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 2022/11/05 00:49:59 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@be44e9c811c071f01f66002729b8a9cb356a3adf)
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 0229239771 deploying docs (apache/tvm@be44e9c811c071f01f66002729b8a9cb356a3adf)
0229239771 is described below
commit 022923977198edc83f2e672d6ad4bc7aaaf55341
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Nov 5 00:49:53 2022 +0000
deploying docs (apache/tvm@be44e9c811c071f01f66002729b8a9cb356a3adf)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 332113 -> 324216 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23380 -> 23634 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 | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 4 +-
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 591 +++------------------
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 310 +++++++++--
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 62 +--
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 43 +-
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 | 14 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 29 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 591 +++------------------
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 310 +++++++++--
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 272 +++++-----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 39 +-
125 files changed, 1488 insertions(+), 1913 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 0fd9c0ef04..58230570fb 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 2b4fe4d842..c7f45c5bc4 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 cd2db60c0b..1f8010c07b 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 11.861 seconds)
+ **Total running time of the script:** ( 1 minutes 13.776 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 c6182cf3f8..35ff6fe2ee 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 950ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 958ms/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 9c640694d8..a2de4bee9a 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.zipe232925d-da3c-4a18-bed2-a6d0928c330f from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip678a38c4-50bd-43f1-83f9-b8730d823e78 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 d4c1e1dce3..69fef6c322 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]
16%|#5 | 6.57M/41.5M [00:00<00:00, 68.8MB/s]
32%|###1 | 13.1M/41.5M [00:00<00:00, 66.9MB/s]
47%|####7 | 19.5M/41.5M [00:00<00:00, 51.7MB/s]
60%|#####9 | 24.8M/41.5M [00:00<00:00, 24.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.5MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 59.9MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 58.6MB/s]
51%|##### | 21.1M/41.5M [00:00<00:00, 63.8MB/s]
66%|######5 | 27.3M/41.5M [00:00<00:00, 41.3MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 42.8MB/s]
90%|########9 | 37.2M/41.5M [00:00<00:00, 40.9MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 45.8MB/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 4176982ed7..c2d263eac8 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%|#8 | 8.41M/44.7M [00:00<00:00, 88.1MB/s]
48%|####8 | 21.6M/44.7M [00:00<00:00, 118MB/s]
74%|#######3 | 32.8M/44.7M [00:00<00:00, 88.5MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 94.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 95.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
23%|##2 | 10.1M/44.7M [00:00<00:00, 86.2MB/s]
58%|#####7 | 25.8M/44.7M [00:00<00:00, 129MB/s]
86%|########5 | 38.4M/44.7M [00:00<00:00, 114MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/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 69b5d31303..0e29644595 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 10.844 seconds)
+ **Total running time of the script:** ( 1 minutes 12.883 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 c5624cda92..4f0e17b9a6 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
=================
-**05:45.577** total execution time for **how_to_compile_models** files:
+**05:55.698** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.861 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:13.776 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:12.883 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.874 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:47.725 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.532 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.578 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.407 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.996 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.987 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.567 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.445 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.968 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.190 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.197 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:18.537 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.394 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.470 | 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 7c20e10c4e..4af3743be1 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
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3996 16.5399 16.8385 15.7575 0.3918
+ 16.7843 16.7883 17.2602 16.2491 0.4103
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 21af748b2e..044db75e3b 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]
9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
18%|#7 | 30.0M/170M [00:00<00:01, 108MB/s]
24%|##4 | 41.1M/170M [00:00<00:01, 108MB/s]
31%|### | 51.9M/170M [00:00<00:01, 94.9MB/s]
36%|###6 | 61.4M/170M [00:00<00:01, 66.6MB/s]
45%|####4 | 76.2M/170M [00:00<00:01, 86.7MB/s]
56%|#####5 | 94.7M/170M [00:00<00:00, 113MB/s]
64%|######4 | 109M/170M [00:01<00:00, 121MB/s]
72%|#######1 | 122M/170M [00:01<00:00, 97.5MB/s]
79%|#######9 | 134M/170M [00:01<00:00, 98.5MB/s]
87%|########7 | 148M/170M [00:01<00:00, 91.9MB/s]
99%|#########8| 168M/170M [00:01<00:00, 117MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|5 | 9.00M/170M [00:00<00:01, 94.4MB/s]
13%|#3 | 22.8M/170M [00:00<00:01, 124MB/s]
20%|## | 34.6M/170M [00:00<00:01, 101MB/s]
28%|##7 | 47.4M/170M [00:00<00:01, 112MB/s]
34%|###4 | 58.6M/170M [00:00<00:01, 106MB/s]
41%|#### | 68.9M/170M [00:00<00:00, 106MB/s]
47%|####6 | 79.2M/170M [00:00<00:00, 97.7MB/s]
53%|#####3 | 90.8M/170M [00:00<00:00, 104MB/s]
59%|#####9 | 101M/170M [00:01<00:00, 103MB/s]
65%|######5 | 111M/170M [00:01<00:00, 102MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 101MB/s]
77%|#######6 | 131M/170M [00:01<00:00, 99.8MB/s]
83%|########2 | 141M/170M [00:01<00:00, 102MB/s]
89%|########8 | 150M/170M [00:01<00:00, 95.7MB/s]
95%|#########5| 162M/170M [00:01<00:00, 102MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/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 14.701 seconds)
+ **Total running time of the script:** ( 3 minutes 24.617 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 1b49fde6ad..394bae4ece 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]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 66.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 80.5MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
65%|######4 | 8.80M/13.6M [00:00<00:00, 92.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 117MB/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)
- 90.5992 90.5281 95.1870 90.2380 0.4903
+ 90.5063 90.3367 93.3010 90.1649 0.4937
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.201 seconds)
+ **Total running time of the script:** ( 1 minutes 8.490 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 117ed86fa8..e4c6879837 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)
- 120.1178 119.9952 125.3989 119.3251 0.6637
+ 120.9338 120.8854 123.2581 120.0275 0.4833
@@ -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 22.886 seconds)
+ **Total running time of the script:** ( 2 minutes 34.418 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 6b44fa563d..aff82906d4 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 35.136 seconds)
+ **Total running time of the script:** ( 1 minutes 35.418 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 16779a3579..68f706ade5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6073/132723 [00:00<00:02, 60726.00KB/s]
11%|# | 14266/132723 [00:00<00:01, 73191.15KB/s]
16%|#6 | 21586/132723 [00:00<00:01, 63785.78KB/s]
22%|##2 | 29818/132723 [00:00<00:01, 70500.02KB/s]
28%|##7 | 37004/132723 [00:00<00:01, 69388.81KB/s]
34%|###4 | 45227/132723 [00:00<00:01, 73532.01KB/s]
40%|###9 | 52659/132723 [00:00<00:01, 68612.56KB/s]
46%|####5 | 60890/132723 [00:00<00:00, 72652.91KB/s]
52%|#####2 | 69047/132723 [00:00<00:00, 75294.74KB/s]
58%|#####8 | 77304/132723 [00:01<00:00, 77455.29KB/s]
64%|######4 | 85116/132723 [00:01<00:00, 74894.97KB/s]
70%|####### | 93223/132723 [00:01<00:00, 76692.38KB/s]
76%|#######6 | 101429/132723 [00:01<00:00, 78267.18KB/s]
83%|########2 | 109560/132723 [00:01<00:00, 79164.39KB/s]
89%|########8 | 117769/132723 [00:01<00:00, 80031.60KB/s]
95%|########
#4| 126032/132723 [00:01<00:00, 80794.05KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74773.55KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6164/132723 [00:00<00:02, 61632.71KB/s]
11%|# | 14563/132723 [00:00<00:01, 74775.18KB/s]
17%|#6 | 22041/132723 [00:00<00:01, 56413.55KB/s]
23%|##2 | 30449/132723 [00:00<00:01, 65533.97KB/s]
29%|##9 | 38900/132723 [00:00<00:01, 71608.79KB/s]
36%|###5 | 47440/132723 [00:00<00:01, 75935.22KB/s]
42%|####1 | 55302/132723 [00:00<00:01, 73055.67KB/s]
47%|####7 | 62802/132723 [00:00<00:01, 62271.94KB/s]
53%|#####2 | 69892/132723 [00:01<00:00, 64544.12KB/s]
59%|#####9 | 78446/132723 [00:01<00:00, 70284.40KB/s]
66%|######5 | 86979/132723 [00:01<00:00, 74509.74KB/s]
72%|#######1 | 95553/132723 [00:01<00:00, 77722.67KB/s]
78%|#######8 | 104138/132723 [00:01<00:00, 80080.06KB/s]
85%|########4 | 112659/132723 [00:01<00:00, 81581.73KB/s]
91%|#########1| 120916/132723 [00:01<00:00, 78810.44KB/s]
97%|########
#7| 129357/132723 [00:01<00:00, 80424.65KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72815.76KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 59.158 seconds)
+ **Total running time of the script:** ( 3 minutes 7.759 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 9185896348..9776f9aacb 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
=================
-**12:43.650** total execution time for **how_to_deploy_models** files:
+**13:21.195** 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``) | 03:14.701 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:24.617 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:59.158 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.759 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:22.886 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:34.418 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.136 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:35.418 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.201 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.490 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.965 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:37.931 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.957 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.574 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.640 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.982 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 fffde0d31c..f30bae1603 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.zipd5949416-3aab-4080-b5de-b79dd81af330 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7345efd8-eac1-43d9-a3f9-0167c607efcb 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 3dd161b275..b0227f32a1 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
=================
-**00:47.430** total execution time for **how_to_extend_tvm** files:
+**00:48.148** 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``) | 00:43.996 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:44.593 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.405 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.472 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.075 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 295b2176e2..46059d0418 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: 6658us [6658us] (46.18%; 46.18%)
- FoldScaleAxis: 7759us [5us] (53.82%; 53.82%)
- FoldConstant: 7753us [1594us] (53.78%; 99.93%)
- InferType: 6159us [6159us] (42.72%; 79.44%)
+ InferType: 7025us [7025us] (46.70%; 46.70%)
+ FoldScaleAxis: 8017us [8us] (53.30%; 53.30%)
+ FoldConstant: 8010us [1610us] (53.25%; 99.90%)
+ InferType: 6400us [6400us] (42.54%; 79.90%)
@@ -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: 6256us [6256us] (44.66%; 44.66%)
- FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
- FoldConstant: 7747us [1624us] (55.31%; 99.94%)
- InferType: 6123us [6123us] (43.71%; 79.03%)
+ InferType: 6450us [6450us] (44.74%; 44.74%)
+ FoldScaleAxis: 7968us [6us] (55.26%; 55.26%)
+ FoldConstant: 7962us [1637us] (55.22%; 99.93%)
+ InferType: 6325us [6325us] (43.87%; 79.44%)
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 16ac321e06..6d8ad64bdd 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: 35.942497 ms
+ Convolution: 54.122657 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 03270725a1..44d09a0501 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
@@ -659,7 +659,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.026060 ms
+ conv2d with tensor core: 11.888048 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 8872d5265e..e09f919952 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: 0.018568
- Baseline: 3.441783
+ Numpy running time: 0.019520
+ Baseline: 3.272778
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296655
+ Opt1: 0.329867
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.331357
+ Opt2: 0.351991
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115943
+ Opt3: 0.124557
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109887
+ Opt4: 0.110050
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112823
+ Opt5: 0.112547
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147258
+ Opt6: 0.147820
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 068599152f..4b657e2bdd 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
=================
-**00:34.862** total execution time for **how_to_optimize_operators** files:
+**00:35.347** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.351 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.717 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.458 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.460 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.054 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.170 | 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 71ddf30929..416e393f7c 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
=================
-**08:59.762** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:12.525** 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``) | 05:32.526 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:41.227 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.468 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:34.407 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:03.203 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.585 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.524 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.369 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.928 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.364 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.573 | 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 28c36a091e..64b99f15a0 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
@@ -771,7 +771,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.367 ms
+ Execution time of this operator: 0.350 ms
@@ -1378,7 +1378,7 @@ 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 32.526 seconds)
+ **Total running time of the script:** ( 5 minutes 41.227 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 a39e0da216..ea94d8d43e 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)
- 8.1633 8.1624 8.1698 8.1577 0.0050
+ 8.2170 8.2206 8.2239 8.2064 0.0076
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.203 seconds)
+ **Total running time of the script:** ( 1 minutes 4.585 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 2aad4a086d..d96f1d06fc 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)
- 762.6226 762.3649 764.3096 761.1933 1.2852
+ 756.7097 756.4098 757.4577 756.2616 0.5324
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.468 seconds)
+ **Total running time of the script:** ( 1 minutes 34.407 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 2cf12805f6..66c3c4e0be 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,527 +386,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- compute_5: Buffer(compute_4, float32, [128], [])[0] = 0f32
- compute_5[1] = 0f32
- compute_5[2] = 0f32
- compute_5[3] = 0f32
- compute_5[4] = 0f32
- compute_5[5] = 0f32
- compute_5[6] = 0f32
- compute_5[7] = 0f32
- compute_5[8] = 0f32
- compute_5[9] = 0f32
- compute_5[10] = 0f32
- compute_5[11] = 0f32
- compute_5[12] = 0f32
- compute_5[13] = 0f32
- compute_5[14] = 0f32
- compute_5[15] = 0f32
- compute_5[16] = 0f32
- compute_5[17] = 0f32
- compute_5[18] = 0f32
- compute_5[19] = 0f32
- compute_5[20] = 0f32
- compute_5[21] = 0f32
- compute_5[22] = 0f32
- compute_5[23] = 0f32
- compute_5[24] = 0f32
- compute_5[25] = 0f32
- compute_5[26] = 0f32
- compute_5[27] = 0f32
- compute_5[28] = 0f32
- compute_5[29] = 0f32
- compute_5[30] = 0f32
- compute_5[31] = 0f32
- compute_5[32] = 0f32
- compute_5[33] = 0f32
- compute_5[34] = 0f32
- compute_5[35] = 0f32
- compute_5[36] = 0f32
- compute_5[37] = 0f32
- compute_5[38] = 0f32
- compute_5[39] = 0f32
- compute_5[40] = 0f32
- compute_5[41] = 0f32
- compute_5[42] = 0f32
- compute_5[43] = 0f32
- compute_5[44] = 0f32
- compute_5[45] = 0f32
- compute_5[46] = 0f32
- compute_5[47] = 0f32
- compute_5[48] = 0f32
- compute_5[49] = 0f32
- compute_5[50] = 0f32
- compute_5[51] = 0f32
- compute_5[52] = 0f32
- compute_5[53] = 0f32
- compute_5[54] = 0f32
- compute_5[55] = 0f32
- compute_5[56] = 0f32
- compute_5[57] = 0f32
- compute_5[58] = 0f32
- compute_5[59] = 0f32
- compute_5[60] = 0f32
- compute_5[61] = 0f32
- compute_5[62] = 0f32
- compute_5[63] = 0f32
- compute_5[64] = 0f32
- compute_5[65] = 0f32
- compute_5[66] = 0f32
- compute_5[67] = 0f32
- compute_5[68] = 0f32
- compute_5[69] = 0f32
- compute_5[70] = 0f32
- compute_5[71] = 0f32
- compute_5[72] = 0f32
- compute_5[73] = 0f32
- compute_5[74] = 0f32
- compute_5[75] = 0f32
- compute_5[76] = 0f32
- compute_5[77] = 0f32
- compute_5[78] = 0f32
- compute_5[79] = 0f32
- compute_5[80] = 0f32
- compute_5[81] = 0f32
- compute_5[82] = 0f32
- compute_5[83] = 0f32
- compute_5[84] = 0f32
- compute_5[85] = 0f32
- compute_5[86] = 0f32
- compute_5[87] = 0f32
- compute_5[88] = 0f32
- compute_5[89] = 0f32
- compute_5[90] = 0f32
- compute_5[91] = 0f32
- compute_5[92] = 0f32
- compute_5[93] = 0f32
- compute_5[94] = 0f32
- compute_5[95] = 0f32
- compute_5[96] = 0f32
- compute_5[97] = 0f32
- compute_5[98] = 0f32
- compute_5[99] = 0f32
- compute_5[100] = 0f32
- compute_5[101] = 0f32
- compute_5[102] = 0f32
- compute_5[103] = 0f32
- compute_5[104] = 0f32
- compute_5[105] = 0f32
- compute_5[106] = 0f32
- compute_5[107] = 0f32
- compute_5[108] = 0f32
- compute_5[109] = 0f32
- compute_5[110] = 0f32
- compute_5[111] = 0f32
- compute_5[112] = 0f32
- compute_5[113] = 0f32
- compute_5[114] = 0f32
- compute_5[115] = 0f32
- compute_5[116] = 0f32
- compute_5[117] = 0f32
- compute_5[118] = 0f32
- compute_5[119] = 0f32
- compute_5[120] = 0f32
- compute_5[121] = 0f32
- compute_5[122] = 0f32
- compute_5[123] = 0f32
- compute_5[124] = 0f32
- compute_5[125] = 0f32
- compute_5[126] = 0f32
