cse_var_2 + 224)
- let cse_var_71: int32 = (cse_var_2 + 207)
- let cse_var_70: int32 = (cse_var_2 + 206)
- let cse_var_69: int32 = (cse_var_2 + 205)
- let cse_var_68: int32 = (cse_var_2 + 204)
- let cse_var_67: int32 = (cse_var_2 + 203)
- let cse_var_66: int32 = (cse_var_2 + 202)
- let cse_var_65: int32 = (cse_var_2 + 201)
- let cse_var_64: int32 = (cse_var_2 + 200)
- let cse_var_63: int32 = (cse_var_2 + 2)
- let cse_var_62: int32 = (cse_var_2 + 199)
- let cse_var_61: int32 = (cse_var_2 + 198)
- let cse_var_60: int32 = (cse_var_2 + 197)
- let cse_var_59: int32 = (cse_var_2 + 196)
- let cse_var_58: int32 = (cse_var_2 + 195)
- let cse_var_57: int32 = (cse_var_2 + 194)
- let cse_var_56: int32 = (cse_var_2 + 193)
- let cse_var_55: int32 = (cse_var_2 + 192)
- let cse_var_54: int32 = (cse_var_2 + 175)
- let cse_var_53: int32 = (cse_var_2 + 174)
- let cse_var_52: int32 = (cse_var_2 + 173)
- let cse_var_51: int32 = (cse_var_2 + 172)
- let cse_var_50: int32 = (cse_var_2 + 171)
- let cse_var_49: int32 = (cse_var_2 + 170)
- let cse_var_48: int32 = (cse_var_2 + 169)
- let cse_var_47: int32 = (cse_var_2 + 168)
- let cse_var_46: int32 = (cse_var_2 + 167)
- let cse_var_45: int32 = (cse_var_2 + 166)
- let cse_var_44: int32 = (cse_var_2 + 165)
- let cse_var_43: int32 = (cse_var_2 + 164)
- let cse_var_42: int32 = (cse_var_2 + 163)
- let cse_var_41: int32 = (cse_var_2 + 162)
- let cse_var_40: int32 = (cse_var_2 + 161)
- let cse_var_39: int32 = (cse_var_2 + 160)
- let cse_var_38: int32 = (cse_var_2 + 15)
- let cse_var_37: int32 = (cse_var_2 + 143)
- let cse_var_36: int32 = (cse_var_2 + 142)
- let cse_var_35: int32 = (cse_var_2 + 141)
- let cse_var_34: int32 = (cse_var_2 + 140)
- let cse_var_33: int32 = (cse_var_2 + 14)
- let cse_var_32: int32 = (cse_var_2 + 139)
- let cse_var_31: int32 = (cse_var_2 + 138)
- let cse_var_30: int32 = (cse_var_2 + 137)
- let cse_var_29: int32 = (cse_var_2 + 136)
- let cse_var_28: int32 = (cse_var_2 + 135)
- let cse_var_27: int32 = (cse_var_2 + 134)
- let cse_var_26: int32 = (cse_var_2 + 133)
- let cse_var_25: int32 = (cse_var_2 + 132)
- let cse_var_24: int32 = (cse_var_2 + 131)
- let cse_var_23: int32 = (cse_var_2 + 130)
- let cse_var_22: int32 = (cse_var_2 + 13)
- let cse_var_21: int32 = (cse_var_2 + 129)
- let cse_var_20: int32 = (cse_var_2 + 128)
- let cse_var_19: int32 = (cse_var_2 + 12)
- let cse_var_18: int32 = (cse_var_2 + 111)
- let cse_var_17: int32 = (cse_var_2 + 110)
- let cse_var_16: int32 = (cse_var_2 + 11)
- let cse_var_15: int32 = (cse_var_2 + 109)
- let cse_var_14: int32 = (cse_var_2 + 108)
- let cse_var_13: int32 = (cse_var_2 + 107)
- let cse_var_12: int32 = (cse_var_2 + 106)
- let cse_var_11: int32 = (cse_var_2 + 105)
- let cse_var_10: int32 = (cse_var_2 + 104)
- let cse_var_9: int32 = (cse_var_2 + 103)
- let cse_var_8: int32 = (cse_var_2 + 102)
- let cse_var_7: int32 = (cse_var_2 + 101)
- let cse_var_6: int32 = (cse_var_2 + 100)
- let cse_var_5: int32 = (cse_var_2 + 10)
- let cse_var_4: int32 = (cse_var_2 + 1)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048))
- {
- compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(cse_var_3 + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_4] = (compute_4[cse_var_4] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_63] = (compute_4[cse_var_63] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_88] = (compute_4[cse_var_88] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_97] = (compute_4[cse_var_97] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_106] = (compute_4[cse_var_106] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_107] = (compute_4[cse_var_107] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_114] = (compute_4[cse_var_114] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_125] = (compute_4[cse_var_125] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_126] = (compute_4[cse_var_126] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_22] = (compute_4[cse_var_22] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_33] = (compute_4[cse_var_33] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_38] = (compute_4[cse_var_38] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[(cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)])], 0f32)))
- compute_4[cse_var_89] = (compute_4[cse_var_89] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_90] = (compute_4[cse_var_90] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_91] = (compute_4[cse_var_91] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_92] = (compute_4[cse_var_92] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_93] = (compute_4[cse_var_93] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_94] = (compute_4[cse_var_94] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_95] = (compute_4[cse_var_95] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_96] = (compute_4[cse_var_96] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_98] = (compute_4[cse_var_98] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_99] = (compute_4[cse_var_99] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_100] = (compute_4[cse_var_100] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_101] = (compute_4[cse_var_101] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_102] = (compute_4[cse_var_102] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_103] = (compute_4[cse_var_103] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_104] = (compute_4[cse_var_104] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_105] = (compute_4[cse_var_105] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 256)], 0f32)))
- compute_4[cse_var_108] = (compute_4[cse_var_108] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_109] = (compute_4[cse_var_109] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_110] = (compute_4[cse_var_110] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_111] = (compute_4[cse_var_111] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_112] = (compute_4[cse_var_112] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_113] = (compute_4[cse_var_113] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_115] = (compute_4[cse_var_115] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_116] = (compute_4[cse_var_116] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_117] = (compute_4[cse_var_117] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_118] = (compute_4[cse_var_118] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_119] = (compute_4[cse_var_119] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_120] = (compute_4[cse_var_120] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_121] = (compute_4[cse_var_121] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_122] = (compute_4[cse_var_122] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_123] = (compute_4[cse_var_123] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_124] = (compute_4[cse_var_124] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 512)], 0f32)))
- compute_4[cse_var_127] = (compute_4[cse_var_127] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_128] = (compute_4[cse_var_128] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_129] = (compute_4[cse_var_129] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_130] = (compute_4[cse_var_130] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 768)], 0f32)))
- compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_21] = (compute_4[cse_var_21] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_23] = (compute_4[cse_var_23] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_24] = (compute_4[cse_var_24] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_25] = (compute_4[cse_var_25] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_26] = (compute_4[cse_var_26] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_27] = (compute_4[cse_var_27] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_28] = (compute_4[cse_var_28] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_29] = (compute_4[cse_var_29] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_30] = (compute_4[cse_var_30] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_31] = (compute_4[cse_var_31] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_32] = (compute_4[cse_var_32] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_34] = (compute_4[cse_var_34] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_35] = (compute_4[cse_var_35] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_36] = (compute_4[cse_var_36] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_37] = (compute_4[cse_var_37] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1024)], 0f32)))
- compute_4[cse_var_39] = (compute_4[cse_var_39] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_40] = (compute_4[cse_var_40] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_41] = (compute_4[cse_var_41] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_42] = (compute_4[cse_var_42] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_43] = (compute_4[cse_var_43] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_44] = (compute_4[cse_var_44] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_45] = (compute_4[cse_var_45] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_46] = (compute_4[cse_var_46] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_47] = (compute_4[cse_var_47] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_48] = (compute_4[cse_var_48] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_49] = (compute_4[cse_var_49] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_50] = (compute_4[cse_var_50] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_51] = (compute_4[cse_var_51] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_52] = (compute_4[cse_var_52] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_53] = (compute_4[cse_var_53] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_54] = (compute_4[cse_var_54] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1280)], 0f32)))
- compute_4[cse_var_55] = (compute_4[cse_var_55] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_56] = (compute_4[cse_var_56] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_57] = (compute_4[cse_var_57] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_58] = (compute_4[cse_var_58] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_59] = (compute_4[cse_var_59] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_60] = (compute_4[cse_var_60] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_61] = (compute_4[cse_var_61] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_62] = (compute_4[cse_var_62] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_64] = (compute_4[cse_var_64] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_65] = (compute_4[cse_var_65] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_66] = (compute_4[cse_var_66] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_67] = (compute_4[cse_var_67] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_68] = (compute_4[cse_var_68] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_69] = (compute_4[cse_var_69] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_70] = (compute_4[cse_var_70] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_71] = (compute_4[cse_var_71] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1536)], 0f32)))