- compute_5[127] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[0] = (compute_5[0] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[1] = (compute_5[1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[2] = (compute_5[2] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[3] = (compute_5[3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[4] = (compute_5[4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[5] = (compute_5[5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[6] = (compute_5[6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[7] = (compute_5[7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[8] = (compute_5[8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[9] = (compute_5[9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[10] = (compute_5[10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[11] = (compute_5[11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[12] = (compute_5[12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[13] = (compute_5[13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[14] = (compute_5[14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[15] = (compute_5[15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[16] = (compute_5[16] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[17] = (compute_5[17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[18] = (compute_5[18] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[19] = (compute_5[19] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[20] = (compute_5[20] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[21] = (compute_5[21] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[22] = (compute_5[22] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[23] = (compute_5[23] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[24] = (compute_5[24] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[25] = (compute_5[25] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[26] = (compute_5[26] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[27] = (compute_5[27] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[28] = (compute_5[28] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[29] = (compute_5[29] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[30] = (compute_5[30] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[31] = (compute_5[31] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[32] = (compute_5[32] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[33] = (compute_5[33] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[34] = (compute_5[34] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[35] = (compute_5[35] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[36] = (compute_5[36] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[37] = (compute_5[37] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[38] = (compute_5[38] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[39] = (compute_5[39] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[40] = (compute_5[40] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[41] = (compute_5[41] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[42] = (compute_5[42] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[43] = (compute_5[43] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[44] = (compute_5[44] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[45] = (compute_5[45] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[46] = (compute_5[46] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[47] = (compute_5[47] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[48] = (compute_5[48] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[49] = (compute_5[49] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[50] = (compute_5[50] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[51] = (compute_5[51] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[52] = (compute_5[52] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[53] = (compute_5[53] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[54] = (compute_5[54] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[55] = (compute_5[55] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[56] = (compute_5[56] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[57] = (compute_5[57] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[58] = (compute_5[58] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[59] = (compute_5[59] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[60] = (compute_5[60] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[61] = (compute_5[61] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[62] = (compute_5[62] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[63] = (compute_5[63] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[64] = (compute_5[64] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[65] = (compute_5[65] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[66] = (compute_5[66] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[67] = (compute_5[67] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[68] = (compute_5[68] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[69] = (compute_5[69] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[70] = (compute_5[70] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[71] = (compute_5[71] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[72] = (compute_5[72] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[73] = (compute_5[73] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[74] = (compute_5[74] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[75] = (compute_5[75] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[76] = (compute_5[76] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[77] = (compute_5[77] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[78] = (compute_5[78] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[79] = (compute_5[79] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[80] = (compute_5[80] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[81] = (compute_5[81] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[82] = (compute_5[82] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[83] = (compute_5[83] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[84] = (compute_5[84] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[85] = (compute_5[85] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[86] = (compute_5[86] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[87] = (compute_5[87] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[88] = (compute_5[88] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[89] = (compute_5[89] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[90] = (compute_5[90] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[91] = (compute_5[91] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[92] = (compute_5[92] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[93] = (compute_5[93] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[94] = (compute_5[94] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[95] = (compute_5[95] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[96] = (compute_5[96] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[97] = (compute_5[97] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[98] = (compute_5[98] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[99] = (compute_5[99] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[100] = (compute_5[100] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[101] = (compute_5[101] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[102] = (compute_5[102] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[103] = (compute_5[103] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[104] = (compute_5[104] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[105] = (compute_5[105] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[106] = (compute_5[106] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[107] = (compute_5[107] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[108] = (compute_5[108] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[109] = (compute_5[109] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[110] = (compute_5[110] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[111] = (compute_5[111] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[112] = (compute_5[112] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[113] = (compute_5[113] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[114] = (compute_5[114] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[115] = (compute_5[115] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[116] = (compute_5[116] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[117] = (compute_5[117] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[118] = (compute_5[118] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[119] = (compute_5[119] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[120] = (compute_5[120] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[121] = (compute_5[121] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[122] = (compute_5[122] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[123] = (compute_5[123] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[124] = (compute_5[124] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[125] = (compute_5[125] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[126] = (compute_5[126] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[127] = (compute_5[127] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ }
+ }
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_1: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_1, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_1, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -962,7 +513,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.699 ms
+ Execution time of this operator: 1.867 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 9e0951e2f9..fea83f7082 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:34.526** total execution time for **how_to_tune_with_autotvm** files:
+**00:42.673** 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``) | 00:34.489 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:42.637 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.007 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
++--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 0f0553f711..aa21674f70 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
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 52.03/52.03 result: MeasureResult(costs=(0.00444939392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1304433345794678, timestamp=1667601805.408173) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,652190
- No: 2 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ No: 1 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -388,8 +387,9 @@ 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, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7734574
- No: 3 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9151438
+ No: 2 GFLOPS: 5.35/5.35 result: MeasureResult(costs=(0.04331021475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.208069086074829, timestamp=1667603786.1221526) [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4137466
+ No: 3 GFLOPS: 0.00/5.35 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
@@ -511,8 +511,8 @@ 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, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7832639
- No: 4 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9510308
+ No: 4 GFLOPS: 0.00/5.35 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
@@ -634,8 +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, 64, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7281042
- No: 5 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,938070
+ No: 5 GFLOPS: 0.00/5.35 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
@@ -757,8 +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, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6032563
- No: 6 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4164494
+ No: 6 GFLOPS: 0.00/5.35 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
@@ -880,8 +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, 32, 4]), ('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', 1500), ('unroll_explicit', 0)],None,4588891
- No: 7 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8838442
+ No: 7 GFLOPS: 0.00/5.35 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
@@ -1003,9 +1003,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10015472
- No: 8 GFLOPS: 41.42/52.03 result: MeasureResult(costs=(0.005589530499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621019124984741, timestamp=1667601811.0111692) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850626
- No: 9 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1267715
+ No: 8 GFLOPS: 0.00/5.35 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
@@ -1127,8 +1126,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('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', 512), ('unroll_explicit', 1)],None,8572150
- No: 10 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3923526
+ No: 9 GFLOPS: 0.00/5.35 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
@@ -1250,8 +1249,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10334589
- No: 11 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3415624
+ No: 10 GFLOPS: 0.00/5.35 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
@@ -1373,13 +1372,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1414509
- No: 12 GFLOPS: 6.99/52.03 result: MeasureResult(costs=(0.033106311750000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4201440811157227, timestamp=1667601813.6674936) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8875092
- No: 13 GFLOPS: 3.77/52.03 result: MeasureResult(costs=(0.06132851025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.819613695144653, timestamp=1667601818.6682076) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6983210
- No: 14 GFLOPS: 124.47/124.47 result: MeasureResult(costs=(0.0018598417962962961,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4296081066131592, timestamp=1667601819.3106053) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2724816
- No: 15 GFLOPS: 75.91/124.47 result: MeasureResult(costs=(0.003049750333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5480942726135254, timestamp=1667601819.9488645) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9891422
- No: 16 GFLOPS: 292.09/292.09 result: MeasureResult(costs=(0.0007925611317829458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8134474754333496, timestamp=1667601820.614421) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
- No: 17 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4663394
+ No: 11 GFLOPS: 96.28/96.28 result: MeasureResult(costs=(0.0024043351904761904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.108785390853882, timestamp=1667603791.5522077) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7043327
+ No: 12 GFLOPS: 263.47/263.47 result: MeasureResult(costs=(0.0008786647912087911,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3370120525360107, timestamp=1667603792.477356) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3684274
+ No: 13 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1501,9 +1497,9 @@ 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, 8, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9800932
- No: 18 GFLOPS: 10.11/292.09 result: MeasureResult(costs=(0.022908447166666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7610547542572021, timestamp=1667601822.5637784) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5355174
- No: 19 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3020507
+ No: 14 GFLOPS: 70.59/263.47 result: MeasureResult(costs=(0.0032796786458333337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.527655124664307, timestamp=1667603801.1912084) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9201943
+ No: 15 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1625,8 +1621,256 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2966493
- No: 20 GFLOPS: 30.46/292.09 result: MeasureResult(costs=(0.0075998355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.213226318359375, timestamp=1667601823.2526355) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3484859
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9789138
+ No: 16 GFLOPS: 22.24/263.47 result: MeasureResult(costs=(0.0104088668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1757991313934326, timestamp=1667603801.9348376) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7948247
+ No: 17 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1714464
+ No: 18 GFLOPS: 20.63/263.47 result: MeasureResult(costs=(0.011222229,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.527989149093628, timestamp=1667603805.6439786) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5112599
+ No: 19 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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, 1, 4, 64]), ('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', 0), ('unroll_explicit', 1)],None,5722627
+ No: 20 GFLOPS: 511.07/511.07 result: MeasureResult(costs=(0.00045297245480225987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3503856658935547, timestamp=1667603806.6087162) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,40934
@@ -1681,9 +1925,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
+ [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,40934
Finish loading 20 records
- Time cost of this operator: 0.001197
+ Time cost of this operator: 0.000806
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 4ee45bd183..b14051e24e 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 310.0 98.727 (1, 2, 10, 10, 3) 2 1 [310.0]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.022 0.962 (1, 6, 10, 10) 1 1 [3.022]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
- Total_time - 313.997 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.5 98.718 (1, 2, 10, 10, 3) 2 1 [310.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.06 0.973 (1, 6, 10, 10) 1 1 [3.06]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.309 (1, 1, 10, 10, 3) 1 1 [0.973]
+ Total_time - 314.533 - - - - -
@@ -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 100.2 97.318 (1, 6, 10, 10, 1) 2 1 [100.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.719 (1, 6, 10, 10) 1 1 [1.77]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.963 (1, 1, 10, 10, 3) 1 1 [0.991]
- Total_time - 102.961 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.445 (1, 6, 10, 10, 1) 2 1 [102.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.814 1.721 (1, 6, 10, 10) 1 1 [1.814]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.878 0.834 (1, 3, 10, 10, 1) 1 1 [0.878]
+ Total_time - 105.392 - - - - -
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 7ef38e8a57..ebf19ff0bf 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/tmpgluqejqp/images/random'
+ '/tmp/tmpy8rx4kkp/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: [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [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], [0.0, 1.0], [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/tmpgluqejqp/images/target contains 8144 images
- /tmp/tmpgluqejqp/images/random contains 5000 images
+ /tmp/tmpy8rx4kkp/images/target contains 8144 images
+ /tmp/tmpy8rx4kkp/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2240 - accuracy: 0.9252 - val_loss: 0.2493 - val_accuracy: 0.9173 - 47s/epoch - 143ms/step
+ 328/328 - 47s - loss: 0.2071 - accuracy: 0.9284 - val_loss: 0.1229 - val_accuracy: 0.9592 - 47s/epoch - 144ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0901 - accuracy: 0.9658 - val_loss: 0.1571 - val_accuracy: 0.9532 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.0883 - accuracy: 0.9680 - val_loss: 0.1032 - val_accuracy: 0.9698 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0640 - accuracy: 0.9754 - val_loss: 0.1400 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.0661 - accuracy: 0.9759 - val_loss: 0.1043 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
- <keras.callbacks.History object at 0x7f76be7e4590>
+ <keras.callbacks.History object at 0x7fa9fc193b10>
@@ -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 38.646 seconds)
+ **Total running time of the script:** ( 4 minutes 35.026 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 73c6aee316..64bc003248 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**05:39.446** total execution time for **how_to_work_with_microtvm** files:
+**05:38.679** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.646 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.026 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:49.358 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.166 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.718 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.625 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.722 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.859 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index adba94052c..245308a0b2 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
=================
-**00:43.480** total execution time for **how_to_work_with_relay** files:
+**00:45.312** 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``) | 00:31.638 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.430 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.128 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.280 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.596 | 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 67a102faf3..27d1abcb15 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 0x7f770e8c5320>
+ <function my_cuda_math_rule at 0x7fa9f86d79e0>
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 41626ef759..0b3c739d17 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:06.008** total execution time for **how_to_work_with_schedules** files:
+**00:07.827** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:03.693 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.414 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.043 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.587 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.539 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.563 | 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``) | 00:00.118 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.051 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.020 | 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 55be8928ec..3d13ca9b87 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp2l4a8w3x/input0.cc'\nsource_filename = \"/tmp/tmp2l4a8w3x/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/tmp507f7oi0/input0.cc'\nsource_filename = \"/tmp/tmp507f7oi0/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 2856016e8a..981bb8da51 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
=================
-**00:26.196** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:27.380** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.190 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.374 | 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 fdd43242df..ae9b50ad5e 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 28.99s!
+ resnet18_v1 inference graph built in 30.16s!
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 775c421dad..3b4d912764 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 19.58s!
+ yolov3-tiny inference graph built in 20.11s!
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 cee700ea9f..06b9d978b0 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
=================
-**01:40.948** total execution time for **topic_vta_tutorials_frontend** files:
+**01:42.163** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.872 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.222 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.076 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.941 | 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 baf5ffa606..98ce21d3e7 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
=================
-**00:03.100** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.184** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.662 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.723 | 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``) | 00:00.461 | 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 036830bcae..01aea12565 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
=================
-**00:00.781** total execution time for **topic_vta_tutorials** files:
+**00:00.800** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.416 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.424 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.365 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.376 | 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 326c9e12fb..1fcbfbae3d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -333,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.653 ms
+ Execution time of this operator: 97.760 ms
@@ -433,7 +426,7 @@ resume the status and do more 5 trials.
Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -451,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 34.020 seconds)
+ **Total running time of the script:** ( 1 minutes 19.577 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 6dc3f29e56..0af67745ab 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: 9.11/9.11 result: MeasureResult(costs=(0.0294639272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.704277515411377, timestamp=1667600439.8011644) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 2 GFLOPS: 12.36/12.36 result: MeasureResult(costs=(0.0217097956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5637028217315674, timestamp=1667600440.3613122) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
- No: 3 GFLOPS: 11.60/12.36 result: MeasureResult(costs=(0.0231313244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5525696277618408, timestamp=1667600441.6351473) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
- No: 4 GFLOPS: 1.47/12.36 result: MeasureResult(costs=(0.1826311896,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.058821201324463, timestamp=1667600445.453223) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.93/12.36 result: MeasureResult(costs=(0.0683016298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.27158522605896, timestamp=1667600446.8736937) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
- No: 6 GFLOPS: 14.41/14.41 result: MeasureResult(costs=(0.0186263354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5002939701080322, timestamp=1667600447.3361092) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 7 GFLOPS: 3.38/14.41 result: MeasureResult(costs=(0.0793295266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4188477993011475, timestamp=1667600449.5113862) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
- No: 8 GFLOPS: 1.55/14.41 result: MeasureResult(costs=(0.1729946346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9581708908081055, timestamp=1667600452.491676) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 9 GFLOPS: 12.10/14.41 result: MeasureResult(costs=(0.022181018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48445558547973633, timestamp=1667600453.0983562) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
- No: 10 GFLOPS: 4.09/14.41 result: MeasureResult(costs=(0.065693861,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.17677903175354, timestamp=1667600454.3130083) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+ No: 1 GFLOPS: 2.31/2.31 result: MeasureResult(costs=(0.1160156268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0121259689331055, timestamp=1667602369.0228992) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 2 GFLOPS: 3.92/3.92 result: MeasureResult(costs=(0.0685516924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3405766487121582, timestamp=1667602370.328644) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+ No: 3 GFLOPS: 9.43/9.43 result: MeasureResult(costs=(0.0284811056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838117599487305, timestamp=1667602371.7321346) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 4 GFLOPS: 3.62/9.43 result: MeasureResult(costs=(0.0741042682,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3438503742218018, timestamp=1667602373.8630242) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 5 GFLOPS: 2.26/9.43 result: MeasureResult(costs=(0.11880267679999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0534772872924805, timestamp=1667602376.0872216) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 6 GFLOPS: 0.50/9.43 result: MeasureResult(costs=(0.5336246658,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.70423412322998, timestamp=1667602384.796229) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 7 GFLOPS: 3.62/9.43 result: MeasureResult(costs=(0.0741095866,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3492913246154785, timestamp=1667602386.9151893) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+ No: 8 GFLOPS: 11.67/11.67 result: MeasureResult(costs=(0.0229932958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6112122535705566, timestamp=1667602387.4983776) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 9 GFLOPS: 2.52/11.67 result: MeasureResult(costs=(0.10667436239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8538415431976318, timestamp=1667602389.4771836) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+ No: 10 GFLOPS: 12.81/12.81 result: MeasureResult(costs=(0.0209618688,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4951808452606201, timestamp=1667602389.9840531) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 32f79745f5..cc2412c6c5 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': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
+ {'mean': 516.3002476199927, 'median': 517.2048575999952, 'std': 2.159932684046858}
@@ -554,31 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.96/ 16.73 GFLOPS | Progress: (4/20) | 7.40 s
[Task 1/25] Current/Best: 11.33/ 16.73 GFLOPS | Progress: (8/20) | 11.02 s
[Task 1/25] Current/Best: 16.79/ 19.58 GFLOPS | Progress: (12/20) | 13.33 s
[Task 1/25] Current/Best: 6.67/ 19.58 GFLOPS | Progress: (16/20) | 18.63 s
[Task 1/25] Current/Best: 8.51/ 19.58 GFLOPS | Progress: (20/20) | 21.25 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.25/ 18.20 GFLOPS | Progress: (4/20) | 3.00 s
[Task 2/25] Current/Best: 5.95/ 18.20 GFLOPS | Progress: (8/20) | 4.61 s
[Task 2/25] Current/Best: 11.49/ 18.80 GFLOPS | Progress: (12/20) | 6.02 s
[Task 2/25] Current/Best: 13.46/ 18.80 GFLOPS | Progress: (16/20) | 7.03 s
[Task 2/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (20/20) | 8.78 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 10.25/ 22.94 GFLOPS | Progress: (4/20) | 4.58 s
[Task 3/25] Current/Best: 11.97/ 22.94 GFLOPS | Progress: (8/20) | 6.62 s
[Task 3/25] Current/Best: 20.15/ 22.94 GFLOPS | Progress: (12/20) | 8.93 s
[Task 3/25] Current/Best: 19.99/ 22.94 GFLOPS | Progress: (16/20) | 10.51 s
[Task 3/25] Current/Best: 17.59/ 22.94 GFLOPS | Progress: (20/20) | 12.14 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.81/ 14.47 GFLOPS | Progress: (4/20) | 3.24 s
[Task 4/25] Current/Best: 6.16/ 21.28 GFLOPS | Progress: (8/20) | 9.10 s
[Task 4/25] Current/Best: 7.51/ 21.28 GFLOPS | Progress: (12/20) | 10.80 s
[Task 4/25] Current/Best: 7.94/ 21.28 GFLOPS | Progress: (16/20) | 13.27 s
[Task 4/25] Current/Best: 14.16/ 21.28 GFLOPS | Progress: (20/20) | 16.20 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.69/ 11.69 GFLOPS | Progress: (4/20) | 3.33 s
[Task 5/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (8/20) | 5.85 s
[Task 5/25] Current/Best: 15.47/ 15.47 GFLOPS | Progress: (12/20) | 7.71 s
[Task 5/25] Current/Best: 18.38/ 18.38 GFLOPS | Progress: (16/20) | 9.12 s
[Task 5/25] Current/Best: 5.28/ 18.38 GFLOPS | Progress: (20/20) | 10.87 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.65/ 13.49 GFLOPS | Progress: (4/20) | 7.55 s
[Task 6/25] Current/Best: 13.88/ 17.20 GFLOPS | Progress: (8/20) | 9.27 s
[Task 6/25] Current/Best: 7.84/ 18.15 GFLOPS | Progress: (12/20) | 12.56 s
[Task 6/25] Current/Best: 3.76/ 18.15 GFLOPS | Progress: (16/20) | 16.07 s
[Task 6/25] Current/Best: 7.38/ 18.15 GFLOPS | Progress: (20/20) | 18.38 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.46/ 18.88 GFLOPS | Progress: (4/20) | 3.78 s
[Task 7/25] Current/Best: 17.03/ 18.88 GFLOPS | Progress: (8/20) | 6.21 s
[Task 7/25] Current/Best: 6.26/ 22.77 GFLOPS | Progress: (12/20) | 8.19 s
[Task 7/25] Current/Best: 12.70/ 22.77 GFLOPS | Progress: (16/20) | 10.44 s
[Task 7/25] Current/Best: 11.26/ 22.77 GFLOPS | Progress: (20/20) | 13.24 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.74/ 14.22 GFLOPS | Progress: (4/20) | 3.91 s
[Task 8/25] Current/Best: 13.03/ 14.22 GFLOPS | Progress: (8/20) | 14.63 s
[Task 8/25] Current/Best: 10.31/ 19.82 GFLOPS | Progress: (12/20) | 17.21 s
[Task 8/25] Current/Best: 10.18/ 19.82 GFLOPS | Progress: (16/20) | 22.30 s
[Task 8/25] Current/Best: 12.54/ 19.82 GFLOPS | Progress: (20/20) | 28.31 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.57/ 16.17 GFLOPS | Progress: (4/20) | 3.30 s
[Task 9/25] Current/Best: 11.91/ 16.46 GFLOPS | Progress: (8/20) | 9.99 s
[Task 9/25] Current/Best: 11.94/ 16.51 GFLOPS | Progress: (12/20) | 14.73 s
[Task 9/25] Current/Best: 14.62/ 16.51 GFLOPS | Progress: (16/20) | 16.95 s
[Task 9/25] Current/Best: 11.01/ 16.51 GFLOPS | Progress: (20/20) | 21.30 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.04/ 13.12 GFLOPS | Progress: (4/20) | 3.50 s
[Task 10/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (8/20) | 5.21 s
[Task 10/25] Current/Best: 9.44/ 20.53 GFLOPS | Progress: (12/20) | 6.79 s
[Task 10/25] Current/Best: 10.75/ 20.53 GFLOPS | Progress: (16/20) | 8.89 s
[Task 10/25] Current/Best: 11.07/ 22.53 GFLOPS | Progress: (20/20) | 11.75 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 5.53/ 16.38 GFLOPS | Progress: (4/20) | 3.92 s
[Task 11/25] Current/Best: 7.67/ 16.38 GFLOPS | Progress: (8/20) | 8.71 s
[Task 11/25] Current/Best: 12.71/ 22.48 GFLOPS | Progress: (12/20) | 11.07 s
[Task 11/25] Current/Best: 6.19/ 23.39 GFLOPS | Progress: (16/20) | 13.21 s
[Task 11/25] Current/Best: 12.35/ 23.57 GFLOPS | Progress: (20/20) | 15.26 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.15/ 14.23 GFLOPS | Progress: (4/20) | 4.37 s
[Task 12/25] Current/Best: 14.60/ 14.86 GFLOPS | Progress: (8/20) | 6.42 s
[Task 12/25] Current/Best: 14.31/ 17.83 GFLOPS | Progress: (12/20) | 8.72 s
[Task 12/25] Current/Best: 3.14/ 17.85 GFLOPS | Progress: (16/20) | 12.32 s
[Task 12/25] Current/Best: 11.78/ 17.85 GFLOPS | Progress: (20/20) | 15.21 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 13.81/ 16.10 GFLOPS | Progress: (4/20) | 4.79 s
[Task 13/25] Current/Best: 5.88/ 17.03 GFLOPS | Progress: (8/20) | 7.68 s
[Task 13/25] Current/Best: 18.90/ 19.86 GFLOPS | Progress: (12/20) | 10.41 s
[Task 13/25] Current/Best: 17.16/ 19.86 GFLOPS | Progress: (16/20) | 12.81 s
[Task 13/25] Current/Best: 11.78/ 22.02 GFLOPS | Progress: (20/20) | 14.46 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 6.67/ 16.46 GFLOPS | Progress: (4/20) | 3.76 s
[Task 14/25] Current/Best: 3.46/ 16.92 GFLOPS | Progress: (8/20) | 6.39 s
[Task 14/25] Current/Best: 13.43/ 18.46 GFLOPS | Progress: (12/20) | 8.86 s
[Task 14/25] Current/Best: 9.27/ 21.30 GFLOPS | Progress: (16/20) | 12.71 s
[Task 14/25] Current/Best: 14.08/ 21.30 GFLOPS | Progress: (20/20) | 14.86 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.12/ 18.05 GFLOPS | Progress: (4/20) | 4.98 s
[Task 15/25] Current/Best: 16.09/ 22.87 GFLOPS | Progress: (8/20) | 6.18 s
[Task 15/25] Current/Best: 23.14/ 23.14 GFLOPS | Progress: (12/20) | 7.35 s
[Task 15/25] Current/Best: 10.22/ 23.14 GFLOPS | Progress: (16/20) | 9.74 s
[Task 15/25] Current/Best: 18.31/ 23.14 GFLOPS | Progress: (20/20) | 12.04 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.82/ 20.07 GFLOPS | Progress: (4/20) | 4.56 s
[Task 16/25] Current/Best: 14.09/ 20.65 GFLOPS | Progress: (8/20) | 6.24 s
[Task 16/25] Current/Best: 16.00/ 20.65 GFLOPS | Progress: (12/20) | 8.14 s
[Task 16/25] Current/Best: 9.71/ 20.65 GFLOPS | Progress: (16/20) | 9.67 s
[Task 16/25] Current/Best: 1.56/ 20.65 GFLOPS | Progress: (20/20) |
11.67 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 10.30/ 22.80 GFLOPS | Progress: (4/20) | 3.59 s
[Task 17/25] Current/Best: 12.12/ 22.80 GFLOPS | Progress: (8/20) | 6.22 s
[Task 17/25] Current/Best: 19.29/ 22.80 GFLOPS | Progress: (12/20) | 8.00 s
[Task 17/25] Current/Best: 12.95/ 23.98 GFLOPS | Progress: (16/20) | 10.21 s
[Task 17/25] Current/Best: 4.31/ 23.98 GFLOPS | Progress: (20/20) | 13.92 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 3.01/ 18.11 GFLOPS | Progress: (4/20) | 4.25 s
[Task 18/25] Current/Best: 13.36/ 18.42 GFLOPS | Progress: (8/20) | 6.55 s
[Task 18/25] Current/Best: 16.09/ 18.42 GFLOPS | Progress: (12/20) | 8.70 s
[Task 18/25] Current/Best: 15.68/ 18.42 GFLOPS | Progress: (16/20) | 14.50 s
[Task 18/25] Current/Best: 11.91/ 21.22 GFLOPS | Progress: (20/20) | 16.91 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 9.94/ 21.33 GFLOPS | Progress: (4/20) | 4.67 s
[Task 19/25] Current/Best: 4.54/ 21.33 GFLOPS | Progress: (8/20) | 7.72 s
[Task 19/25] Current/Best: 8.71/ 21.33 GFLOPS | Progress: (12/20) | 10.63 s
[Task 19/25] Current/Best: 7.50/ 21.33 GFLOPS | Progress: (16/20) | 14.04 s
[Task 19/25] Current/Best: 8.63/ 22.33 GFLOPS | Progress: (20/20) | 16.92 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.44/ 19.28 GFLOPS | Progress: (4/20) | 4.16 s Done.
-
[Task 20/25] Current/Best: 10.13/ 19.28 GFLOPS | Progress: (8/20) | 8.31 s
[Task 20/25] Current/Best: 7.45/ 19.28 GFLOPS | Progress: (12/20) | 11.42 s
[Task 20/25] Current/Best: 11.99/ 19.28 GFLOPS | Progress: (16/20) | 14.00 s
[Task 20/25] Current/Best: 10.01/ 19.28 GFLOPS | Progress: (20/20) | 16.65 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 12.95/ 13.28 GFLOPS | Progress: (4/20) | 3.17 s
[Task 21/25] Current/Best: 9.26/ 13.28 GFLOPS | Progress: (8/20) | 6.63 s
[Task 21/25] Current/Best: 8.09/ 14.85 GFLOPS | Progress: (12/20) | 9.02 s
[Task 21/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (16/20) | 10.98 s
[Task 21/25] Current/Best: 9.05/ 20.63 GFLOPS | Progress: (20/20) | 13.95 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (4/20
) | 4.40 s Done.
- Done.