- compute_4[cse_var_72] = (compute_4[cse_var_72] + (placeholder_16[((placeholder_15[cse_var_1]*16) + cse_var_131)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_73] = (compute_4[cse_var_73] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 1)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_74] = (compute_4[cse_var_74] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 2)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_75] = (compute_4[cse_var_75] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 3)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_76] = (compute_4[cse_var_76] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 4)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_77] = (compute_4[cse_var_77] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 5)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_78] = (compute_4[cse_var_78] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 6)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_79] = (compute_4[cse_var_79] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 7)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_80] = (compute_4[cse_var_80] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 8)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_81] = (compute_4[cse_var_81] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 9)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_82] = (compute_4[cse_var_82] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 10)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_83] = (compute_4[cse_var_83] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 11)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_84] = (compute_4[cse_var_84] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 12)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_85] = (compute_4[cse_var_85] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 13)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_86] = (compute_4[cse_var_86] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 14)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
- compute_4[cse_var_87] = (compute_4[cse_var_87] + (placeholder_16[(((placeholder_15[cse_var_1]*16) + cse_var_131) + 15)]*max(placeholder_17[((cse_var_3 + placeholder_18[(placeholder_15[cse_var_1] + elem_idx)]) + 1792)], 0f32)))
+ for (i.outer.inner: int32, 0, 64) {
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [2048], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ if @tir.likely((elem_idx < (placeholder_15[(i0.outer.i1.outer.fused + 1)] - placeholder_15[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_1: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
+ compute_4[cse_var_1] = (compute_4[cse_var_1] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((i.outer.inner*512) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_132: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_132, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_132, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
+ compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_2, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -1071,7 +691,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.742 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.251 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 5589f75a5c..06ce170cce 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>00:27.982</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:58.300</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:27.947</p></td>
+<td><p>00:58.265</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 75b319fae8..b5805854eb 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, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5088019
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4256317
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)
@@ -812,9 +812,9 @@ 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, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1002025
-No: 3 GFLOPS: 210.89/210.89 result: MeasureResult(costs=(0.0010977583070175439,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1155447959899902, timestamp=1669070470.1798065) [('tile_f', [-1, 1, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9009485
-No: 4 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9207409
+No: 3 GFLOPS: 93.49/93.49 result: MeasureResult(costs=(0.0024761461886792457,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6428587436676025, timestamp=1669088249.5815248) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6016228
+No: 4 GFLOPS: 0.00/93.49 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
@@ -936,9 +936,8 @@ 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, 1, 1, 7]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8004212
-No: 5 GFLOPS: 5.40/210.89 result: MeasureResult(costs=(0.0429052085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1623175144195557, timestamp=1669070474.4587286) [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2914259
-No: 6 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8073709
+No: 5 GFLOPS: 0.00/93.49 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
@@ -1060,9 +1059,8 @@ 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, 2, 4, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4973955
-No: 7 GFLOPS: 64.79/210.89 result: MeasureResult(costs=(0.0035728547142857142,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2142045497894287, timestamp=1669070476.026077) [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5619975
-No: 8 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2350035
+No: 6 GFLOPS: 0.00/93.49 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
@@ -1184,8 +1182,8 @@ 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, 2, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1254493
-No: 9 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7882644
+No: 7 GFLOPS: 0.00/93.49 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
@@ -1307,8 +1305,9 @@ 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, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9845277
-No: 10 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5734517
+No: 8 GFLOPS: 79.99/93.49 result: MeasureResult(costs=(0.0028942559736842106,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.43855619430542, timestamp=1669088253.059729) [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,101361
+No: 9 GFLOPS: 0.00/93.49 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
@@ -1430,8 +1429,11 @@ 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, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3985151
-No: 11 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+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, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4635232
+No: 10 GFLOPS: 0.83/93.49 result: MeasureResult(costs=(0.27840701274999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.333498001098633, timestamp=1669088261.5922532) [('tile_f', [-1, 1, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10272645
+No: 11 GFLOPS: 193.58/193.58 result: MeasureResult(costs=(0.0011958714925373135,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.493093967437744, timestamp=1669088262.811639) [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8078868
+No: 12 GFLOPS: 174.00/193.58 result: MeasureResult(costs=(0.0013304507603305786,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.409214973449707, timestamp=1669088263.7386754) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9684064
+No: 13 GFLOPS: 0.00/193.58 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
@@ -1553,500 +1555,198 @@ 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, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10209975
-No: 12 GFLOPS: 0.00/210.89 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, 8, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6657683
-No: 13 GFLOPS: 0.00/210.89 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, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2118363
-No: 14 GFLOPS: 0.00/210.89 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)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3613442
+No: 14 GFLOPS: 5.32/193.58 result: MeasureResult(costs=(0.04352962475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8917021751403809, timestamp=1669088274.8652062) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5302204
+No: 15 GFLOPS: 0.00/193.58 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
+ yield remote, remote.load_module(os.path.split(build_result.filename)[1])
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
+ costs = time_f(*args).results
+ File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
+ blob = feval(*args)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
+ 4: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 3: 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
+ 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../src/runtime/rpc/rpc_module.cc:129
+ 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1012
+ 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
+ at ../src/runtime/rpc/rpc_endpoint.cc:804
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 804
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
+
+During handling of the above exception, another exception occurred:
Traceback (most recent call last):
- 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, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1917007
-No: 15 GFLOPS: 0.00/210.89 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
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
+ costs = time_f(*args).results
+ File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
+ self.gen.throw(type, value, traceback)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
+ remote.remove(build_result.filename)
+ File "/workspace/python/tvm/rpc/client.py", line 144, in remove
+ self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
+ File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
+ return self._sess.get_function(name)
+ File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCallKeywords
+ 18: _PyEval_EvalFrameDefault
+ 17: _PyFunction_FastCallKeywords
+ 16: _PyEval_EvalCodeWithName
+ 15: _PyEval_EvalFrameDefault
+ 14: 0x0000000000537c30
+ 13: _PyObject_FastCallKeywords
+ 12: 0x00007f4eb71f9fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
at ../include/tvm/runtime/packed_func.h: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
+ at ../src/runtime/rpc/rpc_endpoint.cc:684
+ File "../src/runtime/rpc/rpc_endpoint.cc", line 684
+TVMError:
+---------------------------------------------------------------
+An error occurred during the execution of TVM.