-
[Task 22/25] Current/Best: 12.76/ 18.94 GFLOPS | Progress: (8/20) | 7.07 s
[Task 22/25] Current/Best: 14.40/ 18.94 GFLOPS | Progress: (12/20) | 8.32 s
[Task 22/25] Current/Best: 13.13/ 18.94 GFLOPS | Progress: (16/20) | 10.25 s
[Task 22/25] Current/Best: 17.79/ 18.94 GFLOPS | Progress: (20/20) | 14.02 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.79/ 20.38 GFLOPS | Progress: (4/20) | 3.69 s
[Task 23/25] Current/Best: 19.95/ 20.38 GFLOPS | Progress: (8/20) | 7.42 s
[Task 23/25] Current/Best: 9.95/ 20.38 GFLOPS | Progress: (12/20) | 10.94 s
[Task 23/25] Current/Best: 9.07/ 20.38 GFLOPS | Progress: (16/20) | 14.10 s
[Task 23/25] Current/Best: 11.54/ 20.38 GFLOPS | Progress: (20/20) | 16.86 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (4/20) | 12.21 s
[Task 24/25] Current/Best: 6.01/ 9.98 GFLOPS | Progress: (8/20) | 22.92 s
[Task 24/25] Current/Best: 5.54/ 9.98 GFLOPS | Progress: (12/20) | 34.54 s
[Task 24/25] Current/Best: 3.26/ 9.98 GFLOPS | Progress: (16/20) | 46.01 s
[Task 24/25] Current/Best: 8.05/ 9.98 GFLOPS | Progress: (20/20) | 57.51 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 2.79/ 8.54 GFLOPS | Progress: (4/20) | 4.55 s
[Task 25/25] Current/Best: 5.71/ 9.35 GFLOPS | Progress: (8/20) | 9.37 s
[Task 25/25] Current/Best: 1.55/ 9.46 GFLOPS | Progress: (12/20) | 10.77 s
[Task 25/25] Current/Best: 8.71/ 9.46 GFLOPS | Progress: (16/20) | 21.06 s
[Task 25/25] Current/Best: 5.79/ 9.46 GFLOPS | Progress: (20/20) | 32.71 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 5.77/ 22.39 GFLOPS | Progress: (4/20) | 7.09 s
[Task 1/25] Current/Best: 7.95/ 23.79 GFLOPS | Progress: (8/20) | 10.20 s
[Task 1/25] Current/Best: 6.00/ 23.79 GFLOPS | Progress: (12/20) | 12.75 s
[Task 1/25] Current/Best: 17.83/ 23.79 GFLOPS | Progress: (16/20) | 16.23 s
[Task 1/25] Current/Best: 6.07/ 23.79 GFLOPS | Progress: (20/20) | 18.60 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.80/ 20.66 GFLOPS | Progress: (4/20) | 2.91 s
[Task 2/25] Current/Best: 10.53/ 20.66 GFLOPS | Progress: (8/20) | 4.23 s
[Task 2/25] Current/Best: 8.86/ 20.66 GFLOPS | Progress: (12/20) | 5.97 s
[Task 2/25] Current/Best: 13.36/ 20.66 GFLOPS | Progress: (16/20) | 7.09 s
[Task 2/25] Current/Best: 13.75/ 20.66 GFLOPS | Progress: (20/20) | 8.75 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.11/ 12.36 GFLOPS | Progress: (4/20) | 4.17 s
[Task 3/25] Current/Best: 12.64/ 20.53 GFLOPS | Progress: (8/20) | 6.65 s
[Task 3/25] Current/Best: 7.48/ 20.53 GFLOPS | Progress: (12/20) | 8.38 s
[Task 3/25] Current/Best: 15.83/ 20.53 GFLOPS | Progress: (16/20) | 10.96 s
[Task 3/25] Current/Best: 15.29/ 20.53 GFLOPS | Progress: (20/20) | 12.89 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 14.64 GFLOPS | Progress: (4/20) | 4.79 s
[Task 4/25] Current/Best: 11.47/ 17.99 GFLOPS | Progress: (8/20) | 6.89 s
[Task 4/25] Current/Best: 9.61/ 17.99 GFLOPS | Progress: (12/20) | 8.44 s
[Task 4/25] Current/Best: 19.22/ 19.22 GFLOPS | Progress: (16/20) | 12.72 s
[Task 4/25] Current/Best: 6.30/ 20.05 GFLOPS | Progress: (20/20) | 14.43 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.18/ 14.89 GFLOPS | Progress: (4/20) | 3.79 s
[Task 5/25] Current/Best: 4.79/ 14.89 GFLOPS | Progress: (8/20) | 5.70 s
[Task 5/25] Current/Best: 5.56/ 19.87 GFLOPS | Progress: (12/20) | 7.37 s
[Task 5/25] Current/Best: 11.76/ 19.87 GFLOPS | Progress: (16/20) | 8.79 s
[Task 5/25] Current/Best: 14.66/ 19.87 GFLOPS | Progress: (20/20) | 10.45 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.11/ 18.71 GFLOPS | Progress: (4/20) | 4.28 s
[Task 6/25] Current/Best: 4.60/ 20.02 GFLOPS | Progress: (8/20) | 6.92 s
[Task 6/25] Current/Best: 15.82/ 20.02 GFLOPS | Progress: (12/20) | 9.14 s
[Task 6/25] Current/Best: 12.45/ 20.02 GFLOPS | Progress: (16/20) | 11.14 s
[Task 6/25] Current/Best: 6.50/ 20.02 GFLOPS | Progress: (20/20) | 13.56 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.50/ 16.50 GFLOPS | Progress: (4/20) | 3.64 s
[Task 7/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (8/20) | 5.71 s
[Task 7/25] Current/Best: 13.87/ 17.45 GFLOPS | Progress: (12/20) | 7.63 s
[Task 7/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (16/20) | 9.85 s
[Task 7/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (20/20) | 12.28 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 21.04/ 21.04 GFLOPS | Progress: (4/20) | 3.93 s
[Task 8/25] Current/Best: 13.56/ 21.04 GFLOPS | Progress: (8/20) | 10.58 s
[Task 8/25] Current/Best: 7.40/ 21.04 GFLOPS | Progress: (12/20) | 14.94 s
[Task 8/25] Current/Best: 3.93/ 21.04 GFLOPS | Progress: (16/20) | 17.20 s
[Task 8/25] Current/Best: 11.13/ 21.04 GFLOPS | Progress: (20/20) | 21.12 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 4.45/ 21.66 GFLOPS | Progress: (4/20) | 3.70 s
[Task 9/25] Current/Best: 17.39/ 21.66 GFLOPS | Progress: (8/20) | 5.13 s
[Task 9/25] Current/Best: 13.57/ 21.66 GFLOPS | Progress: (12/20) | 7.21 s
[Task 9/25] Current/Best: 7.53/ 21.66 GFLOPS | Progress: (16/20) | 10.36 s
[Task 9/25] Current/Best: 9.02/ 21.66 GFLOPS | Progress: (20/20) | 13.14 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 6.04/ 13.17 GFLOPS | Progress: (4/20) | 3.58 s
[Task 10/25] Current/Best: 9.52/ 15.47 GFLOPS | Progress: (8/20) | 5.53 s
[Task 10/25] Current/Best: 1.61/ 17.92 GFLOPS | Progress: (12/20) | 8.12 s
[Task 10/25] Current/Best: 3.78/ 17.92 GFLOPS | Progress: (16/20) | 10.11 s
[Task 10/25] Current/Best: 9.99/ 20.28 GFLOPS | Progress: (20/20) | 11.52 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 8.68/ 20.13 GFLOPS | Progress: (4/20) | 3.84 s
[Task 11/25] Current/Best: 10.99/ 20.13 GFLOPS | Progress: (8/20) | 6.68 s
[Task 11/25] Current/Best: 7.63/ 21.63 GFLOPS | Progress: (12/20) | 9.40 s
[Task 11/25] Current/Best: 13.81/ 21.63 GFLOPS | Progress: (16/20) | 11.66 s
[Task 11/25] Current/Best: 20.38/ 21.63 GFLOPS | Progress: (20/20) | 13.34 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.22/ 16.79 GFLOPS | Progress: (4/20) | 7.76 s
[Task 12/25] Current/Best: 11.22/ 16.79 GFLOPS | Progress: (8/20) | 13.65 s
[Task 12/25] Current/Best: 9.09/ 16.79 GFLOPS | Progress: (12/20) | 16.30 s
[Task 12/25] Current/Best: 13.18/ 19.12 GFLOPS | Progress: (16/20) | 20.29 s
[Task 12/25] Current/Best: 18.24/ 19.12 GFLOPS | Progress: (20/20) | 28.84 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 4.08 s
[Task 13/25] Current/Best: 12.44/ 20.58 GFLOPS | Progress: (8/20) | 7.46 s
[Task 13/25] Current/Best: 7.46/ 20.58 GFLOPS | Progress: (12/20) | 10.61 s
[Task 13/25] Current/Best: 15.05/ 20.58 GFLOPS | Progress: (16/20) | 13.16 s
[Task 13/25] Current/Best: 22.21/ 22.21 GFLOPS | Progress: (20/20) | 16.47 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 17.82/ 17.82 GFLOPS | Progress: (4/20) | 3.69 s
[Task 14/25] Current/Best: 5.97/ 17.82 GFLOPS | Progress: (8/20) | 6.19 s
[Task 14/25] Current/Best: 10.37/ 18.98 GFLOPS | Progress: (12/20) | 8.98 s
[Task 14/25] Current/Best: 9.08/ 18.98 GFLOPS | Progress: (16/20) | 15.74 s
[Task 14/25] Current/Best: 3.78/ 18.98 GFLOPS | Progress: (20/20) | 18.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (4/20) | 5.79 s
[Task 15/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (8/20) | 7.83 s
[Task 15/25] Current/Best: 9.26/ 20.49 GFLOPS | Progress: (12/20) | 11.34 s
[Task 15/25] Current/Best: 21.40/ 21.40 GFLOPS | Progress: (16/20) | 14.45 s
[Task 15/25] Current/Best: 17.00/ 21.40 GFLOPS | Progress: (20/20)
| 16.45 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 7.45/ 14.24 GFLOPS | Progress: (4/20) | 4.67 s
[Task 16/25] Current/Best: 11.49/ 14.24 GFLOPS | Progress: (8/20) | 7.04 s
[Task 16/25] Current/Best: 18.64/ 18.64 GFLOPS | Progress: (12/20) | 8.85 s
[Task 16/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (16/20) | 10.58 s
[Task 16/25] Current/Best: 16.30/ 20.59 GFLOPS | Progress: (20/20) | 13.01 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 17.03/ 17.03 GFLOPS | Progress: (4/20) | 3.68 s
[Task 17/25] Current/Best: 16.79/ 20.29 GFLOPS | Progress: (8/20) | 5.73 s
[Task 17/25] Current/Best: 19.19/ 20.29 GFLOPS | Progress: (12/20) | 7.81 s
[Task 17/25] Current/Best: 4.88/ 20.29 GFLOPS | Progress: (16/20) | 11.51 s
[Task 17/25] Current/Best: 5.06/ 22.33 GFLOPS | Progress: (20/20) | 15.89 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (4/20) | 6.63 s
[Task 18/25] Current/Best: 6.95/ 19.45 GFLOPS | Progress: (8/20) | 8.40 s
[Task 18/25] Current/Best: 12.40/ 20.78 GFLOPS | Progress: (12/20) | 10.57 s
[Task 18/25] Current/Best: 16.90/ 20.78 GFLOPS | Progress: (16/20) | 12.70 s
[Task 18/25] Current/Best: 7.63/ 20.78 GFLOPS | Progress: (20/20) | 17.87 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.46/ 16.14 GFLOPS | Progress: (4/20) | 4.78 s
[Task 19/25] Current/Best: 10.85/ 16.14 GFLOPS | Progress: (8/20) | 11.05 s
[Task 19/25] Current/Best: 7.52/ 17.44 GFLOPS | Progress: (12/20) | 13.96 s
[Task 19/25] Current/Best: 11.13/ 17.44 GFLOPS | Progress: (16/20) | 20.45 s
[Task 19/25] Current/Best: 6.46/ 17.44 GFLOPS | Progress: (20/20) | 24.06 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 7.66/ 21.18 GFLOPS | Progress: (4/20) | 3.96 s
[Task 20/25] Current/Best: 3.03/ 21.18 GFLOPS | Progress: (8/20) | 6.73 s
[Task 20/25] Current/Best: 16.45/ 21.18 GFLOPS | Progress: (12/20) | 9.30 s Done.
+
[Task 20/25] Current/Best: 11.74/ 21.18 GFLOPS | Progress: (16/20) | 12.04 s
[Task 20/25] Current/Best: 6.19/ 21.18 GFLOPS | Progress: (20/20) | 14.72 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 4.43/ 10.04 GFLOPS | Progress: (4/20) | 4.27 s
[Task 21/25] Current/Best: 10.03/ 15.75 GFLOPS | Progress: (8/20) | 6.55 s
[Task 21/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (12/20) | 8.51 s
[Task 21/25] Current/Best: 9.27/ 16.95 GFLOPS | Progress: (16/20) | 11.11 s
[Task 21/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (20/20) | 13.91 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.14/ 15.14 GFLOPS | Progress: (4/20) | 4.47 s
[Task 22/25] Current/Best: 5.24/ 20.16 GFLOPS | Progress: (8/20) | 5.92 s
[Task 22/25] Current/Best: 5.25/ 20.16 GFLOPS | Progress: (12/20) | 8.00 s
[Task 22/25] Current/Best: 2.69/ 20.16 GFLOPS | Progress: (16/20) | 10.61 s
[Task 22/25] Current/Best: 8.60/ 20.16 GFLOPS | Progress: (20/20)
| 12.71 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 12.84/ 22.88 GFLOPS | Progress: (4/20) | 4.15 s
[Task 23/25] Current/Best: 20.80/ 22.88 GFLOPS | Progress: (8/20) | 6.35 s
[Task 23/25] Current/Best: 13.03/ 22.88 GFLOPS | Progress: (12/20) | 9.10 s
[Task 23/25] Current/Best: 13.00/ 22.88 GFLOPS | Progress: (16/20) | 11.82 s
[Task 23/25] Current/Best: 3.09/ 22.88 GFLOPS | Progress: (20/20) | 17.02 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 5.46/ 10.04 GFLOPS | Progress: (4/20) | 8.04 s
[Task 24/25] Current/Best: 1.54/ 10.04 GFLOPS | Progress: (8/20) | 19.09 s
[Task 24/25] Current/Best: 3.89/ 10.04 GFLOPS | Progress: (12/20) | 21.34 s Done.
+
[Task 24/25] Current/Best: 1.56/ 10.04 GFLOPS | Progress: (16/20) | 31.76 s
[Task 24/25] Current/Best: 7.00/ 10.04 GFLOPS | Progress: (20/20) | 42.03 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 9.41/ 9.41 GFLOPS | Progress: (4/20) | 12.26 s
[Task 25/25] Current/Best: 2.67/ 9.41 GFLOPS | Progress: (8/20) | 23.70 s
[Task 25/25] Current/Best: 8.17/ 9.41 GFLOPS | Progress: (12/20) | 35.61 s Done.
+
[Task 25/25] Current/Best: 4.79/ 9.41 GFLOPS | Progress: (16/20) | 46.33 s
[Task 25/25] Current/Best: 3.00/ 9.41 GFLOPS | Progress: (20/20) | 57.87 s
@@ -674,8 +674,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621102
- class='n02123159 tiger cat' with probability=0.356379
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 406.0337182000035, 'median': 406.1050522000073, 'std': 1.1477014024438263}
- unoptimized: {'mean': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
+ optimized: {'mean': 402.4906679900005, 'median': 402.483829699986, 'std': 0.8240857902972529}
+ unoptimized: {'mean': 516.3002476199927, 'median': 517.2048575999952, 'std': 2.159932684046858}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 52.900 seconds)
+ **Total running time of the script:** ( 11 minutes 9.699 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 6c689a7e6f..36dac20bd2 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
- 1.506e-07 secs/op
+ 1.253e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d3eb9dbca2..934912b90d 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x5610c10)), stage(b, placeholder(b, 0x22961a50)), 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, 0x22852f00)), stage(b, placeholder(b, 0x1b0326f0)), 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 894d32b518..eec0997075 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**14:24.924** total execution time for **tutorial** files:
+**14:33.911** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:52.900 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:09.699 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:34.020 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:19.577 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.016 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.627 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:35.795 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.607 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:19.028 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:26.903 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.230 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.780 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.757 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.545 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.169 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.166 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 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 |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 741fd2e2fa..f775de0854 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.90564999988419e-06 1.0
- naive 6.6824e-06 0.8452688899834789
- parallel 6.9530999999999995e-06 0.879510223713655
- vector 2.4559499999999998e-05 3.1065756769348214
+ numpy 7.669649999115791e-06 1.0
+ naive 6.7220999999999996e-06 0.8764545971165527
+ parallel 6.988800000000001e-06 0.9112280222442637
+ vector 2.4559100000000003e-05 3.2021148295986572
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017863
+ Numpy running time: 0.019169
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.421262
+ none: 3.247187
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.303684
+ blocking: 0.326988
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335182
+ vectorization: 0.353425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.115062
+ loop permutation: 0.124741
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108361
+ array packing: 0.108710
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110699
+ block caching: 0.111546
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146580
+ parallelization: 0.146937
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.421261704 1.0
- blocking 0.30368355 0.08876361303929062
- vectorization 0.33518173139999996 0.097970211108995
- loop permutation 0.11506181280000001 0.03363139764066409
- array packing 0.10836136290000001 0.031672924282088184
- block caching 0.11069907539999999 0.03235621387003956
- parallelization 0.1465796965 0.04284375449227546
+ none 3.2471866261000004 1.0
+ blocking 0.32698844779999997 0.1006990005353422
+ vectorization 0.3534247574 0.10884029718503649
+ loop permutation 0.124740865 0.038415058745736065
+ array packing 0.10871017270000001 0.033478264484775005
+ block caching 0.1115463012 0.034351675479142856
+ parallelization 0.1469365568 0.04525041943045836
@@ -1661,11 +1661,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.016 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index c2de33fcef..73fd66e2bd 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-dec74cb93d3460d686f1935f933dc24404c5e995
+be44e9c811c071f01f66002729b8a9cb356a3adf
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 13c6b68ecf..bc30b02391 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 11.861 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.776 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 82ef37cd45..b1bb52252b 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 950ms/step
+1/1 [==============================] - 1s 958ms/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 28ee8e754a..83c5d43d18 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.zipe232925d-da3c-4a18-bed2-a6d0928c330f 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.zip678a38c4-50bd-43f1-83f9-b8730d823e78 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 7655e7bf0f..d5c822ff27 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,13 +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]
- 16%|#5 | 6.57M/41.5M [00:00<00:00, 68.8MB/s]
- 32%|###1 | 13.1M/41.5M [00:00<00:00, 66.9MB/s]
- 47%|####7 | 19.5M/41.5M [00:00<00:00, 51.7MB/s]
- 60%|#####9 | 24.8M/41.5M [00:00<00:00, 24.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 32.5MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 37.1MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 34.9MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 59.9MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 58.6MB/s]
+ 51%|##### | 21.1M/41.5M [00:00<00:00, 63.8MB/s]
+ 66%|######5 | 27.3M/41.5M [00:00<00:00, 41.3MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 42.8MB/s]
+ 90%|########9 | 37.2M/41.5M [00:00<00:00, 40.9MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 45.8MB/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 71b4b9245c..c9956cf86d 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%|#8 | 8.41M/44.7M [00:00<00:00, 88.1MB/s]
- 48%|####8 | 21.6M/44.7M [00:00<00:00, 118MB/s]
- 74%|#######3 | 32.8M/44.7M [00:00<00:00, 88.5MB/s]
- 99%|#########8| 44.2M/44.7M [00:00<00:00, 94.1MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 95.7MB/s]
+ 23%|##2 | 10.1M/44.7M [00:00<00:00, 86.2MB/s]
+ 58%|#####7 | 25.8M/44.7M [00:00<00:00, 129MB/s]
+ 86%|########5 | 38.4M/44.7M [00:00<00:00, 114MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 111MB/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 f49c74b66e..8662e8b5bf 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 10.844 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.883 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 d2770eda6f..372cd6bd69 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>05:45.577</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:55.698</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_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>01:11.861</p></td>
+<td><p>01:13.776</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:10.844</p></td>
+<td><p>01:12.883</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>00:45.874</p></td>
+<td><p>00:47.725</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>00:32.532</p></td>
+<td><p>00:33.578</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>00:30.407</p></td>
+<td><p>00:29.996</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>00:26.987</p></td>
+<td><p>00:27.567</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>00:24.445</p></td>
+<td><p>00:25.968</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>00:22.190</p></td>
+<td><p>00:23.197</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>00:18.043</p></td>
+<td><p>00:18.537</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>00:02.394</p></td>
+<td><p>00:02.470</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 a6588eae65..5c7caef77f 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3996 16.5399 16.8385 15.7575 0.3918
+ 16.7843 16.7883 17.2602 16.2491 0.4103
</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 b9bf0bfde6..0a5d163f9a 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,18 +453,21 @@ 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]
- 9%|8 | 15.0M/170M [00:00<00:01, 157MB/s]
- 18%|#7 | 30.0M/170M [00:00<00:01, 108MB/s]
- 24%|##4 | 41.1M/170M [00:00<00:01, 108MB/s]
- 31%|### | 51.9M/170M [00:00<00:01, 94.9MB/s]
- 36%|###6 | 61.4M/170M [00:00<00:01, 66.6MB/s]
- 45%|####4 | 76.2M/170M [00:00<00:01, 86.7MB/s]
- 56%|#####5 | 94.7M/170M [00:00<00:00, 113MB/s]
- 64%|######4 | 109M/170M [00:01<00:00, 121MB/s]
- 72%|#######1 | 122M/170M [00:01<00:00, 97.5MB/s]
- 79%|#######9 | 134M/170M [00:01<00:00, 98.5MB/s]
- 87%|########7 | 148M/170M [00:01<00:00, 91.9MB/s]
- 99%|#########8| 168M/170M [00:01<00:00, 117MB/s]
+ 5%|5 | 9.00M/170M [00:00<00:01, 94.4MB/s]
+ 13%|#3 | 22.8M/170M [00:00<00:01, 124MB/s]
+ 20%|## | 34.6M/170M [00:00<00:01, 101MB/s]
+ 28%|##7 | 47.4M/170M [00:00<00:01, 112MB/s]
+ 34%|###4 | 58.6M/170M [00:00<00:01, 106MB/s]
+ 41%|#### | 68.9M/170M [00:00<00:00, 106MB/s]
+ 47%|####6 | 79.2M/170M [00:00<00:00, 97.7MB/s]
+ 53%|#####3 | 90.8M/170M [00:00<00:00, 104MB/s]
+ 59%|#####9 | 101M/170M [00:01<00:00, 103MB/s]
+ 65%|######5 | 111M/170M [00:01<00:00, 102MB/s]
+ 71%|#######1 | 121M/170M [00:01<00:00, 101MB/s]
+ 77%|#######6 | 131M/170M [00:01<00:00, 99.8MB/s]
+ 83%|########2 | 141M/170M [00:01<00:00, 102MB/s]
+ 89%|########8 | 150M/170M [00:01<00:00, 95.7MB/s]
+ 95%|#########5| 162M/170M [00:01<00:00, 102MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/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)
@@ -563,7 +566,7 @@ 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 14.701 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 24.617 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 ee2e07070a..ff60361389 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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 66.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 80.5MB/s]
+ 65%|######4 | 8.80M/13.6M [00:00<00:00, 92.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 117MB/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)
- 90.5992 90.5281 95.1870 90.2380 0.4903
+ 90.5063 90.3367 93.3010 90.1649 0.4937
</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 6.201 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.490 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 6d375decc3..470d465459 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)
- 120.1178 119.9952 125.3989 119.3251 0.6637
+ 120.9338 120.8854 123.2581 120.0275 0.4833
</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 22.886 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.418 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 fcb62e54f4..e7be24aae1 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 35.136 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 35.418 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 cec617f552..c873c890db 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,23 +462,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6073/132723 [00:00<00:02, 60726.00KB/s]
- 11%|# | 14266/132723 [00:00<00:01, 73191.15KB/s]
- 16%|#6 | 21586/132723 [00:00<00:01, 63785.78KB/s]
- 22%|##2 | 29818/132723 [00:00<00:01, 70500.02KB/s]
- 28%|##7 | 37004/132723 [00:00<00:01, 69388.81KB/s]
- 34%|###4 | 45227/132723 [00:00<00:01, 73532.01KB/s]
- 40%|###9 | 52659/132723 [00:00<00:01, 68612.56KB/s]
- 46%|####5 | 60890/132723 [00:00<00:00, 72652.91KB/s]
- 52%|#####2 | 69047/132723 [00:00<00:00, 75294.74KB/s]
- 58%|#####8 | 77304/132723 [00:01<00:00, 77455.29KB/s]
- 64%|######4 | 85116/132723 [00:01<00:00, 74894.97KB/s]
- 70%|####### | 93223/132723 [00:01<00:00, 76692.38KB/s]
- 76%|#######6 | 101429/132723 [00:01<00:00, 78267.18KB/s]
- 83%|########2 | 109560/132723 [00:01<00:00, 79164.39KB/s]