+For more information, please see: https://tvm.apache.org/docs/errors.html
+---------------------------------------------------------------
+ Check failed: (code == RPCCode::kReturn) is false: code=1
Traceback (most recent call last):
- 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, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8925918
-No: 16 GFLOPS: 0.00/210.89 result: Traceback (most recent call last):
+ 52: 0xffffffffffffffff
+ 51: _start
+ 50: __libc_start_main
+ 49: _Py_UnixMain
+ 48: 0x0000000000650da0
+ 47: 0x0000000000650afa
+ 46: _PyFunction_FastCallDict
+ 45: _PyEval_EvalCodeWithName
+ 44: _PyEval_EvalFrameDefault
+ 43: _PyFunction_FastCallKeywords
+ 42: _PyEval_EvalCodeWithName
+ 41: _PyEval_EvalFrameDefault
+ 40: _PyMethodDef_RawFastCallKeywords
+ 39: 0x0000000000546369
+ 38: _PyEval_EvalCodeWithName
+ 37: _PyEval_EvalFrameDefault
+ 36: _PyFunction_FastCallKeywords
+ 35: _PyEval_EvalCodeWithName
+ 34: _PyEval_EvalFrameDefault
+ 33: _PyFunction_FastCallDict
+ 32: _PyEval_EvalCodeWithName
+ 31: _PyEval_EvalFrameDefault
+ 30: _PyObject_FastCallDict
+ 29: 0x00000000004c06e1
+ 28: _PyFunction_FastCallDict
+ 27: _PyEval_EvalFrameDefault
+ 26: _PyMethodDescr_FastCallKeywords
+ 25: 0x00000000005dcb58
+ 24: 0x00000000005dc83f
+ 23: 0x00000000004ba127
+ 22: _PyEval_EvalFrameDefault
+ 21: _PyFunction_FastCallKeywords
+ 20: _PyEval_EvalFrameDefault
+ 19: _PyFunction_FastCall [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1166849
+No: 16 GFLOPS: 0.00/193.58 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, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9139038
+No: 17 GFLOPS: 0.00/193.58 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, 2, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9274321
+No: 18 GFLOPS: 0.00/193.58 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
@@ -2168,9 +1868,8 @@ 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4734059
-No: 17 GFLOPS: 306.99/306.99 result: MeasureResult(costs=(0.0007540923517241379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.548452138900757, timestamp=1669070479.167015) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
-No: 18 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3768184
+No: 19 GFLOPS: 0.00/193.58 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
@@ -2292,8 +1991,8 @@ 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, 128, 2, 1]), ('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, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1952737
-No: 19 GFLOPS: 0.00/306.99 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2213250
+No: 20 GFLOPS: 0.00/193.58 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
@@ -2415,8 +2114,7 @@ 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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934185
-No: 20 GFLOPS: 39.90/306.99 result: MeasureResult(costs=(0.005802182888888888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9944984912872314, timestamp=1669070479.8508644) [('tile_f', [-1, 1, 16, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,422558
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9758688
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2455,9 +2153,9 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9014299
+[('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8078868
Finish loading 20 records
-Time cost of this operator: 0.001050
+Time cost of this operator: 0.001583
</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 cd6f978aa4..f67d9559d4 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 313.2 98.621 (1, 2, 10, 10, 3) 2 1 [313.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.235 1.019 (1, 6, 10, 10) 1 1 [3.235]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.145 0.361 (1, 1, 10, 10, 3) 1 1 [1.145]
-Total_time - 317.58 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.9 98.729 (1, 2, 10, 10, 3) 2 1 [312.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.953 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 0.318 (1, 1, 10, 10, 3) 1 1 [1.008]
+Total_time - 316.929 - - - - -
</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 136.6 98.123 (1, 6, 10, 10, 1) 2 1 [136.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 1.273 (1, 6, 10, 10) 1 1 [1.772]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.605 (1, 3, 10, 10, 1) 1 1 [0.842]
-Total_time - 139.213 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.299 (1, 6, 10, 10, 1) 2 1 [102.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.785 1.691 (1, 6, 10, 10) 1 1 [1.785]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.066 1.01 (1, 3, 10, 10, 1) 1 1 [1.066]
+Total_time - 105.551 - - - - -
</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 450372afa1..e088711a38 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +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]
- 96%|#########5| 3.28M/3.42M [00:00<00:00, 34.2MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 35.0MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 85.3MB/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.
@@ -565,7 +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 2.963 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.488 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 d68d02a7ef..b72f397c87 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/tmp59_o2aft/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpwmbvasan/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/tmp59_o2aft/images/target contains 8144 images
-/tmp/tmp59_o2aft/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpwmbvasan/images/target contains 8144 images
+/tmp/tmpwmbvasan/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 - 46s - loss: 0.2390 - accuracy: 0.9168 - val_loss: 0.1144 - val_accuracy: 0.9603 - 46s/epoch - 142ms/step
+328/328 - 46s - loss: 0.2424 - accuracy: 0.9183 - val_loss: 0.1623 - val_accuracy: 0.9460 - 46s/epoch - 141ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1015 - accuracy: 0.9616 - val_loss: 0.0897 - val_accuracy: 0.9683 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0983 - accuracy: 0.9614 - val_loss: 0.1244 - val_accuracy: 0.9585 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0620 - accuracy: 0.9769 - val_loss: 0.1089 - val_accuracy: 0.9641 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.0622 - accuracy: 0.9771 - val_loss: 0.1664 - val_accuracy: 0.9498 - 43s/epoch - 130ms/step
-<keras.callbacks.History object at 0x7ff34e46da90>
+<keras.callbacks.History object at 0x7fb28649bed0>
</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 4.174 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 19.910 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 edd02607ab..8323dd54d0 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>06:09.111</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:24.133</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>04:04.174</p></td>
+<td><p>04:19.910</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>01:02.963</p></td>
+<td><p>01:02.488</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:50.170</p></td>
+<td><p>00:49.628</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.031</p></td>
+<td><p>00:08.386</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>00:03.770</p></td>
+<td><p>00:03.719</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 ef0f196c35..e35ba69a2c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.665</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.291</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.924</p></td>
+<td><p>00:31.757</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>00:10.115</p></td>
+<td><p>00:10.009</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>00:01.619</p></td>
+<td><p>00:01.518</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 0c6ffa5646..0fc1485868 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 0x7ff34cf0cef0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fb1036e9440>
</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 25081a6d2c..c0a7505ca7 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>00:06.967</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.467</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.558</p></td>
+<td><p>00:05.087</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>00:01.081</p></td>
+<td><p>00:01.067</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>00:00.568</p></td>
+<td><p>00:00.564</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.549</p></td>
+<td><p>00:00.541</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.116</p></td>
+<td><p>00:00.112</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>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index fe5f3f7ecd..7ac659fdc4 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/tmp7gcvbn52/input0.cc'\nsource_filename = \"/tmp/tmp7gcvbn52/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/tmpu1k46lw3/input0.cc'\nsource_filename = \"/tmp/tmpu1k46lw3/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 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<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"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<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="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 df086300f1..59229b4c92 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 b08b395f7c..7a1b9a4ae7 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/545f8dc92/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 35dd81dcb7..8d856b656d 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/545f8dc92/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 5e093eb2d5..f938ed500b 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/545f8dc92/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 7512ca0c6a..fac0a765ab 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/545f8dc92/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 9a064549d0..4c70a7f3a3 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/545f8dc92/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 27cf6a205d..269aea76eb 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/545f8dc92/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 552d83c66e..685c113fbd 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/545f8dc92/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 79f1c8996b..1d4ba17778 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/545f8dc92/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 7e08e7e0fa..0130295f73 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/545f8dc92/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 e0e7f46d6e..ca9125d219 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/545f8dc92/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 f86b0e3995..fb35e92717 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/545f8dc92/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 65d92ce69c..a2fb4b0ecb 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/545f8dc92/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 cadaf0d282..8587d23ae6 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/545f8dc92/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 71db3623bb..5f17d42370 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/545f8dc92/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 6190fe5e7f..9c6cfaef33 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/545f8dc92/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 f0a96baf95..f7b18ce14a 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/545f8dc92/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 b010d47335..476c25ffc3 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/545f8dc92/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 b9f3799eda..5d4c10ce8b 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/545f8dc92/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 cb0fde64b6..f2e8b277a5 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/545f8dc92/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 7d4c1d28ca..1100aafb9c 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/545f8dc92/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 9a0b6e124e..30784aea2b 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/545f8dc92/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 7e9f2ce948..25dac99457 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/545f8dc92/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 5eea978144..fe027a2ca2 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/545f8dc92/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 e57ddd0993..5064af991e 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/545f8dc92/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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/545f8dc92/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7cfa62e25/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 6ea9bf9c60..e46ffd0d84 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 c0177b36d2..dc8c2749c2 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>00:26.497</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:26.063</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>00:26.490</p></td>
+<td><p>00:26.057</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 4a71179fa4..4e19bdc39a 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 29.30s!
+resnet18_v1 inference graph built in 28.51s!
</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 c3755c11c2..5c934f0019 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 19.73s!
+yolov3-tiny inference graph built in 19.10s!
</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 24f02d8d74..403a0cd319 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>01:40.137</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:39.278</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>00:51.095</p></td>
+<td><p>00:51.030</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>00:49.042</p></td>
+<td><p>00:48.247</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 58dafe6958..e91b1d5881 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>00:03.128</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.093</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>00:02.689</p></td>
+<td><p>00:02.658</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>00:00.438</p></td>
+<td><p>00:00.435</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 e3bcfe6bb8..cff19936b1 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>00:00.757</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.776</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,7 +349,7 @@
</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>00:00.399</p></td>
+<td><p>00:00.418</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>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index c100e8cf46..fc9bb67d4a 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,7 +491,7 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
</pre></div>
</div>
</div>
@@ -580,7 +580,7 @@ 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: 93.093 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.943 ms
</pre></div>
</div>
</div>
@@ -654,7 +654,7 @@ 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 33.730 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.220 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 950023279c..46b98eb67c 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: 11.69/11.69 result: MeasureResult(costs=(0.0229614498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.550915002822876, timestamp=1669069093.9232368) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
-No: 2 GFLOPS: 0.50/11.69 result: MeasureResult(costs=(0.5346515846,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.731043100357056, timestamp=1669069102.682373) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
-No: 3 GFLOPS: 1.55/11.69 result: MeasureResult(costs=(0.1727075166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9166369438171387, timestamp=1669069106.362152) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
-No: 4 GFLOPS: 8.24/11.69 result: MeasureResult(costs=(0.032565906,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.653590202331543, timestamp=1669069107.798683) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
-No: 5 GFLOPS: 1.69/11.69 result: MeasureResult(costs=(0.1589572562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.681199312210083, timestamp=1669069110.6333787) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
-No: 6 GFLOPS: 12.19/12.19 result: MeasureResult(costs=(0.022028911800000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5019567012786865, timestamp=1669069111.910717) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
-No: 7 GFLOPS: 13.38/13.38 result: MeasureResult(costs=(0.020057455600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4962158203125, timestamp=1669069112.4011486) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
-No: 8 GFLOPS: 12.85/13.38 result: MeasureResult(costs=(0.020884536399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5327770709991455, timestamp=1669069112.9469588) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
-No: 9 GFLOPS: 0.50/13.38 result: MeasureResult(costs=(0.5390465264000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.724902391433716, timestamp=1669069121.7890291) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 10 GFLOPS: 3.21/13.38 result: MeasureResult(costs=(0.08349640439999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4820079803466797, timestamp=1669069123.291861) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+No: 1 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226330332,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6061704158782959, timestamp=1669086902.1382785) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 2 GFLOPS: 3.93/11.86 result: MeasureResult(costs=(0.06823413739999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.27858567237854, timestamp=1669086904.1286464) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+No: 3 GFLOPS: 2.00/11.86 result: MeasureResult(costs=(0.1340270294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.291276693344116, timestamp=1669086906.439967) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+No: 4 GFLOPS: 11.39/11.86 result: MeasureResult(costs=(0.0235759818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5234189033508301, timestamp=1669086907.7067509) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
+No: 5 GFLOPS: 1.22/11.86 result: MeasureResult(costs=(0.2193744502,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.64174222946167, timestamp=1669086911.6997578) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
+No: 6 GFLOPS: 8.66/11.86 result: MeasureResult(costs=(0.0309889144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8616781234741211, timestamp=1669086913.1001549) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
+No: 7 GFLOPS: 11.94/11.94 result: MeasureResult(costs=(0.022490805,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4999420642852783, timestamp=1669086913.6278863) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 8 GFLOPS: 3.17/11.94 result: MeasureResult(costs=(0.084648184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5348148345947266, timestamp=1669086915.1869886) [('tile_y', [-1, 2]), ('tile_x', [-1, 8])],None,31
+No: 9 GFLOPS: 10.60/11.94 result: MeasureResult(costs=(0.0253301342,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5456850528717041, timestamp=1669086915.9072635) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+No: 10 GFLOPS: 9.07/11.94 result: MeasureResult(costs=(0.029611005999999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6649487018585205, timestamp=1669086916.5419445) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
</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 a825f6b228..63d879e75e 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': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 514.0096369799994, 'median': 513.533555500004, 'std': 2.507549372894095}
</pre></div>
</div>
</div>
@@ -712,179 +712,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 14.02/ 18.79 GFLOPS | Progress: (4/20) | 6.98 s
-[Task 1/25] Current/Best: 22.49/ 22.49 GFLOPS | Progress: (8/20) | 11.43 s
-[Task 1/25] Current/Best: 9.25/ 23.48 GFLOPS | Progress: (12/20) | 13.62 s
-[Task 1/25] Current/Best: 17.21/ 23.48 GFLOPS | Progress: (16/20) | 16.07 s
-[Task 1/25] Current/Best: 15.13/ 23.48 GFLOPS | Progress: (20/20) | 19.10 s Done.
+[Task 1/25] Current/Best: 22.30/ 23.35 GFLOPS | Progress: (4/20) | 6.51 s
+[Task 1/25] Current/Best: 3.45/ 23.35 GFLOPS | Progress: (8/20) | 11.55 s
+[Task 1/25] Current/Best: 19.55/ 23.35 GFLOPS | Progress: (12/20) | 14.03 s
+[Task 1/25] Current/Best: 9.61/ 23.35 GFLOPS | Progress: (16/20) | 15.74 s
+[Task 1/25] Current/Best: 17.60/ 23.35 GFLOPS | Progress: (20/20) | 18.35 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 11.20/ 17.44 GFLOPS | Progress: (4/20) | 3.34 s
-[Task 2/25] Current/Best: 14.45/ 17.44 GFLOPS | Progress: (8/20) | 4.54 s
-[Task 2/25] Current/Best: 7.49/ 22.85 GFLOPS | Progress: (12/20) | 7.23 s
-[Task 2/25] Current/Best: 21.95/ 22.85 GFLOPS | Progress: (16/20) | 8.47 s
-[Task 2/25] Current/Best: 12.94/ 22.85 GFLOPS | Progress: (20/20) | 9.89 s Done.