- 89%|########8 | 117769/132723 [00:01<00:00, 80031.60KB/s]
- 95%|#########4| 126032/132723 [00:01<00:00, 80794.05KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74773.55KB/s]
+ 5%|4 | 6164/132723 [00:00<00:02, 61632.71KB/s]
+ 11%|# | 14563/132723 [00:00<00:01, 74775.18KB/s]
+ 17%|#6 | 22041/132723 [00:00<00:01, 56413.55KB/s]
+ 23%|##2 | 30449/132723 [00:00<00:01, 65533.97KB/s]
+ 29%|##9 | 38900/132723 [00:00<00:01, 71608.79KB/s]
+ 36%|###5 | 47440/132723 [00:00<00:01, 75935.22KB/s]
+ 42%|####1 | 55302/132723 [00:00<00:01, 73055.67KB/s]
+ 47%|####7 | 62802/132723 [00:00<00:01, 62271.94KB/s]
+ 53%|#####2 | 69892/132723 [00:01<00:00, 64544.12KB/s]
+ 59%|#####9 | 78446/132723 [00:01<00:00, 70284.40KB/s]
+ 66%|######5 | 86979/132723 [00:01<00:00, 74509.74KB/s]
+ 72%|#######1 | 95553/132723 [00:01<00:00, 77722.67KB/s]
+ 78%|#######8 | 104138/132723 [00:01<00:00, 80080.06KB/s]
+ 85%|########4 | 112659/132723 [00:01<00:00, 81581.73KB/s]
+ 91%|#########1| 120916/132723 [00:01<00:00, 78810.44KB/s]
+ 97%|#########7| 129357/132723 [00:01<00:00, 80424.65KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72815.76KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -517,7 +517,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.158 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.759 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 e6d3f3b998..e8d3511d57 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>12:43.650</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:21.195</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:14.701</p></td>
+<td><p>03:24.617</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:59.158</p></td>
+<td><p>03:07.759</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>02:22.886</p></td>
+<td><p>02:34.418</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>01:35.136</p></td>
+<td><p>01:35.418</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>01:06.201</p></td>
+<td><p>01:08.490</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>00:35.965</p></td>
+<td><p>00:37.931</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:24.957</p></td>
+<td><p>00:26.574</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.640</p></td>
+<td><p>00:25.982</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index b743c7d659..acf1494dbf 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.zipd5949416-3aab-4080-b5de-b79dd81af330 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.zip7345efd8-eac1-43d9-a3f9-0167c607efcb 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 12b2a757aa..4dff9371d8 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>00:47.430</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:48.148</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>00:43.996</p></td>
+<td><p>00:44.593</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>00:02.405</p></td>
+<td><p>00:02.472</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>00:01.022</p></td>
+<td><p>00:01.075</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 7bd8a5cd56..f13e333f15 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: 6658us [6658us] (46.18%; 46.18%)
-FoldScaleAxis: 7759us [5us] (53.82%; 53.82%)
- FoldConstant: 7753us [1594us] (53.78%; 99.93%)
- InferType: 6159us [6159us] (42.72%; 79.44%)
+InferType: 7025us [7025us] (46.70%; 46.70%)
+FoldScaleAxis: 8017us [8us] (53.30%; 53.30%)
+ FoldConstant: 8010us [1610us] (53.25%; 99.90%)
+ InferType: 6400us [6400us] (42.54%; 79.90%)
</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: 6256us [6256us] (44.66%; 44.66%)
-FoldScaleAxis: 7752us [5us] (55.34%; 55.34%)
- FoldConstant: 7747us [1624us] (55.31%; 99.94%)
- InferType: 6123us [6123us] (43.71%; 79.03%)
+InferType: 6450us [6450us] (44.74%; 44.74%)
+FoldScaleAxis: 7968us [6us] (55.26%; 55.26%)
+ FoldConstant: 7962us [1637us] (55.22%; 99.93%)
+ InferType: 6325us [6325us] (43.87%; 79.44%)
</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 71c1606c6a..375b3e7287 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: 35.942497 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.122657 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 ffc21e5b51..c04b6f1e2a 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -916,7 +916,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.026060 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.888048 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 6fce7a2688..b6b5b22dd0 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: 0.018568
-Baseline: 3.441783
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019520
+Baseline: 3.272778
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -535,7 +535,7 @@ 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: 0.296655
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.329867
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -602,7 +602,7 @@ 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: 0.331357
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.351991
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -663,7 +663,7 @@ 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: 0.115943
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.124557
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -746,7 +746,7 @@ 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: 0.109887
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110050
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -832,7 +832,7 @@ 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: 0.112823
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112547
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -922,7 +922,7 @@ 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: 0.147258
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147820
</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 a0dc35136e..3e16de42d8 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>00:34.862</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.347</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>00:32.351</p></td>
+<td><p>00:32.717</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>00:01.458</p></td>
+<td><p>00:01.460</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>00:01.054</p></td>
+<td><p>00:01.170</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 61cd86aeb1..0143cad8b0 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>08:59.762</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:12.525</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>05:32.526</p></td>
+<td><p>05:41.227</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>01:32.468</p></td>
+<td><p>01:34.407</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>01:03.203</p></td>
+<td><p>01:04.585</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:28.524</p></td>
+<td><p>00:28.369</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>00:11.928</p></td>
+<td><p>00:12.364</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>00:11.112</p></td>
+<td><p>00:11.573</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 e7610cce76..e39371960c 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
@@ -1017,7 +1017,7 @@ 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: 0.367 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.350 ms
</pre></div>
</div>
</div>
@@ -1580,7 +1580,7 @@ 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 32.526 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 41.227 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 733420e052..2a2ee34e4b 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)
- 8.1633 8.1624 8.1698 8.1577 0.0050
+ 8.2170 8.2206 8.2239 8.2064 0.0076
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.203 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.585 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 ff72abbd53..810d317819 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)
- 762.6226 762.3649 764.3096 761.1933 1.2852
+ 756.7097 756.4098 757.4577 756.2616 0.5324
</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 32.468 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.407 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 4e896bf144..04e3e7ea11 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,527 +632,78 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- compute_5: Buffer(compute_4, float32, [128], [])[0] = 0f32
- compute_5[1] = 0f32
- compute_5[2] = 0f32
- compute_5[3] = 0f32
- compute_5[4] = 0f32
- compute_5[5] = 0f32
- compute_5[6] = 0f32
- compute_5[7] = 0f32
- compute_5[8] = 0f32
- compute_5[9] = 0f32
- compute_5[10] = 0f32
- compute_5[11] = 0f32
- compute_5[12] = 0f32
- compute_5[13] = 0f32
- compute_5[14] = 0f32
- compute_5[15] = 0f32
- compute_5[16] = 0f32
- compute_5[17] = 0f32
- compute_5[18] = 0f32
- compute_5[19] = 0f32
- compute_5[20] = 0f32
- compute_5[21] = 0f32
- compute_5[22] = 0f32
- compute_5[23] = 0f32
- compute_5[24] = 0f32
- compute_5[25] = 0f32
- compute_5[26] = 0f32
- compute_5[27] = 0f32
- compute_5[28] = 0f32
- compute_5[29] = 0f32
- compute_5[30] = 0f32
- compute_5[31] = 0f32
- compute_5[32] = 0f32
- compute_5[33] = 0f32
- compute_5[34] = 0f32
- compute_5[35] = 0f32
- compute_5[36] = 0f32
- compute_5[37] = 0f32
- compute_5[38] = 0f32
- compute_5[39] = 0f32
- compute_5[40] = 0f32
- compute_5[41] = 0f32
- compute_5[42] = 0f32
- compute_5[43] = 0f32
- compute_5[44] = 0f32
- compute_5[45] = 0f32
- compute_5[46] = 0f32
- compute_5[47] = 0f32
- compute_5[48] = 0f32
- compute_5[49] = 0f32
- compute_5[50] = 0f32
- compute_5[51] = 0f32
- compute_5[52] = 0f32
- compute_5[53] = 0f32
- compute_5[54] = 0f32
- compute_5[55] = 0f32
- compute_5[56] = 0f32
- compute_5[57] = 0f32
- compute_5[58] = 0f32
- compute_5[59] = 0f32
- compute_5[60] = 0f32
- compute_5[61] = 0f32
- compute_5[62] = 0f32
- compute_5[63] = 0f32
- compute_5[64] = 0f32
- compute_5[65] = 0f32
- compute_5[66] = 0f32
- compute_5[67] = 0f32
- compute_5[68] = 0f32
- compute_5[69] = 0f32
- compute_5[70] = 0f32
- compute_5[71] = 0f32
- compute_5[72] = 0f32
- compute_5[73] = 0f32
- compute_5[74] = 0f32
- compute_5[75] = 0f32
- compute_5[76] = 0f32
- compute_5[77] = 0f32
- compute_5[78] = 0f32
- compute_5[79] = 0f32
- compute_5[80] = 0f32
- compute_5[81] = 0f32
- compute_5[82] = 0f32
- compute_5[83] = 0f32
- compute_5[84] = 0f32
- compute_5[85] = 0f32
- compute_5[86] = 0f32
- compute_5[87] = 0f32
- compute_5[88] = 0f32
- compute_5[89] = 0f32
- compute_5[90] = 0f32
- compute_5[91] = 0f32
- compute_5[92] = 0f32
- compute_5[93] = 0f32
- compute_5[94] = 0f32
- compute_5[95] = 0f32
- compute_5[96] = 0f32
- compute_5[97] = 0f32
- compute_5[98] = 0f32
- compute_5[99] = 0f32
- compute_5[100] = 0f32
- compute_5[101] = 0f32
- compute_5[102] = 0f32
- compute_5[103] = 0f32
- compute_5[104] = 0f32
- compute_5[105] = 0f32
- compute_5[106] = 0f32
- compute_5[107] = 0f32
- compute_5[108] = 0f32
- compute_5[109] = 0f32
- compute_5[110] = 0f32
- compute_5[111] = 0f32
- compute_5[112] = 0f32
- compute_5[113] = 0f32
- compute_5[114] = 0f32
- compute_5[115] = 0f32
- compute_5[116] = 0f32
- compute_5[117] = 0f32
- compute_5[118] = 0f32
- compute_5[119] = 0f32
- compute_5[120] = 0f32
- compute_5[121] = 0f32
- compute_5[122] = 0f32
- compute_5[123] = 0f32
- compute_5[124] = 0f32
- compute_5[125] = 0f32
- compute_5[126] = 0f32
- compute_5[127] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[0] = (compute_5[0] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[1] = (compute_5[1] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[2] = (compute_5[2] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[3] = (compute_5[3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[4] = (compute_5[4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[5] = (compute_5[5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[6] = (compute_5[6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[7] = (compute_5[7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[8] = (compute_5[8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[9] = (compute_5[9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[10] = (compute_5[10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[11] = (compute_5[11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[12] = (compute_5[12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[13] = (compute_5[13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[14] = (compute_5[14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[15] = (compute_5[15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[16] = (compute_5[16] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[17] = (compute_5[17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[18] = (compute_5[18] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[19] = (compute_5[19] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[20] = (compute_5[20] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[21] = (compute_5[21] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[22] = (compute_5[22] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[23] = (compute_5[23] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[24] = (compute_5[24] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[25] = (compute_5[25] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[26] = (compute_5[26] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[27] = (compute_5[27] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[28] = (compute_5[28] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[29] = (compute_5[29] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[30] = (compute_5[30] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[31] = (compute_5[31] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 256)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[32] = (compute_5[32] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[33] = (compute_5[33] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[34] = (compute_5[34] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[35] = (compute_5[35] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[36] = (compute_5[36] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[37] = (compute_5[37] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[38] = (compute_5[38] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[39] = (compute_5[39] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[40] = (compute_5[40] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[41] = (compute_5[41] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[42] = (compute_5[42] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[43] = (compute_5[43] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[44] = (compute_5[44] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[45] = (compute_5[45] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[46] = (compute_5[46] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[47] = (compute_5[47] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 512)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[48] = (compute_5[48] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[49] = (compute_5[49] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[50] = (compute_5[50] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[51] = (compute_5[51] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[52] = (compute_5[52] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[53] = (compute_5[53] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[54] = (compute_5[54] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[55] = (compute_5[55] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[56] = (compute_5[56] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[57] = (compute_5[57] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[58] = (compute_5[58] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[59] = (compute_5[59] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[60] = (compute_5[60] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[61] = (compute_5[61] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[62] = (compute_5[62] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[63] = (compute_5[63] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 768)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[64] = (compute_5[64] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[65] = (compute_5[65] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[66] = (compute_5[66] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[67] = (compute_5[67] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[68] = (compute_5[68] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[69] = (compute_5[69] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[70] = (compute_5[70] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[71] = (compute_5[71] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[72] = (compute_5[72] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[73] = (compute_5[73] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[74] = (compute_5[74] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[75] = (compute_5[75] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[76] = (compute_5[76] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[77] = (compute_5[77] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[78] = (compute_5[78] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[79] = (compute_5[79] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1024)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[80] = (compute_5[80] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[81] = (compute_5[81] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[82] = (compute_5[82] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[83] = (compute_5[83] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[84] = (compute_5[84] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[85] = (compute_5[85] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[86] = (compute_5[86] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[87] = (compute_5[87] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[88] = (compute_5[88] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[89] = (compute_5[89] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[90] = (compute_5[90] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[91] = (compute_5[91] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[92] = (compute_5[92] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[93] = (compute_5[93] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[94] = (compute_5[94] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[95] = (compute_5[95] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1280)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[96] = (compute_5[96] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[97] = (compute_5[97] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[98] = (compute_5[98] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[99] = (compute_5[99] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[100] = (compute_5[100] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[101] = (compute_5[101] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[102] = (compute_5[102] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[103] = (compute_5[103] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[104] = (compute_5[104] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[105] = (compute_5[105] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[106] = (compute_5[106] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[107] = (compute_5[107] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[108] = (compute_5[108] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[109] = (compute_5[109] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[110] = (compute_5[110] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[111] = (compute_5[111] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1536)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[112] = (compute_5[112] + (placeholder_1[((placeholder_3[i1.outer]*16) + (elem_idx*16))]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[113] = (compute_5[113] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[114] = (compute_5[114] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[115] = (compute_5[115] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[116] = (compute_5[116] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[117] = (compute_5[117] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[118] = (compute_5[118] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[119] = (compute_5[119] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[120] = (compute_5[120] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[121] = (compute_5[121] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[122] = (compute_5[122] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[123] = (compute_5[123] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[124] = (compute_5[124] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[125] = (compute_5[125] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[126] = (compute_5[126] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])), dtype=bool) {
- compute_5[127] = (compute_5[127] + (placeholder_1[(((placeholder_3[i1.outer]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i0.outer*2048) + placeholder_2[(placeholder_3[i1.outer] + elem_idx)]) + 1792)], 0f32)))
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 64) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
+ }
+ }
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_1: int32 = (((i0.outer*4096) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_1, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_1, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -1190,7 +741,7 @@ 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: 2.699 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.867 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 abe2b2f38e..8bb3db4b6d 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>00:34.526</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:42.673</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,18 +349,18 @@
</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>00:34.489</p></td>
+<td><p>00:42.637</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 71dffaec42..0fbf957f2f 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 52.03/52.03 result: MeasureResult(costs=(0.00444939392,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1304433345794678, timestamp=1667601805.408173) [('tile_f', [-1, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,652190
-No: 2 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+No: 1 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -690,8 +689,9 @@ 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, 1, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7734574
-No: 3 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9151438
+No: 2 GFLOPS: 5.35/5.35 result: MeasureResult(costs=(0.04331021475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.208069086074829, timestamp=1667603786.1221526) [('tile_f', [-1, 8, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4137466
+No: 3 GFLOPS: 0.00/5.35 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
@@ -813,8 +813,8 @@ 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, 16, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7832639
-No: 4 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9510308
+No: 4 GFLOPS: 0.00/5.35 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
@@ -936,8 +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, 64, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7281042