+[Task 2/25] Current/Best: 11.81/ 15.42 GFLOPS | Progress: (4/20) | 3.07 s
+[Task 2/25] Current/Best: 12.88/ 15.42 GFLOPS | Progress: (8/20) | 4.13 s
+[Task 2/25] Current/Best: 13.60/ 18.99 GFLOPS | Progress: (12/20) | 5.68 s
+[Task 2/25] Current/Best: 13.13/ 18.99 GFLOPS | Progress: (16/20) | 7.22 s
+[Task 2/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 8.62 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 12.59/ 19.55 GFLOPS | Progress: (4/20) | 3.62 s
-[Task 3/25] Current/Best: 10.19/ 19.55 GFLOPS | Progress: (8/20) | 5.39 s
-[Task 3/25] Current/Best: 9.87/ 23.40 GFLOPS | Progress: (12/20) | 7.45 s
-[Task 3/25] Current/Best: 14.59/ 23.92 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 3/25] Current/Best: 14.21/ 23.92 GFLOPS | Progress: (20/20) | 11.41 s Done.
+[Task 3/25] Current/Best: 8.57/ 15.67 GFLOPS | Progress: (4/20) | 4.00 s
+[Task 3/25] Current/Best: 10.14/ 19.59 GFLOPS | Progress: (8/20) | 5.71 s
+[Task 3/25] Current/Best: 7.71/ 19.59 GFLOPS | Progress: (12/20) | 9.11 s
+[Task 3/25] Current/Best: 15.44/ 19.59 GFLOPS | Progress: (16/20) | 10.78 s
+[Task 3/25] Current/Best: 6.42/ 19.59 GFLOPS | Progress: (20/20) | 13.08 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 11.61/ 19.51 GFLOPS | Progress: (4/20) | 3.44 s
-[Task 4/25] Current/Best: 12.42/ 19.51 GFLOPS | Progress: (8/20) | 5.20 s
-[Task 4/25] Current/Best: 13.90/ 19.51 GFLOPS | Progress: (12/20) | 9.47 s
-[Task 4/25] Current/Best: 15.62/ 19.51 GFLOPS | Progress: (16/20) | 17.50 s
-[Task 4/25] Current/Best: 15.48/ 19.51 GFLOPS | Progress: (20/20) | 28.36 s
-[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 5/25] Current/Best: 19.33/ 23.48 GFLOPS | Progress: (4/20) | 3.62 s
-[Task 5/25] Current/Best: 5.28/ 23.48 GFLOPS | Progress: (8/20) | 5.46 s
-[Task 5/25] Current/Best: 10.84/ 23.48 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 5/25] Current/Best: 17.85/ 23.48 GFLOPS | Progress: (16/20) | 8.88 s
-[Task 5/25] Current/Best: 15.50/ 23.48 GFLOPS | Progress: (20/20) | 10.89 s Done.
+[Task 4/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (4/20) | 3.26 s
+[Task 4/25] Current/Best: 13.99/ 19.07 GFLOPS | Progress: (8/20) | 5.80 s
+[Task 4/25] Current/Best: 5.80/ 22.04 GFLOPS | Progress: (12/20) | 8.93 s
+[Task 4/25] Current/Best: 17.88/ 22.04 GFLOPS | Progress: (16/20) | 10.27 s
+[Task 4/25] Current/Best: 10.44/ 22.04 GFLOPS | Progress: (20/20) | 11.99 s Done.
+
+[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 5/25] Current/Best: 12.24/ 18.03 GFLOPS | Progress: (4/20) | 3.75 s
+[Task 5/25] Current/Best: 3.25/ 18.03 GFLOPS | Progress: (8/20) | 6.06 s
+[Task 5/25] Current/Best: 5.95/ 18.03 GFLOPS | Progress: (12/20) | 7.98 s
+[Task 5/25] Current/Best: 3.24/ 21.25 GFLOPS | Progress: (16/20) | 9.51 s
+[Task 5/25] Current/Best: 10.43/ 21.25 GFLOPS | Progress: (20/20) | 13.16 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 14.04/ 19.54 GFLOPS | Progress: (4/20) | 3.43 s
-[Task 6/25] Current/Best: 8.14/ 19.54 GFLOPS | Progress: (8/20) | 5.86 s
-[Task 6/25] Current/Best: 5.86/ 19.54 GFLOPS | Progress: (12/20) | 8.38 s
-[Task 6/25] Current/Best: 3.19/ 19.54 GFLOPS | Progress: (16/20) | 11.57 s
-[Task 6/25] Current/Best: 11.94/ 19.54 GFLOPS | Progress: (20/20) | 15.23 s Done.
+[Task 6/25] Current/Best: 5.91/ 17.13 GFLOPS | Progress: (4/20) | 3.55 s
+[Task 6/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (8/20) | 7.55 s
+[Task 6/25] Current/Best: 2.99/ 23.10 GFLOPS | Progress: (12/20) | 10.44 s
+[Task 6/25] Current/Best: 7.93/ 23.10 GFLOPS | Progress: (16/20) | 12.48 s
+[Task 6/25] Current/Best: 14.04/ 23.10 GFLOPS | Progress: (20/20) | 14.73 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.76/ 12.37 GFLOPS | Progress: (4/20) | 4.25 s
-[Task 7/25] Current/Best: 14.38/ 16.97 GFLOPS | Progress: (8/20) | 7.34 s
-[Task 7/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 9.52 s
-[Task 7/25] Current/Best: 18.18/ 19.05 GFLOPS | Progress: (16/20) | 12.42 s
-[Task 7/25] Current/Best: 12.08/ 19.05 GFLOPS | Progress: (20/20) | 14.78 s Done.
+[Task 7/25] Current/Best: 16.10/ 18.11 GFLOPS | Progress: (4/20) | 3.37 s
+[Task 7/25] Current/Best: 13.57/ 18.11 GFLOPS | Progress: (8/20) | 5.62 s
+[Task 7/25] Current/Best: 17.34/ 18.11 GFLOPS | Progress: (12/20) | 7.78 s
+[Task 7/25] Current/Best: 11.62/ 18.11 GFLOPS | Progress: (16/20) | 10.95 s
+[Task 7/25] Current/Best: 8.79/ 18.11 GFLOPS | Progress: (20/20) | 13.71 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.24/ 10.24 GFLOPS | Progress: (4/20) | 13.36 s
-[Task 8/25] Current/Best: 3.19/ 14.15 GFLOPS | Progress: (8/20) | 20.47 s
-[Task 8/25] Current/Best: 7.72/ 20.42 GFLOPS | Progress: (12/20) | 24.06 s
-[Task 8/25] Current/Best: 7.60/ 20.42 GFLOPS | Progress: (16/20) | 30.65 s
-[Task 8/25] Current/Best: 13.17/ 20.42 GFLOPS | Progress: (20/20) | 34.73 s
+[Task 8/25] Current/Best: 11.55/ 11.55 GFLOPS | Progress: (4/20) | 8.45 s
+[Task 8/25] Current/Best: 12.16/ 14.79 GFLOPS | Progress: (8/20) | 13.84 s
+[Task 8/25] Current/Best: 9.81/ 14.79 GFLOPS | Progress: (12/20) | 17.32 s
+[Task 8/25] Current/Best: 12.85/ 14.79 GFLOPS | Progress: (16/20) | 24.21 s
+[Task 8/25] Current/Best: 9.20/ 20.94 GFLOPS | Progress: (20/20) | 28.71 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 4.90/ 13.76 GFLOPS | Progress: (4/20) | 7.58 s
-[Task 9/25] Current/Best: 12.83/ 13.91 GFLOPS | Progress: (8/20) | 13.01 s
-[Task 9/25] Current/Best: 12.73/ 22.86 GFLOPS | Progress: (12/20) | 21.23 s
-[Task 9/25] Current/Best: 18.55/ 22.86 GFLOPS | Progress: (16/20) | 24.05 s
-[Task 9/25] Current/Best: 17.66/ 22.86 GFLOPS | Progress: (20/20) | 34.82 s
+[Task 9/25] Current/Best: 12.55/ 12.92 GFLOPS | Progress: (4/20) | 7.23 s
+[Task 9/25] Current/Best: 3.35/ 18.90 GFLOPS | Progress: (8/20) | 9.15 s
+[Task 9/25] Current/Best: 9.09/ 18.90 GFLOPS | Progress: (12/20) | 15.76 s
+[Task 9/25] Current/Best: 9.49/ 18.90 GFLOPS | Progress: (16/20) | 17.79 s
+[Task 9/25] Current/Best: 16.59/ 18.90 GFLOPS | Progress: (20/20) | 19.61 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 17.93/ 17.93 GFLOPS | Progress: (4/20) | 4.12 s
-[Task 10/25] Current/Best: 8.93/ 17.93 GFLOPS | Progress: (8/20) | 5.88 s
-[Task 10/25] Current/Best: 16.89/ 17.93 GFLOPS | Progress: (12/20) | 7.58 s
-[Task 10/25] Current/Best: 18.07/ 20.24 GFLOPS | Progress: (16/20) | 9.20 s
-[Task 10/25] Current/Best: 6.70/ 20.24 GFLOPS | Progress: (20/20) | 11.15 s Done.