-No: 5 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,938070
+No: 5 GFLOPS: 0.00/5.35 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
@@ -1059,8 +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, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6032563
-No: 6 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4164494
+No: 6 GFLOPS: 0.00/5.35 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
@@ -1182,8 +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, 32, 4]), ('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', 1500), ('unroll_explicit', 0)],None,4588891
-No: 7 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8838442
+No: 7 GFLOPS: 0.00/5.35 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
@@ -1305,9 +1305,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10015472
-No: 8 GFLOPS: 41.42/52.03 result: MeasureResult(costs=(0.005589530499999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.621019124984741, timestamp=1667601811.0111692) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4850626
-No: 9 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1267715
+No: 8 GFLOPS: 0.00/5.35 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
@@ -1429,8 +1428,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('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', 512), ('unroll_explicit', 1)],None,8572150
-No: 10 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3923526
+No: 9 GFLOPS: 0.00/5.35 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
@@ -1552,8 +1551,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10334589
-No: 11 GFLOPS: 0.00/52.03 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3415624
+No: 10 GFLOPS: 0.00/5.35 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
@@ -1675,13 +1674,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1414509
-No: 12 GFLOPS: 6.99/52.03 result: MeasureResult(costs=(0.033106311750000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4201440811157227, timestamp=1667601813.6674936) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8875092
-No: 13 GFLOPS: 3.77/52.03 result: MeasureResult(costs=(0.06132851025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.819613695144653, timestamp=1667601818.6682076) [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,6983210
-No: 14 GFLOPS: 124.47/124.47 result: MeasureResult(costs=(0.0018598417962962961,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4296081066131592, timestamp=1667601819.3106053) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2724816
-No: 15 GFLOPS: 75.91/124.47 result: MeasureResult(costs=(0.003049750333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5480942726135254, timestamp=1667601819.9488645) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9891422
-No: 16 GFLOPS: 292.09/292.09 result: MeasureResult(costs=(0.0007925611317829458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8134474754333496, timestamp=1667601820.614421) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
-No: 17 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4663394
+No: 11 GFLOPS: 96.28/96.28 result: MeasureResult(costs=(0.0024043351904761904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.108785390853882, timestamp=1667603791.5522077) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7043327
+No: 12 GFLOPS: 263.47/263.47 result: MeasureResult(costs=(0.0008786647912087911,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3370120525360107, timestamp=1667603792.477356) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3684274
+No: 13 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1803,9 +1799,9 @@ 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, 8, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9800932
-No: 18 GFLOPS: 10.11/292.09 result: MeasureResult(costs=(0.022908447166666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7610547542572021, timestamp=1667601822.5637784) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5355174
-No: 19 GFLOPS: 0.00/292.09 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3020507
+No: 14 GFLOPS: 70.59/263.47 result: MeasureResult(costs=(0.0032796786458333337,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.527655124664307, timestamp=1667603801.1912084) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9201943
+No: 15 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1927,8 +1923,256 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2966493
-No: 20 GFLOPS: 30.46/292.09 result: MeasureResult(costs=(0.0075998355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.213226318359375, timestamp=1667601823.2526355) [('tile_f', [-1, 16, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3484859
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9789138
+No: 16 GFLOPS: 22.24/263.47 result: MeasureResult(costs=(0.0104088668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1757991313934326, timestamp=1667603801.9348376) [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7948247
+No: 17 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1714464
+No: 18 GFLOPS: 20.63/263.47 result: MeasureResult(costs=(0.011222229,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.527989149093628, timestamp=1667603805.6439786) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5112599
+No: 19 GFLOPS: 0.00/263.47 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
+ func = build(s, args, target_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1731
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1671
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1631
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1646
+ 13: operator()
+ at ../src/driver/driver_api.cc:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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:391
+ 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:377
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:272
+ 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, 1, 4, 64]), ('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', 0), ('unroll_explicit', 1)],None,5722627
+No: 20 GFLOPS: 511.07/511.07 result: MeasureResult(costs=(0.00045297245480225987,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3503856658935547, timestamp=1667603806.6087162) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,40934
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -1967,9 +2211,9 @@ 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, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8916687
+[('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,40934
Finish loading 20 records
-Time cost of this operator: 0.001197
+Time cost of this operator: 0.000806
</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 6a076bfc33..420fe4c953 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -595,10 +595,10 @@ 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 310.0 98.727 (1, 2, 10, 10, 3) 2 1 [310.0]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.022 0.962 (1, 6, 10, 10) 1 1 [3.022]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.976 0.311 (1, 1, 10, 10, 3) 1 1 [0.976]
-Total_time - 313.997 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.5 98.718 (1, 2, 10, 10, 3) 2 1 [310.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.06 0.973 (1, 6, 10, 10) 1 1 [3.06]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.309 (1, 1, 10, 10, 3) 1 1 [0.973]
+Total_time - 314.533 - - - - -
</pre></div>
</div>
</div>
@@ -649,10 +649,10 @@ 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 100.2 97.318 (1, 6, 10, 10, 1) 2 1 [100.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.719 (1, 6, 10, 10) 1 1 [1.77]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.991 0.963 (1, 1, 10, 10, 3) 1 1 [0.991]
-Total_time - 102.961 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.7 97.445 (1, 6, 10, 10, 1) 2 1 [102.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.814 1.721 (1, 6, 10, 10) 1 1 [1.814]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.878 0.834 (1, 3, 10, 10, 1) 1 1 [0.878]
+Total_time - 105.392 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 745d058531..d92154a1ae 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -529,7 +529,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpgluqejqp/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpy8rx4kkp/images/random'
</pre></div>
</div>
</div>
@@ -589,8 +589,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpgluqejqp/images/target contains 8144 images
-/tmp/tmpgluqejqp/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpy8rx4kkp/images/target contains 8144 images
+/tmp/tmpy8rx4kkp/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -702,13 +702,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2240 - accuracy: 0.9252 - val_loss: 0.2493 - val_accuracy: 0.9173 - 47s/epoch - 143ms/step
+328/328 - 47s - loss: 0.2071 - accuracy: 0.9284 - val_loss: 0.1229 - val_accuracy: 0.9592 - 47s/epoch - 144ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0901 - accuracy: 0.9658 - val_loss: 0.1571 - val_accuracy: 0.9532 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.0883 - accuracy: 0.9680 - val_loss: 0.1032 - val_accuracy: 0.9698 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0640 - accuracy: 0.9754 - val_loss: 0.1400 - val_accuracy: 0.9535 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.0661 - accuracy: 0.9759 - val_loss: 0.1043 - val_accuracy: 0.9641 - 44s/epoch - 133ms/step
-<keras.callbacks.History object at 0x7f76be7e4590>
+<keras.callbacks.History object at 0x7fa9fc193b10>
</pre></div>
</div>
</div>
@@ -970,7 +970,7 @@ 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 38.646 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.026 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 0baf71fc7f..e5d00d72e5 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>05:39.446</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:38.679</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:38.646</p></td>
+<td><p>04:35.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:49.358</p></td>
+<td><p>00:51.166</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.718</p></td>
+<td><p>00:08.625</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.722</p></td>
+<td><p>00:03.859</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index e30003a41b..a4717976ca 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>00:43.480</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.312</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>00:31.638</p></td>
+<td><p>00:33.430</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>00:10.128</p></td>
+<td><p>00:10.280</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>00:01.707</p></td>
+<td><p>00:01.596</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 7b3eb0914a..9fb0d941ef 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 0x7f770e8c5320>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa9f86d79e0>
</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 2d7e9689cb..43b46b21cb 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>00:06.008</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.827</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:03.693</p></td>
+<td><p>00:05.414</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>00:01.007</p></td>
+<td><p>00:01.043</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>00:00.557</p></td>
+<td><p>00:00.587</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>00:00.539</p></td>
+<td><p>00:00.563</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>00:00.118</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.049</p></td>
+<td><p>00:00.051</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.029</p></td>
+<td><p>00:00.030</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 44c222e640..2e0f3a99fc 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -590,7 +590,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp2l4a8w3x/input0.cc'\nsource_filename = \"/tmp/tmp2l4a8w3x/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/tmp507f7oi0/input0.cc'\nsource_filename = \"/tmp/tmp507f7oi0/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 3be3c88b46..88c953b44a 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 04eb5e21ec..039014ccde 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/dec74cb93/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 19a9688ec7..efff3b45f8 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/dec74cb93/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 4ef4ffc34d..b412536f1f 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/dec74cb93/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 fad1657030..e466c032d6 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/dec74cb93/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 65c346e62d..37bcea7d0b 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/dec74cb93/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 8ac31d7e30..546baa72cd 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/dec74cb93/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 bbbc985ff2..886aba5931 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/dec74cb93/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 acb1e3af56..c3dba392d8 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/dec74cb93/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 8781a719d0..327a9c47a9 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/dec74cb93/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 91f428cea7..7976a033bd 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/dec74cb93/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 7020181fdb..b4c49d1edb 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/dec74cb93/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 8bf5324dad..73399dcaf1 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/dec74cb93/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 395d76206d..772e2e29df 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/dec74cb93/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 9fee72176f..05bc78daf9 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/dec74cb93/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 340643ddf4..1326eacfc9 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/dec74cb93/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 5771c5ee7f..47f920745c 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/dec74cb93/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 78c4313647..e8f62e29df 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/dec74cb93/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 875adb5cc6..94c22978b6 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/dec74cb93/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 5dc321ac25..e324212fbb 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/dec74cb93/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 3e8d90b707..5eb0fa8073 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/dec74cb93/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 6703b356db..177753b07d 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/dec74cb93/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 a85e387884..208804610b 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/dec74cb93/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 f7867bda48..93823cda41 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/dec74cb93/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 e4a63b7e8e..7e3e2532a1 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/dec74cb93/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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/dec74cb93/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/be44e9c81/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 a0383c386c..e7ed476b45 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 0fc88f8503..8df973d4f4 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>00:26.196</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:27.380</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:26.190</p></td>
+<td><p>00:27.374</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 40b297aae2..29784e23de 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 28.99s!
+resnet18_v1 inference graph built in 30.16s!
</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 afa2d98e14..4bbe62034c 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 19.58s!
+yolov3-tiny inference graph built in 20.11s!
</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 ca3fa9d80c..7a39bf59b4 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>01:40.948</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:42.163</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>00:51.872</p></td>
+<td><p>00:52.222</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>00:49.076</p></td>
+<td><p>00:49.941</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 edc0600b4c..fcc7d6ea4b 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>00:03.100</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.184</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>00:02.662</p></td>
+<td><p>00:02.723</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>00:00.461</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 7c131aeb1c..d5f33029fb 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>00:00.781</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.800</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.416</p></td>
+<td><p>00:00.424</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.365</p></td>
+<td><p>00:00.376</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index d42e5630e9..40ac342c43 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,9 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-</pre></div>
-</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -581,7 +578,7 @@ 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: 93.653 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.760 ms
</pre></div>
</div>
</div>
@@ -645,7 +642,6 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-*E
</pre></div>
</div>
</div>
@@ -656,7 +652,7 @@ 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 34.020 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.577 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 59ed9c0dfc..98e692017d 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: 9.11/9.11 result: MeasureResult(costs=(0.0294639272,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.704277515411377, timestamp=1667600439.8011644) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
-No: 2 GFLOPS: 12.36/12.36 result: MeasureResult(costs=(0.0217097956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5637028217315674, timestamp=1667600440.3613122) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
-No: 3 GFLOPS: 11.60/12.36 result: MeasureResult(costs=(0.0231313244,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5525696277618408, timestamp=1667600441.6351473) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
-No: 4 GFLOPS: 1.47/12.36 result: MeasureResult(costs=(0.1826311896,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.058821201324463, timestamp=1667600445.453223) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.93/12.36 result: MeasureResult(costs=(0.0683016298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.27158522605896, timestamp=1667600446.8736937) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
-No: 6 GFLOPS: 14.41/14.41 result: MeasureResult(costs=(0.0186263354,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5002939701080322, timestamp=1667600447.3361092) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
-No: 7 GFLOPS: 3.38/14.41 result: MeasureResult(costs=(0.0793295266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4188477993011475, timestamp=1667600449.5113862) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
-No: 8 GFLOPS: 1.55/14.41 result: MeasureResult(costs=(0.1729946346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9581708908081055, timestamp=1667600452.491676) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 9 GFLOPS: 12.10/14.41 result: MeasureResult(costs=(0.022181018,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.48445558547973633, timestamp=1667600453.0983562) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
-No: 10 GFLOPS: 4.09/14.41 result: MeasureResult(costs=(0.065693861,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.17677903175354, timestamp=1667600454.3130083) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+No: 1 GFLOPS: 2.31/2.31 result: MeasureResult(costs=(0.1160156268,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0121259689331055, timestamp=1667602369.0228992) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+No: 2 GFLOPS: 3.92/3.92 result: MeasureResult(costs=(0.0685516924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3405766487121582, timestamp=1667602370.328644) [('tile_y', [-1, 64]), ('tile_x', [-1, 16])],None,46
+No: 3 GFLOPS: 9.43/9.43 result: MeasureResult(costs=(0.0284811056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5838117599487305, timestamp=1667602371.7321346) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+No: 4 GFLOPS: 3.62/9.43 result: MeasureResult(costs=(0.0741042682,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3438503742218018, timestamp=1667602373.8630242) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+No: 5 GFLOPS: 2.26/9.43 result: MeasureResult(costs=(0.11880267679999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0534772872924805, timestamp=1667602376.0872216) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 6 GFLOPS: 0.50/9.43 result: MeasureResult(costs=(0.5336246658,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.70423412322998, timestamp=1667602384.796229) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+No: 7 GFLOPS: 3.62/9.43 result: MeasureResult(costs=(0.0741095866,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3492913246154785, timestamp=1667602386.9151893) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+No: 8 GFLOPS: 11.67/11.67 result: MeasureResult(costs=(0.0229932958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6112122535705566, timestamp=1667602387.4983776) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+No: 9 GFLOPS: 2.52/11.67 result: MeasureResult(costs=(0.10667436239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8538415431976318, timestamp=1667602389.4771836) [('tile_y', [-1, 512]), ('tile_x', [-1, 8])],None,39
+No: 10 GFLOPS: 12.81/12.81 result: MeasureResult(costs=(0.0209618688,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.4951808452606201, timestamp=1667602389.9840531) [('tile_y', [-1, 8]), ('tile_x', [-1, 512])],None,93
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 1b4ad7bc84..196cbf16e4 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': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 516.3002476199927, 'median': 517.2048575999952, 'std': 2.159932684046858}
</pre></div>
</div>
</div>
@@ -712,179 +712,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 9.96/ 16.73 GFLOPS | Progress: (4/20) | 7.40 s
-[Task 1/25] Current/Best: 11.33/ 16.73 GFLOPS | Progress: (8/20) | 11.02 s
-[Task 1/25] Current/Best: 16.79/ 19.58 GFLOPS | Progress: (12/20) | 13.33 s
-[Task 1/25] Current/Best: 6.67/ 19.58 GFLOPS | Progress: (16/20) | 18.63 s
-[Task 1/25] Current/Best: 8.51/ 19.58 GFLOPS | Progress: (20/20) | 21.25 s Done.
+[Task 1/25] Current/Best: 5.77/ 22.39 GFLOPS | Progress: (4/20) | 7.09 s
+[Task 1/25] Current/Best: 7.95/ 23.79 GFLOPS | Progress: (8/20) | 10.20 s
+[Task 1/25] Current/Best: 6.00/ 23.79 GFLOPS | Progress: (12/20) | 12.75 s
+[Task 1/25] Current/Best: 17.83/ 23.79 GFLOPS | Progress: (16/20) | 16.23 s
+[Task 1/25] Current/Best: 6.07/ 23.79 GFLOPS | Progress: (20/20) | 18.60 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 13.25/ 18.20 GFLOPS | Progress: (4/20) | 3.00 s
-[Task 2/25] Current/Best: 5.95/ 18.20 GFLOPS | Progress: (8/20) | 4.61 s
-[Task 2/25] Current/Best: 11.49/ 18.80 GFLOPS | Progress: (12/20) | 6.02 s
-[Task 2/25] Current/Best: 13.46/ 18.80 GFLOPS | Progress: (16/20) | 7.03 s
-[Task 2/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (20/20) | 8.78 s Done.
+[Task 2/25] Current/Best: 11.80/ 20.66 GFLOPS | Progress: (4/20) | 2.91 s
+[Task 2/25] Current/Best: 10.53/ 20.66 GFLOPS | Progress: (8/20) | 4.23 s
+[Task 2/25] Current/Best: 8.86/ 20.66 GFLOPS | Progress: (12/20) | 5.97 s
+[Task 2/25] Current/Best: 13.36/ 20.66 GFLOPS | Progress: (16/20) | 7.09 s
+[Task 2/25] Current/Best: 13.75/ 20.66 GFLOPS | Progress: (20/20) | 8.75 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 10.25/ 22.94 GFLOPS | Progress: (4/20) | 4.58 s
-[Task 3/25] Current/Best: 11.97/ 22.94 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 3/25] Current/Best: 20.15/ 22.94 GFLOPS | Progress: (12/20) | 8.93 s
-[Task 3/25] Current/Best: 19.99/ 22.94 GFLOPS | Progress: (16/20) | 10.51 s
-[Task 3/25] Current/Best: 17.59/ 22.94 GFLOPS | Progress: (20/20) | 12.14 s Done.
+[Task 3/25] Current/Best: 3.11/ 12.36 GFLOPS | Progress: (4/20) | 4.17 s
+[Task 3/25] Current/Best: 12.64/ 20.53 GFLOPS | Progress: (8/20) | 6.65 s
+[Task 3/25] Current/Best: 7.48/ 20.53 GFLOPS | Progress: (12/20) | 8.38 s
+[Task 3/25] Current/Best: 15.83/ 20.53 GFLOPS | Progress: (16/20) | 10.96 s
+[Task 3/25] Current/Best: 15.29/ 20.53 GFLOPS | Progress: (20/20) | 12.89 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 13.81/ 14.47 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 4/25] Current/Best: 6.16/ 21.28 GFLOPS | Progress: (8/20) | 9.10 s
-[Task 4/25] Current/Best: 7.51/ 21.28 GFLOPS | Progress: (12/20) | 10.80 s
-[Task 4/25] Current/Best: 7.94/ 21.28 GFLOPS | Progress: (16/20) | 13.27 s
-[Task 4/25] Current/Best: 14.16/ 21.28 GFLOPS | Progress: (20/20) | 16.20 s Done.
+[Task 4/25] Current/Best: 9.54/ 14.64 GFLOPS | Progress: (4/20) | 4.79 s
+[Task 4/25] Current/Best: 11.47/ 17.99 GFLOPS | Progress: (8/20) | 6.89 s
+[Task 4/25] Current/Best: 9.61/ 17.99 GFLOPS | Progress: (12/20) | 8.44 s
+[Task 4/25] Current/Best: 19.22/ 19.22 GFLOPS | Progress: (16/20) | 12.72 s
+[Task 4/25] Current/Best: 6.30/ 20.05 GFLOPS | Progress: (20/20) | 14.43 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 11.69/ 11.69 GFLOPS | Progress: (4/20) | 3.33 s
-[Task 5/25] Current/Best: 13.64/ 13.64 GFLOPS | Progress: (8/20) | 5.85 s
-[Task 5/25] Current/Best: 15.47/ 15.47 GFLOPS | Progress: (12/20) | 7.71 s
-[Task 5/25] Current/Best: 18.38/ 18.38 GFLOPS | Progress: (16/20) | 9.12 s
-[Task 5/25] Current/Best: 5.28/ 18.38 GFLOPS | Progress: (20/20) | 10.87 s Done.
+[Task 5/25] Current/Best: 13.18/ 14.89 GFLOPS | Progress: (4/20) | 3.79 s
+[Task 5/25] Current/Best: 4.79/ 14.89 GFLOPS | Progress: (8/20) | 5.70 s
+[Task 5/25] Current/Best: 5.56/ 19.87 GFLOPS | Progress: (12/20) | 7.37 s
+[Task 5/25] Current/Best: 11.76/ 19.87 GFLOPS | Progress: (16/20) | 8.79 s
+[Task 5/25] Current/Best: 14.66/ 19.87 GFLOPS | Progress: (20/20) | 10.45 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 10.65/ 13.49 GFLOPS | Progress: (4/20) | 7.55 s
-[Task 6/25] Current/Best: 13.88/ 17.20 GFLOPS | Progress: (8/20) | 9.27 s
-[Task 6/25] Current/Best: 7.84/ 18.15 GFLOPS | Progress: (12/20) | 12.56 s
-[Task 6/25] Current/Best: 3.76/ 18.15 GFLOPS | Progress: (16/20) | 16.07 s
-[Task 6/25] Current/Best: 7.38/ 18.15 GFLOPS | Progress: (20/20) | 18.38 s Done.
+[Task 6/25] Current/Best: 10.11/ 18.71 GFLOPS | Progress: (4/20) | 4.28 s
+[Task 6/25] Current/Best: 4.60/ 20.02 GFLOPS | Progress: (8/20) | 6.92 s
+[Task 6/25] Current/Best: 15.82/ 20.02 GFLOPS | Progress: (12/20) | 9.14 s
+[Task 6/25] Current/Best: 12.45/ 20.02 GFLOPS | Progress: (16/20) | 11.14 s
+[Task 6/25] Current/Best: 6.50/ 20.02 GFLOPS | Progress: (20/20) | 13.56 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 9.46/ 18.88 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 7/25] Current/Best: 17.03/ 18.88 GFLOPS | Progress: (8/20) | 6.21 s
-[Task 7/25] Current/Best: 6.26/ 22.77 GFLOPS | Progress: (12/20) | 8.19 s
-[Task 7/25] Current/Best: 12.70/ 22.77 GFLOPS | Progress: (16/20) | 10.44 s
-[Task 7/25] Current/Best: 11.26/ 22.77 GFLOPS | Progress: (20/20) | 13.24 s Done.
+[Task 7/25] Current/Best: 16.50/ 16.50 GFLOPS | Progress: (4/20) | 3.64 s
+[Task 7/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (8/20) | 5.71 s
+[Task 7/25] Current/Best: 13.87/ 17.45 GFLOPS | Progress: (12/20) | 7.63 s
+[Task 7/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (16/20) | 9.85 s
+[Task 7/25] Current/Best: 22.22/ 22.22 GFLOPS | Progress: (20/20) | 12.28 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 2.74/ 14.22 GFLOPS | Progress: (4/20) | 3.91 s
-[Task 8/25] Current/Best: 13.03/ 14.22 GFLOPS | Progress: (8/20) | 14.63 s
-[Task 8/25] Current/Best: 10.31/ 19.82 GFLOPS | Progress: (12/20) | 17.21 s
-[Task 8/25] Current/Best: 10.18/ 19.82 GFLOPS | Progress: (16/20) | 22.30 s
-[Task 8/25] Current/Best: 12.54/ 19.82 GFLOPS | Progress: (20/20) | 28.31 s Done.
+[Task 8/25] Current/Best: 21.04/ 21.04 GFLOPS | Progress: (4/20) | 3.93 s
+[Task 8/25] Current/Best: 13.56/ 21.04 GFLOPS | Progress: (8/20) | 10.58 s
+[Task 8/25] Current/Best: 7.40/ 21.04 GFLOPS | Progress: (12/20) | 14.94 s
+[Task 8/25] Current/Best: 3.93/ 21.04 GFLOPS | Progress: (16/20) | 17.20 s
+[Task 8/25] Current/Best: 11.13/ 21.04 GFLOPS | Progress: (20/20) | 21.12 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 6.57/ 16.17 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 9/25] Current/Best: 11.91/ 16.46 GFLOPS | Progress: (8/20) | 9.99 s
-[Task 9/25] Current/Best: 11.94/ 16.51 GFLOPS | Progress: (12/20) | 14.73 s
-[Task 9/25] Current/Best: 14.62/ 16.51 GFLOPS | Progress: (16/20) | 16.95 s
-[Task 9/25] Current/Best: 11.01/ 16.51 GFLOPS | Progress: (20/20) | 21.30 s Done.
+[Task 9/25] Current/Best: 4.45/ 21.66 GFLOPS | Progress: (4/20) | 3.70 s
+[Task 9/25] Current/Best: 17.39/ 21.66 GFLOPS | Progress: (8/20) | 5.13 s
+[Task 9/25] Current/Best: 13.57/ 21.66 GFLOPS | Progress: (12/20) | 7.21 s
+[Task 9/25] Current/Best: 7.53/ 21.66 GFLOPS | Progress: (16/20) | 10.36 s
+[Task 9/25] Current/Best: 9.02/ 21.66 GFLOPS | Progress: (20/20) | 13.14 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 3.04/ 13.12 GFLOPS | Progress: (4/20) | 3.50 s
-[Task 10/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (8/20) | 5.21 s
-[Task 10/25] Current/Best: 9.44/ 20.53 GFLOPS | Progress: (12/20) | 6.79 s
-[Task 10/25] Current/Best: 10.75/ 20.53 GFLOPS | Progress: (16/20) | 8.89 s
-[Task 10/25] Current/Best: 11.07/ 22.53 GFLOPS | Progress: (20/20) | 11.75 s Done.
+[Task 10/25] Current/Best: 6.04/ 13.17 GFLOPS | Progress: (4/20) | 3.58 s
+[Task 10/25] Current/Best: 9.52/ 15.47 GFLOPS | Progress: (8/20) | 5.53 s
+[Task 10/25] Current/Best: 1.61/ 17.92 GFLOPS | Progress: (12/20) | 8.12 s
+[Task 10/25] Current/Best: 3.78/ 17.92 GFLOPS | Progress: (16/20) | 10.11 s
+[Task 10/25] Current/Best: 9.99/ 20.28 GFLOPS | Progress: (20/20) | 11.52 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 5.53/ 16.38 GFLOPS | Progress: (4/20) | 3.92 s
-[Task 11/25] Current/Best: 7.67/ 16.38 GFLOPS | Progress: (8/20) | 8.71 s
-[Task 11/25] Current/Best: 12.71/ 22.48 GFLOPS | Progress: (12/20) | 11.07 s
-[Task 11/25] Current/Best: 6.19/ 23.39 GFLOPS | Progress: (16/20) | 13.21 s
-[Task 11/25] Current/Best: 12.35/ 23.57 GFLOPS | Progress: (20/20) | 15.26 s Done.
+[Task 11/25] Current/Best: 8.68/ 20.13 GFLOPS | Progress: (4/20) | 3.84 s
+[Task 11/25] Current/Best: 10.99/ 20.13 GFLOPS | Progress: (8/20) | 6.68 s
+[Task 11/25] Current/Best: 7.63/ 21.63 GFLOPS | Progress: (12/20) | 9.40 s
+[Task 11/25] Current/Best: 13.81/ 21.63 GFLOPS | Progress: (16/20) | 11.66 s
+[Task 11/25] Current/Best: 20.38/ 21.63 GFLOPS | Progress: (20/20) | 13.34 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 13.15/ 14.23 GFLOPS | Progress: (4/20) | 4.37 s
-[Task 12/25] Current/Best: 14.60/ 14.86 GFLOPS | Progress: (8/20) | 6.42 s
-[Task 12/25] Current/Best: 14.31/ 17.83 GFLOPS | Progress: (12/20) | 8.72 s
-[Task 12/25] Current/Best: 3.14/ 17.85 GFLOPS | Progress: (16/20) | 12.32 s
-[Task 12/25] Current/Best: 11.78/ 17.85 GFLOPS | Progress: (20/20) | 15.21 s Done.
+[Task 12/25] Current/Best: 5.22/ 16.79 GFLOPS | Progress: (4/20) | 7.76 s
+[Task 12/25] Current/Best: 11.22/ 16.79 GFLOPS | Progress: (8/20) | 13.65 s
+[Task 12/25] Current/Best: 9.09/ 16.79 GFLOPS | Progress: (12/20) | 16.30 s
+[Task 12/25] Current/Best: 13.18/ 19.12 GFLOPS | Progress: (16/20) | 20.29 s
+[Task 12/25] Current/Best: 18.24/ 19.12 GFLOPS | Progress: (20/20) | 28.84 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 13.81/ 16.10 GFLOPS | Progress: (4/20) | 4.79 s
-[Task 13/25] Current/Best: 5.88/ 17.03 GFLOPS | Progress: (8/20) | 7.68 s
-[Task 13/25] Current/Best: 18.90/ 19.86 GFLOPS | Progress: (12/20) | 10.41 s
-[Task 13/25] Current/Best: 17.16/ 19.86 GFLOPS | Progress: (16/20) | 12.81 s
-[Task 13/25] Current/Best: 11.78/ 22.02 GFLOPS | Progress: (20/20) | 14.46 s Done.
+[Task 13/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (4/20) | 4.08 s
+[Task 13/25] Current/Best: 12.44/ 20.58 GFLOPS | Progress: (8/20) | 7.46 s
+[Task 13/25] Current/Best: 7.46/ 20.58 GFLOPS | Progress: (12/20) | 10.61 s
+[Task 13/25] Current/Best: 15.05/ 20.58 GFLOPS | Progress: (16/20) | 13.16 s
+[Task 13/25] Current/Best: 22.21/ 22.21 GFLOPS | Progress: (20/20) | 16.47 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 6.67/ 16.46 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 14/25] Current/Best: 3.46/ 16.92 GFLOPS | Progress: (8/20) | 6.39 s
-[Task 14/25] Current/Best: 13.43/ 18.46 GFLOPS | Progress: (12/20) | 8.86 s
-[Task 14/25] Current/Best: 9.27/ 21.30 GFLOPS | Progress: (16/20) | 12.71 s
-[Task 14/25] Current/Best: 14.08/ 21.30 GFLOPS | Progress: (20/20) | 14.86 s Done.