+[Task 10/25] Current/Best: 13.35/ 18.07 GFLOPS | Progress: (4/20) | 2.86 s
+[Task 10/25] Current/Best: 10.50/ 18.07 GFLOPS | Progress: (8/20) | 4.31 s
+[Task 10/25] Current/Best: 12.30/ 18.07 GFLOPS | Progress: (12/20) | 5.86 s
+[Task 10/25] Current/Best: 16.12/ 20.15 GFLOPS | Progress: (16/20) | 7.60 s
+[Task 10/25] Current/Best: 6.03/ 22.00 GFLOPS | Progress: (20/20) | 9.11 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 9.11/ 12.69 GFLOPS | Progress: (4/20) | 3.72 s
-[Task 11/25] Current/Best: 8.33/ 21.59 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 11/25] Current/Best: 7.72/ 23.63 GFLOPS | Progress: (12/20) | 9.20 s
-[Task 11/25] Current/Best: 7.79/ 23.63 GFLOPS | Progress: (16/20) | 11.85 s
-[Task 11/25] Current/Best: 7.12/ 23.63 GFLOPS | Progress: (20/20) | 13.96 s Done.
+[Task 11/25] Current/Best: 15.74/ 16.90 GFLOPS | Progress: (4/20) | 3.16 s
+[Task 11/25] Current/Best: 15.42/ 19.91 GFLOPS | Progress: (8/20) | 5.07 s
+[Task 11/25] Current/Best: 18.14/ 19.91 GFLOPS | Progress: (12/20) | 7.35 s
+[Task 11/25] Current/Best: 21.05/ 21.14 GFLOPS | Progress: (16/20) | 9.37 s
+[Task 11/25] Current/Best: 12.69/ 21.48 GFLOPS | Progress: (20/20) | 11.14 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 9.44/ 12.43 GFLOPS | Progress: (4/20) | 4.98 s
-[Task 12/25] Current/Best: 7.29/ 16.16 GFLOPS | Progress: (8/20) | 9.93 s
-[Task 12/25] Current/Best: 9.17/ 18.54 GFLOPS | Progress: (12/20) | 14.06 s
-[Task 12/25] Current/Best: 11.69/ 18.54 GFLOPS | Progress: (16/20) | 18.09 s
-[Task 12/25] Current/Best: 8.27/ 18.54 GFLOPS | Progress: (20/20) | 21.96 s Done.
+[Task 12/25] Current/Best: 10.15/ 15.65 GFLOPS | Progress: (4/20) | 5.17 s
+[Task 12/25] Current/Best: 13.69/ 15.65 GFLOPS | Progress: (8/20) | 8.58 s
+[Task 12/25] Current/Best: 12.46/ 15.65 GFLOPS | Progress: (12/20) | 12.00 s
+[Task 12/25] Current/Best: 7.80/ 15.65 GFLOPS | Progress: (16/20) | 14.18 s
+[Task 12/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (20/20) | 16.29 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 6.03/ 12.06 GFLOPS | Progress: (4/20) | 4.63 s
-[Task 13/25] Current/Best: 9.98/ 12.06 GFLOPS | Progress: (8/20) | 7.53 s
-[Task 13/25] Current/Best: 17.34/ 17.48 GFLOPS | Progress: (12/20) | 10.26 s
-[Task 13/25] Current/Best: 7.00/ 18.85 GFLOPS | Progress: (16/20) | 12.87 s
-[Task 13/25] Current/Best: 1.57/ 19.19 GFLOPS | Progress: (20/20) | 17.32 s Done.
+[Task 13/25] Current/Best: 7.64/ 16.40 GFLOPS | Progress: (4/20) | 4.59 s
+[Task 13/25] Current/Best: 6.21/ 23.08 GFLOPS | Progress: (8/20) | 7.12 s
+[Task 13/25] Current/Best: 11.83/ 23.08 GFLOPS | Progress: (12/20) | 10.01 s
+[Task 13/25] Current/Best: 6.24/ 23.08 GFLOPS | Progress: (16/20) | 13.47 s
+[Task 13/25] Current/Best: 8.52/ 23.08 GFLOPS | Progress: (20/20) | 16.93 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 18.31/ 18.31 GFLOPS | Progress: (4/20) | 3.23 s
-[Task 14/25] Current/Best: 16.98/ 20.07 GFLOPS | Progress: (8/20) | 5.26 s
-[Task 14/25] Current/Best: 10.49/ 20.07 GFLOPS | Progress: (12/20) | 11.04 s
-[Task 14/25] Current/Best: 15.40/ 20.07 GFLOPS | Progress: (16/20) | 12.95 s
-[Task 14/25] Current/Best: 4.84/ 20.07 GFLOPS | Progress: (20/20) | 15.20 s Done.
-
+[Task 14/25] Current/Best: 5.91/ 13.77 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 14/25] Current/Best: 13.58/ 18.49 GFLOPS | Progress: (8/20) | 5.97 s
+[Task 14/25] Current/Best: 21.45/ 21.45 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 14/25] Current/Best: 1.60/ 21.45 GFLOPS | Progress: (16/20) | 13.17 s
+[Task 14/25] Current/Best: 13.59/ 21.45 GFLOPS | Progress: (20/20) | 15.36 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 3.13/ 19.20 GFLOPS | Progress: (4/20) | 5.62 s
-[Task 15/25] Current/Best: 8.56/ 19.20 GFLOPS | Progress: (8/20) | 8.88 s
-[Task 15/25] Current/Best: 11.80/ 19.20 GFLOPS | Progress: (12/20) | 12.71 s
-[Task 15/25] Current/Best: 12.40/ 19.20 GFLOPS | Progress: (16/20) | 14.23 s
-[Task 15/25] Current/Best: 19.01/ 19.20 GFLOPS | Progress: (20/20) | 20.36 s Done.