-
+[Task 14/25] Current/Best: 17.82/ 17.82 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 14/25] Current/Best: 5.97/ 17.82 GFLOPS | Progress: (8/20) | 6.19 s
+[Task 14/25] Current/Best: 10.37/ 18.98 GFLOPS | Progress: (12/20) | 8.98 s
+[Task 14/25] Current/Best: 9.08/ 18.98 GFLOPS | Progress: (16/20) | 15.74 s
+[Task 14/25] Current/Best: 3.78/ 18.98 GFLOPS | Progress: (20/20) | 18.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 15.12/ 18.05 GFLOPS | Progress: (4/20) | 4.98 s
-[Task 15/25] Current/Best: 16.09/ 22.87 GFLOPS | Progress: (8/20) | 6.18 s
-[Task 15/25] Current/Best: 23.14/ 23.14 GFLOPS | Progress: (12/20) | 7.35 s
-[Task 15/25] Current/Best: 10.22/ 23.14 GFLOPS | Progress: (16/20) | 9.74 s
-[Task 15/25] Current/Best: 18.31/ 23.14 GFLOPS | Progress: (20/20) | 12.04 s
+[Task 15/25] Current/Best: 18.87/ 18.87 GFLOPS | Progress: (4/20) | 5.79 s
+[Task 15/25] Current/Best: 19.15/ 19.15 GFLOPS | Progress: (8/20) | 7.83 s
+[Task 15/25] Current/Best: 9.26/ 20.49 GFLOPS | Progress: (12/20) | 11.34 s
+[Task 15/25] Current/Best: 21.40/ 21.40 GFLOPS | Progress: (16/20) | 14.45 s
+[Task 15/25] Current/Best: 17.00/ 21.40 GFLOPS | Progress: (20/20) | 16.45 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 9.82/ 20.07 GFLOPS | Progress: (4/20) | 4.56 s
-[Task 16/25] Current/Best: 14.09/ 20.65 GFLOPS | Progress: (8/20) | 6.24 s
-[Task 16/25] Current/Best: 16.00/ 20.65 GFLOPS | Progress: (12/20) | 8.14 s
-[Task 16/25] Current/Best: 9.71/ 20.65 GFLOPS | Progress: (16/20) | 9.67 s
-[Task 16/25] Current/Best: 1.56/ 20.65 GFLOPS | Progress: (20/20) | 11.67 s Done.
+[Task 16/25] Current/Best: 7.45/ 14.24 GFLOPS | Progress: (4/20) | 4.67 s
+[Task 16/25] Current/Best: 11.49/ 14.24 GFLOPS | Progress: (8/20) | 7.04 s
+[Task 16/25] Current/Best: 18.64/ 18.64 GFLOPS | Progress: (12/20) | 8.85 s
+[Task 16/25] Current/Best: 20.59/ 20.59 GFLOPS | Progress: (16/20) | 10.58 s
+[Task 16/25] Current/Best: 16.30/ 20.59 GFLOPS | Progress: (20/20) | 13.01 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 10.30/ 22.80 GFLOPS | Progress: (4/20) | 3.59 s
-[Task 17/25] Current/Best: 12.12/ 22.80 GFLOPS | Progress: (8/20) | 6.22 s
-[Task 17/25] Current/Best: 19.29/ 22.80 GFLOPS | Progress: (12/20) | 8.00 s
-[Task 17/25] Current/Best: 12.95/ 23.98 GFLOPS | Progress: (16/20) | 10.21 s
-[Task 17/25] Current/Best: 4.31/ 23.98 GFLOPS | Progress: (20/20) | 13.92 s Done.
+[Task 17/25] Current/Best: 17.03/ 17.03 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 17/25] Current/Best: 16.79/ 20.29 GFLOPS | Progress: (8/20) | 5.73 s
+[Task 17/25] Current/Best: 19.19/ 20.29 GFLOPS | Progress: (12/20) | 7.81 s
+[Task 17/25] Current/Best: 4.88/ 20.29 GFLOPS | Progress: (16/20) | 11.51 s
+[Task 17/25] Current/Best: 5.06/ 22.33 GFLOPS | Progress: (20/20) | 15.89 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 3.01/ 18.11 GFLOPS | Progress: (4/20) | 4.25 s
-[Task 18/25] Current/Best: 13.36/ 18.42 GFLOPS | Progress: (8/20) | 6.55 s
-[Task 18/25] Current/Best: 16.09/ 18.42 GFLOPS | Progress: (12/20) | 8.70 s
-[Task 18/25] Current/Best: 15.68/ 18.42 GFLOPS | Progress: (16/20) | 14.50 s
-[Task 18/25] Current/Best: 11.91/ 21.22 GFLOPS | Progress: (20/20) | 16.91 s Done.
+[Task 18/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (4/20) | 6.63 s
+[Task 18/25] Current/Best: 6.95/ 19.45 GFLOPS | Progress: (8/20) | 8.40 s
+[Task 18/25] Current/Best: 12.40/ 20.78 GFLOPS | Progress: (12/20) | 10.57 s
+[Task 18/25] Current/Best: 16.90/ 20.78 GFLOPS | Progress: (16/20) | 12.70 s
+[Task 18/25] Current/Best: 7.63/ 20.78 GFLOPS | Progress: (20/20) | 17.87 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 9.94/ 21.33 GFLOPS | Progress: (4/20) | 4.67 s
-[Task 19/25] Current/Best: 4.54/ 21.33 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 19/25] Current/Best: 8.71/ 21.33 GFLOPS | Progress: (12/20) | 10.63 s
-[Task 19/25] Current/Best: 7.50/ 21.33 GFLOPS | Progress: (16/20) | 14.04 s
-[Task 19/25] Current/Best: 8.63/ 22.33 GFLOPS | Progress: (20/20) | 16.92 s Done.
+[Task 19/25] Current/Best: 10.46/ 16.14 GFLOPS | Progress: (4/20) | 4.78 s
+[Task 19/25] Current/Best: 10.85/ 16.14 GFLOPS | Progress: (8/20) | 11.05 s
+[Task 19/25] Current/Best: 7.52/ 17.44 GFLOPS | Progress: (12/20) | 13.96 s
+[Task 19/25] Current/Best: 11.13/ 17.44 GFLOPS | Progress: (16/20) | 20.45 s
+[Task 19/25] Current/Best: 6.46/ 17.44 GFLOPS | Progress: (20/20) | 24.06 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.44/ 19.28 GFLOPS | Progress: (4/20) | 4.16 s Done.
+[Task 20/25] Current/Best: 7.66/ 21.18 GFLOPS | Progress: (4/20) | 3.96 s
+[Task 20/25] Current/Best: 3.03/ 21.18 GFLOPS | Progress: (8/20) | 6.73 s
+[Task 20/25] Current/Best: 16.45/ 21.18 GFLOPS | Progress: (12/20) | 9.30 s Done.
+
+[Task 20/25] Current/Best: 11.74/ 21.18 GFLOPS | Progress: (16/20) | 12.04 s
+[Task 20/25] Current/Best: 6.19/ 21.18 GFLOPS | Progress: (20/20) | 14.72 s Done.
-[Task 20/25] Current/Best: 10.13/ 19.28 GFLOPS | Progress: (8/20) | 8.31 s
-[Task 20/25] Current/Best: 7.45/ 19.28 GFLOPS | Progress: (12/20) | 11.42 s
-[Task 20/25] Current/Best: 11.99/ 19.28 GFLOPS | Progress: (16/20) | 14.00 s
-[Task 20/25] Current/Best: 10.01/ 19.28 GFLOPS | Progress: (20/20) | 16.65 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 12.95/ 13.28 GFLOPS | Progress: (4/20) | 3.17 s
-[Task 21/25] Current/Best: 9.26/ 13.28 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 21/25] Current/Best: 8.09/ 14.85 GFLOPS | Progress: (12/20) | 9.02 s
-[Task 21/25] Current/Best: 20.63/ 20.63 GFLOPS | Progress: (16/20) | 10.98 s
-[Task 21/25] Current/Best: 9.05/ 20.63 GFLOPS | Progress: (20/20) | 13.95 s
+[Task 21/25] Current/Best: 4.43/ 10.04 GFLOPS | Progress: (4/20) | 4.27 s
+[Task 21/25] Current/Best: 10.03/ 15.75 GFLOPS | Progress: (8/20) | 6.55 s
+[Task 21/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (12/20) | 8.51 s
+[Task 21/25] Current/Best: 9.27/ 16.95 GFLOPS | Progress: (16/20) | 11.11 s
+[Task 21/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (20/20) | 13.91 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (4/20) | 4.40 s Done.
- Done.
-
-[Task 22/25] Current/Best: 12.76/ 18.94 GFLOPS | Progress: (8/20) | 7.07 s
-[Task 22/25] Current/Best: 14.40/ 18.94 GFLOPS | Progress: (12/20) | 8.32 s
-[Task 22/25] Current/Best: 13.13/ 18.94 GFLOPS | Progress: (16/20) | 10.25 s
-[Task 22/25] Current/Best: 17.79/ 18.94 GFLOPS | Progress: (20/20) | 14.02 s Done.
+[Task 22/25] Current/Best: 15.14/ 15.14 GFLOPS | Progress: (4/20) | 4.47 s
+[Task 22/25] Current/Best: 5.24/ 20.16 GFLOPS | Progress: (8/20) | 5.92 s
+[Task 22/25] Current/Best: 5.25/ 20.16 GFLOPS | Progress: (12/20) | 8.00 s
+[Task 22/25] Current/Best: 2.69/ 20.16 GFLOPS | Progress: (16/20) | 10.61 s
+[Task 22/25] Current/Best: 8.60/ 20.16 GFLOPS | Progress: (20/20) | 12.71 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 10.79/ 20.38 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 23/25] Current/Best: 19.95/ 20.38 GFLOPS | Progress: (8/20) | 7.42 s
-[Task 23/25] Current/Best: 9.95/ 20.38 GFLOPS | Progress: (12/20) | 10.94 s
-[Task 23/25] Current/Best: 9.07/ 20.38 GFLOPS | Progress: (16/20) | 14.10 s
-[Task 23/25] Current/Best: 11.54/ 20.38 GFLOPS | Progress: (20/20) | 16.86 s Done.
+[Task 23/25] Current/Best: 12.84/ 22.88 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 23/25] Current/Best: 20.80/ 22.88 GFLOPS | Progress: (8/20) | 6.35 s
+[Task 23/25] Current/Best: 13.03/ 22.88 GFLOPS | Progress: (12/20) | 9.10 s
+[Task 23/25] Current/Best: 13.00/ 22.88 GFLOPS | Progress: (16/20) | 11.82 s
+[Task 23/25] Current/Best: 3.09/ 22.88 GFLOPS | Progress: (20/20) | 17.02 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (4/20) | 12.21 s
-[Task 24/25] Current/Best: 6.01/ 9.98 GFLOPS | Progress: (8/20) | 22.92 s
-[Task 24/25] Current/Best: 5.54/ 9.98 GFLOPS | Progress: (12/20) | 34.54 s
-[Task 24/25] Current/Best: 3.26/ 9.98 GFLOPS | Progress: (16/20) | 46.01 s
-[Task 24/25] Current/Best: 8.05/ 9.98 GFLOPS | Progress: (20/20) | 57.51 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25] Current/Best: 2.79/ 8.54 GFLOPS | Progress: (4/20) | 4.55 s
-[Task 25/25] Current/Best: 5.71/ 9.35 GFLOPS | Progress: (8/20) | 9.37 s
-[Task 25/25] Current/Best: 1.55/ 9.46 GFLOPS | Progress: (12/20) | 10.77 s
-[Task 25/25] Current/Best: 8.71/ 9.46 GFLOPS | Progress: (16/20) | 21.06 s
-[Task 25/25] Current/Best: 5.79/ 9.46 GFLOPS | Progress: (20/20) | 32.71 s
+[Task 24/25] Current/Best: 5.46/ 10.04 GFLOPS | Progress: (4/20) | 8.04 s
+[Task 24/25] Current/Best: 1.54/ 10.04 GFLOPS | Progress: (8/20) | 19.09 s
+[Task 24/25] Current/Best: 3.89/ 10.04 GFLOPS | Progress: (12/20) | 21.34 s Done.
+
+[Task 24/25] Current/Best: 1.56/ 10.04 GFLOPS | Progress: (16/20) | 31.76 s
+[Task 24/25] Current/Best: 7.00/ 10.04 GFLOPS | Progress: (20/20) | 42.03 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 9.41/ 9.41 GFLOPS | Progress: (4/20) | 12.26 s
+[Task 25/25] Current/Best: 2.67/ 9.41 GFLOPS | Progress: (8/20) | 23.70 s
+[Task 25/25] Current/Best: 8.17/ 9.41 GFLOPS | Progress: (12/20) | 35.61 s Done.
+
+[Task 25/25] Current/Best: 4.79/ 9.41 GFLOPS | Progress: (16/20) | 46.33 s
+[Task 25/25] Current/Best: 3.00/ 9.41 GFLOPS | Progress: (20/20) | 57.87 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -945,8 +945,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
-class='n02123159 tiger cat' with probability=0.356379
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
+class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -983,8 +983,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 406.0337182000035, 'median': 406.1050522000073, 'std': 1.1477014024438263}
-unoptimized: {'mean': 513.8701477699988, 'median': 513.6327808999965, 'std': 1.3264686737052278}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 402.4906679900005, 'median': 402.483829699986, 'std': 0.8240857902972529}
+unoptimized: {'mean': 516.3002476199927, 'median': 517.2048575999952, 'std': 2.159932684046858}
</pre></div>
</div>
</div>
@@ -998,7 +998,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 52.900 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 9.699 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 fde4b84011..6e0eba29b6 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>1.506e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.253e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index eba5eea6fa..47bbb31bd8 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -497,7 +497,7 @@ 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, 0x5610c10)), stage(b, placeholder(b, 0x22961a50)), 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, 0x22852f00)), stage(b, placeholder(b, 0x1b0326f0)), 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 10c06784a1..ca70da4beb 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>14:24.924</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:33.911</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:52.900</p></td>
+<td><p>11:09.699</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>01:34.020</p></td>
+<td><p>01:19.577</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.016</p></td>
+<td><p>00:59.627</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:35.795</p></td>
+<td><p>00:36.607</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:19.028</p></td>
+<td><p>00:26.903</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>00:01.230</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.780</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.757</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.545</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.169</p></td>
+<td><p>00:00.166</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 814e3cae29..8d04706e5e 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -673,10 +673,10 @@ 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 7.90564999988419e-06 1.0
- naive 6.6824e-06 0.8452688899834789
-parallel 6.9530999999999995e-06 0.879510223713655
- vector 2.4559499999999998e-05 3.1065756769348214
+ numpy 7.669649999115791e-06 1.0
+ naive 6.7220999999999996e-06 0.8764545971165527
+parallel 6.988800000000001e-06 0.9112280222442637
+ vector 2.4559100000000003e-05 3.2021148295986572
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -992,7 +992,7 @@ 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: 0.017863
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019169
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1033,7 +1033,7 @@ 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: 3.421262
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.247187
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1098,7 +1098,7 @@ 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: 0.303684
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.326988
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1157,7 +1157,7 @@ already cache friendly from our previous optimizations.</p>
<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: 0.335182
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.353425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1212,7 +1212,7 @@ 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: 0.115062
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.124741
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1288,7 +1288,7 @@ 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: 0.108361
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108710
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1362,7 +1362,7 @@ 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: 0.110699
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111546
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1429,7 +1429,7 @@ 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: 0.146580
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146937
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ 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 3.421261704 1.0
- blocking 0.30368355 0.08876361303929062
- vectorization 0.33518173139999996 0.097970211108995
-loop permutation 0.11506181280000001 0.03363139764066409
- array packing 0.10836136290000001 0.031672924282088184
- block caching 0.11069907539999999 0.03235621387003956
- parallelization 0.1465796965 0.04284375449227546
+ none 3.2471866261000004 1.0
+ blocking 0.32698844779999997 0.1006990005353422
+ vectorization 0.3534247574 0.10884029718503649
+loop permutation 0.124740865 0.038415058745736065
+ array packing 0.10871017270000001 0.033478264484775005
+ block caching 0.1115463012 0.034351675479142856
+ parallelization 0.1469365568 0.04525041943045836
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1529,7 +1529,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.016 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>