-
+[Task 15/25] Current/Best: 15.66/ 20.03 GFLOPS | Progress: (4/20) | 4.45 s
+[Task 15/25] Current/Best: 6.76/ 22.14 GFLOPS | Progress: (8/20) | 6.43 s
+[Task 15/25] Current/Best: 8.35/ 22.14 GFLOPS | Progress: (12/20) | 10.91 s
+[Task 15/25] Current/Best: 18.38/ 22.14 GFLOPS | Progress: (16/20) | 12.19 s
+[Task 15/25] Current/Best: 14.92/ 22.14 GFLOPS | Progress: (20/20) | 13.65 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 16.27/ 16.36 GFLOPS | Progress: (4/20) | 3.61 s
-[Task 16/25] Current/Best: 5.38/ 19.49 GFLOPS | Progress: (8/20) | 5.20 s Done.
+[Task 16/25] Current/Best: 12.00/ 15.02 GFLOPS | Progress: (4/20) | 3.08 s Done.
Done.
-[Task 16/25] Current/Best: 17.93/ 19.49 GFLOPS | Progress: (12/20) | 7.27 s
-[Task 16/25] Current/Best: 13.82/ 19.49 GFLOPS | Progress: (16/20) | 8.72 s
-[Task 16/25] Current/Best: 12.03/ 20.68 GFLOPS | Progress: (20/20) | 10.37 s Done.
+[Task 16/25] Current/Best: 20.73/ 20.73 GFLOPS | Progress: (8/20) | 4.35 s
+[Task 16/25] Current/Best: 5.98/ 20.97 GFLOPS | Progress: (12/20) | 6.58 s
+[Task 16/25] Current/Best: 15.07/ 20.97 GFLOPS | Progress: (16/20) | 8.51 s
+[Task 16/25] Current/Best: 2.96/ 20.97 GFLOPS | Progress: (20/20) | 10.57 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 12.68/ 20.05 GFLOPS | Progress: (4/20) | 3.37 s
-[Task 17/25] Current/Best: 11.62/ 20.05 GFLOPS | Progress: (8/20) | 7.16 s
-[Task 17/25] Current/Best: 6.16/ 22.46 GFLOPS | Progress: (12/20) | 10.55 s
-[Task 17/25] Current/Best: 14.59/ 23.13 GFLOPS | Progress: (16/20) | 12.38 s
-[Task 17/25] Current/Best: 10.42/ 23.13 GFLOPS | Progress: (20/20) | 14.50 s Done.
+[Task 17/25] Current/Best: 12.71/ 19.16 GFLOPS | Progress: (4/20) | 4.40 s
+[Task 17/25] Current/Best: 11.85/ 19.16 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 17/25] Current/Best: 4.31/ 19.16 GFLOPS | Progress: (12/20) | 10.80 s
+[Task 17/25] Current/Best: 3.09/ 19.16 GFLOPS | Progress: (16/20) | 13.35 s
+[Task 17/25] Current/Best: 6.14/ 19.58 GFLOPS | Progress: (20/20) | 15.19 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (4/20) | 3.47 s
-[Task 18/25] Current/Best: 3.11/ 21.21 GFLOPS | Progress: (8/20) | 5.68 s
-[Task 18/25] Current/Best: 14.80/ 21.21 GFLOPS | Progress: (12/20) | 7.84 s
-[Task 18/25] Current/Best: 10.90/ 21.21 GFLOPS | Progress: (16/20) | 11.63 s
-[Task 18/25] Current/Best: 15.51/ 21.21 GFLOPS | Progress: (20/20) | 13.85 s Done.
+[Task 18/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (4/20) | 3.51 s
+[Task 18/25] Current/Best: 10.17/ 20.25 GFLOPS | Progress: (8/20) | 7.09 s
+[Task 18/25] Current/Best: 5.89/ 21.14 GFLOPS | Progress: (12/20) | 8.72 s
+[Task 18/25] Current/Best: 15.33/ 21.14 GFLOPS | Progress: (16/20) | 11.80 s
+[Task 18/25] Current/Best: 10.48/ 21.14 GFLOPS | Progress: (20/20) | 17.66 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 5.31 s
-[Task 19/25] Current/Best: 10.28/ 21.30 GFLOPS | Progress: (8/20) | 10.31 s
-[Task 19/25] Current/Best: 17.77/ 21.30 GFLOPS | Progress: (12/20) | 13.93 s
-[Task 19/25] Current/Best: 11.87/ 21.30 GFLOPS | Progress: (16/20) | 16.63 s
-[Task 19/25] Current/Best: 10.07/ 21.30 GFLOPS | Progress: (20/20) | 18.59 s Done.
+[Task 19/25] Current/Best: 12.09/ 20.81 GFLOPS | Progress: (4/20) | 4.19 s
+[Task 19/25] Current/Best: 3.09/ 20.81 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 19/25] Current/Best: 11.95/ 20.81 GFLOPS | Progress: (12/20) | 10.57 s
+[Task 19/25] Current/Best: 10.89/ 20.81 GFLOPS | Progress: (16/20) | 14.44 s
+[Task 19/25] Current/Best: 11.66/ 20.81 GFLOPS | Progress: (20/20) | 17.74 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 13.30/ 16.52 GFLOPS | Progress: (4/20) | 3.39 s
-[Task 20/25] Current/Best: 15.42/ 17.94 GFLOPS | Progress: (8/20) | 5.39 s
-[Task 20/25] Current/Best: 15.57/ 18.82 GFLOPS | Progress: (12/20) | 8.01 s
-[Task 20/25] Current/Best: 16.59/ 18.82 GFLOPS | Progress: (16/20) | 10.84 s
-[Task 20/25] Current/Best: 2.24/ 18.82 GFLOPS | Progress: (20/20) | 13.72 s
+[Task 20/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (4/20) | 3.60 s
+[Task 20/25] Current/Best: 15.56/ 22.49 GFLOPS | Progress: (8/20) | 6.27 s
+[Task 20/25] Current/Best: 5.21/ 22.49 GFLOPS | Progress: (12/20) | 10.14 s
+[Task 20/25] Current/Best: 6.76/ 22.49 GFLOPS | Progress: (16/20) | 15.72 s
+[Task 20/25] Current/Best: 16.71/ 22.49 GFLOPS | Progress: (20/20) | 17.71 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 5.22/ 11.16 GFLOPS | Progress: (4/20) | 4.28 s
-[Task 21/25] Current/Best: 8.84/ 14.51 GFLOPS | Progress: (8/20) | 6.79 s
-[Task 21/25] Current/Best: 16.30/ 16.30 GFLOPS | Progress: (12/20) | 9.53 s Done.
-
-[Task 21/25] Current/Best: 11.45/ 20.16 GFLOPS | Progress: (16/20) | 11.91 s
-[Task 21/25] Current/Best: 9.53/ 20.16 GFLOPS | Progress: (20/20) | 14.02 s Done.
-
+[Task 21/25] Current/Best: 2.70/ 20.64 GFLOPS | Progress: (4/20) | 3.83 s
+[Task 21/25] Current/Best: 6.38/ 20.64 GFLOPS | Progress: (8/20) | 7.13 s
+[Task 21/25] Current/Best: 13.17/ 20.64 GFLOPS | Progress: (12/20) | 8.52 s
+[Task 21/25] Current/Best: 17.82/ 20.64 GFLOPS | Progress: (16/20) | 10.10 s
+[Task 21/25] Current/Best: 8.66/ 20.64 GFLOPS | Progress: (20/20) | 13.25 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 9.60/ 11.59 GFLOPS | Progress: (4/20) | 3.54 s
-[Task 22/25] Current/Best: 17.28/ 17.28 GFLOPS | Progress: (8/20) | 5.39 s
-[Task 22/25] Current/Best: 4.46/ 17.28 GFLOPS | Progress: (12/20) | 6.87 s
-[Task 22/25] Current/Best: 16.47/ 17.28 GFLOPS | Progress: (16/20) | 8.19 s
-[Task 22/25] Current/Best: 11.96/ 17.28 GFLOPS | Progress: (20/20) | 10.24 s Done.
+[Task 22/25] Current/Best: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 4.48 s
+[Task 22/25] Current/Best: 6.87/ 19.86 GFLOPS | Progress: (8/20) | 7.70 s
+[Task 22/25] Current/Best: 19.96/ 19.96 GFLOPS | Progress: (12/20) | 12.63 s
+[Task 22/25] Current/Best: 19.49/ 19.96 GFLOPS | Progress: (16/20) | 14.16 s
+[Task 22/25] Current/Best: 5.20/ 19.96 GFLOPS | Progress: (20/20) | 16.16 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 10.50/ 10.50 GFLOPS | Progress: (4/20) | 4.67 s
-[Task 23/25] Current/Best: 13.42/ 16.38 GFLOPS | Progress: (8/20) | 7.15 s
-[Task 23/25] Current/Best: 9.81/ 16.38 GFLOPS | Progress: (12/20) | 10.47 s
-[Task 23/25] Current/Best: 9.80/ 18.98 GFLOPS | Progress: (16/20) | 12.89 s
-[Task 23/25] Current/Best: 8.33/ 18.98 GFLOPS | Progress: (20/20) | 15.21 s Done.
+[Task 23/25] Current/Best: 12.96/ 21.02 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 23/25] Current/Best: 20.66/ 21.02 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 23/25] Current/Best: 19.74/ 21.02 GFLOPS | Progress: (12/20) | 9.99 s
+[Task 23/25] Current/Best: 12.20/ 22.75 GFLOPS | Progress: (16/20) | 12.86 s
+[Task 23/25] Current/Best: 21.49/ 22.75 GFLOPS | Progress: (20/20) | 18.15 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 7.90/ 8.24 GFLOPS | Progress: (4/20) | 12.27 s
-[Task 24/25] Current/Best: 9.93/ 9.93 GFLOPS | Progress: (8/20) | 22.97 s
-[Task 24/25] Current/Best: 3.74/ 9.93 GFLOPS | Progress: (12/20) | 33.71 s
-[Task 24/25] Current/Best: 3.94/ 9.93 GFLOPS | Progress: (16/20) | 44.41 s
-[Task 24/25] Current/Best: 1.71/ 9.93 GFLOPS | Progress: (20/20) | 54.91 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25] Current/Best: 3.02/ 3.02 GFLOPS | Progress: (4/20) | 12.98 s
-[Task 25/25] Current/Best: 3.04/ 9.07 GFLOPS | Progress: (8/20) | 18.78 s
-[Task 25/25] Current/Best: 7.75/ 9.07 GFLOPS | Progress: (12/20) | 19.82 s
-[Task 25/25] Current/Best: 1.54/ 9.07 GFLOPS | Progress: (16/20) | 30.55 s
-[Task 25/25] Current/Best: 1.55/ 9.29 GFLOPS | Progress: (20/20) | 35.59 s
+[Task 24/25] Current/Best: 10.67/ 10.67 GFLOPS | Progress: (4/20) | 12.17 s Done.
+ Done.
+
+[Task 24/25] Current/Best: 3.21/ 10.67 GFLOPS | Progress: (8/20) | 23.22 s
+[Task 24/25] Current/Best: 8.55/ 10.67 GFLOPS | Progress: (12/20) | 24.93 s
+[Task 24/25] Current/Best: 10.61/ 10.67 GFLOPS | Progress: (16/20) | 35.38 s
+[Task 24/25] Current/Best: 1.38/ 10.67 GFLOPS | Progress: (20/20) | 47.28 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 6.40/ 6.40 GFLOPS | Progress: (4/20) | 12.18 s
+[Task 25/25] Current/Best: 2.83/ 9.36 GFLOPS | Progress: (8/20) | 15.10 s
+[Task 25/25] Current/Best: 6.74/ 9.36 GFLOPS | Progress: (12/20) | 24.56 s
+[Task 25/25] Current/Best: 3.01/ 9.36 GFLOPS | Progress: (16/20) | 27.19 s
+[Task 25/25] Current/Best: 4.28/ 9.36 GFLOPS | Progress: (20/20) | 37.92 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +944,8 @@ 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=0.356377
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +982,8 @@ 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': 416.1014501600016, 'median': 415.50952905000713, 'std': 4.321109686634458}
-unoptimized: {'mean': 515.2991086700013, 'median': 515.4468862500039, 'std': 0.9121252091298173}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 413.7397979600041, 'median': 412.7553719000048, 'std': 4.334746790432081}
+unoptimized: {'mean': 514.0096369799994, 'median': 513.533555500004, 'std': 2.507549372894095}
</pre></div>
</div>
</div>
@@ -998,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 28.828 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 42.113 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 d0d6f19df0..eb82c3db61 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>1.25e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.222e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 86d9a96cf4..07415540f9 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, 0x8a10b00)), stage(b, placeholder(b, 0x2399d1b0)), 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 [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x220e1dc0)), stage(b, placeholder(b, 0x220b6320)), 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=[ [...]
</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 1164acd295..80a06c0274 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>15:11.609</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:09.492</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:28.828</p></td>
+<td><p>10:42.113</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>01:33.730</p></td>
+<td><p>01:31.220</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:59.170</p></td>
+<td><p>01:01.399</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:33.794</p></td>
+<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>00:33.563</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:33.784</p></td>
+<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>00:18.717</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.355</p></td>
+<td><p>00:01.543</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
@@ -377,7 +377,7 @@
<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>00:00.176</p></td>
+<td><p>00:00.168</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>
@@ -385,18 +385,18 @@
<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>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="install.html#sphx-glr-tutorial-install-py"><span class="std std-ref">Installing TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">install.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.001</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="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 b15de9a5ce..350174aa74 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,7 +551,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000007
</pre></div>
</div>
@@ -639,7 +639,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000046
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
@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, [n: int32], [stride: int32], type="auto"),
@@ -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 7.813590000296245e-06 1.0
- naive 6.7472e-06 0.8635211215003842
-parallel 6.9564e-06 0.8902949860097925
- vector 4.60098e-05 5.888432845626093
+ numpy 7.007709998561041e-06 1.0
+ naive 6.9286e-06 0.9887110056527332
+parallel 7.2283e-06 1.0314781863810367
+ vector 2.45875e-05 3.5086354893465606
</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: 0.018505
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018952
</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: 3.251925
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.453091
</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: 0.306264
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.289743
</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: 0.341208
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.330403
@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: 0.119167
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.114389
@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: 0.110721
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108428
@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: 0.111180
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.115082
@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: 0.146938
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.151680
@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 3.2519253935 1.0
- blocking 0.30626426110000005 0.09417936269760858
- vectorization 0.3412077699 0.10492484562592103
-loop permutation 0.1191673078 0.036645154294804395
- array packing 0.1107214522 0.034047968142600006
- block caching 0.11117954749999999 0.03418883708778419
- parallelization 0.1469377231 0.04518483830954469
+ none 3.4530912585999998 1.0
+ blocking 0.2897431765 0.08390834611694326
+ vectorization 0.3304027778 0.09568318734036484
+loop permutation 0.1143893309 0.033126645759827766
+ array packing 0.10842805429999999 0.031400286346315795
+ block caching 0.11508194040000001 0.03332722241654804
+ parallelization 0.1516800285 0.043925867328944046
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,6 +1520,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.399 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>